diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json index 06ff398..35d06e0 100644 --- a/.claude-plugin/marketplace.json +++ b/.claude-plugin/marketplace.json @@ -6,7 +6,7 @@ }, "metadata": { "description": "Claude scientific skills from K-Dense Inc", - "version": "2.11.0" + "version": "2.11.1" }, "plugins": [ { diff --git a/scientific-skills/adaptyv/SKILL.md b/scientific-skills/adaptyv/SKILL.md index 7fa94a1..1e694de 100644 --- a/scientific-skills/adaptyv/SKILL.md +++ b/scientific-skills/adaptyv/SKILL.md @@ -1,6 +1,8 @@ --- name: adaptyv description: Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation. +metadata: + skill-author: K-Dense Inc. --- # Adaptyv diff --git a/scientific-skills/aeon/SKILL.md b/scientific-skills/aeon/SKILL.md index 5301375..dda56ff 100644 --- a/scientific-skills/aeon/SKILL.md +++ b/scientific-skills/aeon/SKILL.md @@ -1,6 +1,8 @@ --- name: aeon description: This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs. +metadata: + skill-author: K-Dense Inc. --- # Aeon Time Series Machine Learning diff --git a/scientific-skills/alphafold-database/SKILL.md b/scientific-skills/alphafold-database/SKILL.md index bca3c86..d7269d4 100644 --- a/scientific-skills/alphafold-database/SKILL.md +++ b/scientific-skills/alphafold-database/SKILL.md @@ -1,6 +1,8 @@ --- name: alphafold-database description: "Access AlphaFold's 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology." +metadata: + skill-author: K-Dense Inc. --- # AlphaFold Database diff --git a/scientific-skills/anndata/SKILL.md b/scientific-skills/anndata/SKILL.md index 42dc505..44957e7 100644 --- a/scientific-skills/anndata/SKILL.md +++ b/scientific-skills/anndata/SKILL.md @@ -1,6 +1,8 @@ --- name: anndata description: This skill should be used when working with annotated data matrices in Python, particularly for single-cell genomics analysis, managing experimental measurements with metadata, or handling large-scale biological datasets. Use when tasks involve AnnData objects, h5ad files, single-cell RNA-seq data, or integration with scanpy/scverse tools. +metadata: + skill-author: K-Dense Inc. --- # AnnData diff --git a/scientific-skills/arboreto/SKILL.md b/scientific-skills/arboreto/SKILL.md index 454afa6..1545099 100644 --- a/scientific-skills/arboreto/SKILL.md +++ b/scientific-skills/arboreto/SKILL.md @@ -1,6 +1,8 @@ --- name: arboreto description: Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets. +metadata: + skill-author: K-Dense Inc. --- # Arboreto diff --git a/scientific-skills/astropy/SKILL.md b/scientific-skills/astropy/SKILL.md index 10a7a24..e1fa05d 100644 --- a/scientific-skills/astropy/SKILL.md +++ b/scientific-skills/astropy/SKILL.md @@ -1,6 +1,8 @@ --- name: astropy description: Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing. +metadata: + skill-author: K-Dense Inc. --- # Astropy diff --git a/scientific-skills/benchling-integration/SKILL.md b/scientific-skills/benchling-integration/SKILL.md index 4a0cf7a..062d691 100644 --- a/scientific-skills/benchling-integration/SKILL.md +++ b/scientific-skills/benchling-integration/SKILL.md @@ -1,6 +1,8 @@ --- name: benchling-integration description: "Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation." +metadata: + skill-author: K-Dense Inc. --- # Benchling Integration diff --git a/scientific-skills/biomni/SKILL.md b/scientific-skills/biomni/SKILL.md index 33a6268..6ee5671 100644 --- a/scientific-skills/biomni/SKILL.md +++ b/scientific-skills/biomni/SKILL.md @@ -1,6 +1,8 @@ --- name: biomni description: Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases. +metadata: + skill-author: K-Dense Inc. --- # Biomni diff --git a/scientific-skills/biopython/SKILL.md b/scientific-skills/biopython/SKILL.md index 16fc6dd..b721261 100644 --- a/scientific-skills/biopython/SKILL.md +++ b/scientific-skills/biopython/SKILL.md @@ -1,6 +1,8 @@ --- name: biopython description: "Primary Python toolkit for molecular biology. Preferred for Python-based PubMed/NCBI queries (Bio.Entrez), sequence manipulation, file parsing (FASTA, GenBank, FASTQ, PDB), advanced BLAST workflows, structures, phylogenetics. For quick BLAST, use gget. For direct REST API, use pubmed-database." +metadata: + skill-author: K-Dense Inc. --- # Biopython: Computational Molecular Biology in Python diff --git a/scientific-skills/biorxiv-database/SKILL.md b/scientific-skills/biorxiv-database/SKILL.md index 440ed50..206a262 100644 --- a/scientific-skills/biorxiv-database/SKILL.md +++ b/scientific-skills/biorxiv-database/SKILL.md @@ -1,6 +1,8 @@ --- name: biorxiv-database description: Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews. +metadata: + skill-author: K-Dense Inc. --- # bioRxiv Database diff --git a/scientific-skills/bioservices/SKILL.md b/scientific-skills/bioservices/SKILL.md index 13bc348..95c9993 100644 --- a/scientific-skills/bioservices/SKILL.md +++ b/scientific-skills/bioservices/SKILL.md @@ -1,6 +1,8 @@ --- name: bioservices description: "Primary Python tool for 40+ bioinformatics services. Preferred for multi-database workflows: UniProt, KEGG, ChEMBL, PubChem, Reactome, QuickGO. Unified API for queries, ID mapping, pathway analysis. For direct REST control, use individual database skills (uniprot-database, kegg-database)." +metadata: + skill-author: K-Dense Inc. --- # BioServices diff --git a/scientific-skills/brenda-database/SKILL.md b/scientific-skills/brenda-database/SKILL.md index 3b7b6a2..e5b053e 100644 --- a/scientific-skills/brenda-database/SKILL.md +++ b/scientific-skills/brenda-database/SKILL.md @@ -1,6 +1,8 @@ --- name: brenda-database description: "Access BRENDA enzyme database via SOAP API. Retrieve kinetic parameters (Km, kcat), reaction equations, organism data, and substrate-specific enzyme information for biochemical research and metabolic pathway analysis." +metadata: + skill-author: K-Dense Inc. --- # BRENDA Database diff --git a/scientific-skills/cellxgene-census/SKILL.md b/scientific-skills/cellxgene-census/SKILL.md index a769633..e0e77a5 100644 --- a/scientific-skills/cellxgene-census/SKILL.md +++ b/scientific-skills/cellxgene-census/SKILL.md @@ -1,6 +1,8 @@ --- name: cellxgene-census description: "Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, integrate with scanpy/PyTorch, for population-scale single-cell analysis." +metadata: + skill-author: K-Dense Inc. --- # CZ CELLxGENE Census diff --git a/scientific-skills/chembl-database/SKILL.md b/scientific-skills/chembl-database/SKILL.md index afb919f..ce938f6 100644 --- a/scientific-skills/chembl-database/SKILL.md +++ b/scientific-skills/chembl-database/SKILL.md @@ -1,6 +1,8 @@ --- name: chembl-database description: "Query ChEMBL's bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry." +metadata: + skill-author: K-Dense Inc. --- # ChEMBL Database diff --git a/scientific-skills/cirq/SKILL.md b/scientific-skills/cirq/SKILL.md index b22fb8b..2decb69 100644 --- a/scientific-skills/cirq/SKILL.md +++ b/scientific-skills/cirq/SKILL.md @@ -1,6 +1,8 @@ --- name: cirq description: Quantum computing framework for building, simulating, optimizing, and executing quantum circuits. Use this skill when working with quantum algorithms, quantum circuit design, quantum simulation (noiseless or noisy), running on quantum hardware (Google, IonQ, AQT, Pasqal), circuit optimization and compilation, noise modeling and characterization, or quantum experiments and benchmarking (VQE, QAOA, QPE, randomized benchmarking). +metadata: + skill-author: K-Dense Inc. --- # Cirq - Quantum Computing with Python diff --git a/scientific-skills/citation-management/SKILL.md b/scientific-skills/citation-management/SKILL.md index 1d54881..5fb75e8 100644 --- a/scientific-skills/citation-management/SKILL.md +++ b/scientific-skills/citation-management/SKILL.md @@ -2,6 +2,8 @@ name: citation-management description: Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing. allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Citation Management diff --git a/scientific-skills/clinical-decision-support/SKILL.md b/scientific-skills/clinical-decision-support/SKILL.md index 41448ac..0fab080 100644 --- a/scientific-skills/clinical-decision-support/SKILL.md +++ b/scientific-skills/clinical-decision-support/SKILL.md @@ -2,6 +2,8 @@ name: clinical-decision-support description: "Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Clinical Decision Support Documents diff --git a/scientific-skills/clinical-reports/IMPLEMENTATION_SUMMARY.md b/scientific-skills/clinical-reports/IMPLEMENTATION_SUMMARY.md deleted file mode 100644 index 1068b6b..0000000 --- a/scientific-skills/clinical-reports/IMPLEMENTATION_SUMMARY.md +++ /dev/null @@ -1,641 +0,0 @@ -# Clinical Reports Skill - Implementation Summary - -## ๐Ÿ“Š Overview - -Successfully implemented a comprehensive clinical reports skill for the Claude Scientific Writer project. - -**Implementation Date**: November 4, 2025 -**Total Files Created**: 30 -**Total Lines of Code/Documentation**: 11,577 -**Status**: โœ… Complete and tested - ---- - -## ๐Ÿ“‚ Structure - -``` -.claude/skills/clinical-reports/ -โ”œโ”€โ”€ README.md (Quick start guide) -โ”œโ”€โ”€ SKILL.md (Main skill definition - 1,089 lines) -โ”œโ”€โ”€ references/ (8 comprehensive guides) -โ”‚ โ”œโ”€โ”€ case_report_guidelines.md (571 lines) -โ”‚ โ”œโ”€โ”€ diagnostic_reports_standards.md (531 lines) -โ”‚ โ”œโ”€โ”€ clinical_trial_reporting.md (694 lines) -โ”‚ โ”œโ”€โ”€ patient_documentation.md (745 lines) -โ”‚ โ”œโ”€โ”€ regulatory_compliance.md (578 lines) -โ”‚ โ”œโ”€โ”€ medical_terminology.md (589 lines) -โ”‚ โ”œโ”€โ”€ data_presentation.md (531 lines) -โ”‚ โ””โ”€โ”€ peer_review_standards.md (586 lines) -โ”œโ”€โ”€ assets/ (12 professional templates) -โ”‚ โ”œโ”€โ”€ case_report_template.md (353 lines) -โ”‚ โ”œโ”€โ”€ soap_note_template.md (254 lines) -โ”‚ โ”œโ”€โ”€ history_physical_template.md (244 lines) -โ”‚ โ”œโ”€โ”€ discharge_summary_template.md (338 lines) -โ”‚ โ”œโ”€โ”€ consult_note_template.md (249 lines) -โ”‚ โ”œโ”€โ”€ radiology_report_template.md (317 lines) -โ”‚ โ”œโ”€โ”€ pathology_report_template.md (261 lines) -โ”‚ โ”œโ”€โ”€ lab_report_template.md (349 lines) -โ”‚ โ”œโ”€โ”€ clinical_trial_sae_template.md (437 lines) -โ”‚ โ”œโ”€โ”€ clinical_trial_csr_template.md (304 lines) -โ”‚ โ”œโ”€โ”€ quality_checklist.md (301 lines) -โ”‚ โ””โ”€โ”€ hipaa_compliance_checklist.md (367 lines) -โ””โ”€โ”€ scripts/ (8 validation tools) - โ”œโ”€โ”€ validate_case_report.py (198 lines) - โ”œโ”€โ”€ check_deidentification.py (250 lines) - โ”œโ”€โ”€ validate_trial_report.py (95 lines) - โ”œโ”€โ”€ format_adverse_events.py (120 lines) - โ”œโ”€โ”€ generate_report_template.py (159 lines) - โ”œโ”€โ”€ extract_clinical_data.py (97 lines) - โ”œโ”€โ”€ compliance_checker.py (88 lines) - โ””โ”€โ”€ terminology_validator.py (125 lines) -``` - ---- - -## โœ… Completed Deliverables - -### 1. Main Skill File โœ“ - -**SKILL.md** (1,089 lines) -- YAML frontmatter with name and description -- Comprehensive overview and usage guidelines -- Four major sections (case reports, diagnostic, trials, patient docs) -- CARE guidelines implementation -- ICH-E3 and CONSORT compliance -- HIPAA privacy and de-identification -- Regulatory compliance (FDA, ICH-GCP) -- Medical terminology standards -- Quality assurance principles -- Integration with other skills -- Complete workflows and checklists - -### 2. Reference Documentation โœ“ - -**8 comprehensive reference files (total 4,825 lines)** - -1. **case_report_guidelines.md** (571 lines) - - Complete CARE checklist (17 items) - - Journal-specific requirements - - De-identification best practices - - Privacy and ethics guidelines - - Literature search strategies - - Submission process - -2. **diagnostic_reports_standards.md** (531 lines) - - ACR radiology standards - - Structured reporting (BI-RADS, Lung-RADS, LI-RADS, PI-RADS) - - CAP pathology protocols - - Synoptic reporting elements - - Laboratory reporting (CLSI) - - LOINC coding - - Critical value reporting - -3. **clinical_trial_reporting.md** (694 lines) - - ICH-E3 complete structure - - CONSORT guidelines - - SAE reporting requirements - - MedDRA coding - - DSMB procedures - - Regulatory timelines - - Causality assessment methods - -4. **patient_documentation.md** (745 lines) - - SOAP note structure - - H&P comprehensive template - - Discharge summary requirements - - ROS (Review of Systems) - - Documentation standards - - Billing considerations - -5. **regulatory_compliance.md** (578 lines) - - HIPAA Privacy Rule - - 18 HIPAA identifiers - - Safe Harbor de-identification - - 21 CFR Part 11 (electronic records) - - ICH-GCP principles - - FDA regulations - - EU CTR requirements - -6. **medical_terminology.md** (589 lines) - - SNOMED-CT - - LOINC codes - - ICD-10-CM - - CPT codes - - Standard abbreviations - - "Do Not Use" list (Joint Commission) - - Anatomical terminology - - Laboratory units and conversions - - Grading/staging systems - -7. **data_presentation.md** (531 lines) - - Clinical tables design - - Demographics tables - - Adverse events tables - - CONSORT flow diagrams - - Kaplan-Meier curves - - Forest plots - - Statistical presentation - - Software recommendations - -8. **peer_review_standards.md** (586 lines) - - Review criteria for clinical manuscripts - - CARE guideline compliance - - CONSORT compliance - - STARD guidelines - - STROBE guidelines - - Statistical assessment - - Writing quality evaluation - -### 3. Professional Templates โœ“ - -**12 templates (total 3,574 lines)** - -All templates include: -- Complete structure with all required sections -- Placeholder text with examples -- Formatting guidelines -- Checklists for completeness -- Regulatory compliance notes -- Best practices - -**Templates created:** -1. Case report (CARE-compliant) -2. SOAP note (progress documentation) -3. History & Physical -4. Discharge summary -5. Consultation note -6. Radiology report -7. Pathology report (with synoptic reporting) -8. Laboratory report -9. SAE report (serious adverse event) -10. CSR outline (ICH-E3) -11. Quality checklist -12. HIPAA compliance checklist - -### 4. Validation Scripts โœ“ - -**8 Python scripts (total 1,132 lines)** - -All scripts include: -- Command-line interface -- JSON output option -- Error handling -- Help documentation -- Executable permissions set - -**Scripts created:** -1. **validate_case_report.py** - CARE compliance checker - - Validates 12+ CARE requirements - - Checks word count (1500-3500) - - Verifies references present - - Scans for HIPAA identifiers - - Generates compliance report - -2. **check_deidentification.py** - HIPAA identifier scanner - - Detects all 18 HIPAA identifiers - - Severity classification (Critical/High/Medium) - - Age compliance checking (>89 aggregation) - - Detailed violation reporting - -3. **validate_trial_report.py** - ICH-E3 structure validator - - Checks 15 ICH-E3 sections - - Calculates compliance rate - - Pass/fail determination - -4. **format_adverse_events.py** - AE table generator - - Converts CSV to formatted markdown tables - - Calculates percentages - - Grouped by treatment arm - - Publication-ready output - -5. **generate_report_template.py** - Interactive template generator - - Lists all 10 template types - - Interactive selection mode - - Command-line mode - - Automatic file copying - -6. **extract_clinical_data.py** - Data extraction tool - - Extracts vital signs - - Parses demographics - - Extracts medications - - JSON output - -7. **compliance_checker.py** - Regulatory compliance - - HIPAA compliance checks - - GCP compliance checks - - FDA compliance checks - - Pattern-based validation - -8. **terminology_validator.py** - Medical terminology validation - - "Do Not Use" abbreviation detection - - Ambiguous abbreviation flagging - - ICD-10 code detection - - Severity classification - ---- - -## ๐ŸŽฏ Key Features Implemented - -### Complete Coverage - -โœ… **Clinical Case Reports** -- CARE guidelines (all 17 checklist items) -- De-identification (18 HIPAA identifiers) -- Informed consent documentation -- Timeline creation -- Journal-specific formatting - -โœ… **Diagnostic Reports** -- Radiology (ACR standards, Lung-RADS, BI-RADS, LI-RADS, PI-RADS) -- Pathology (CAP synoptic reporting, TNM staging) -- Laboratory (LOINC coding, critical values, reference ranges) - -โœ… **Clinical Trial Reports** -- SAE reporting (7-day, 15-day timelines) -- ICH-E3 Clinical Study Reports (15 sections) -- CONSORT compliance -- MedDRA coding -- Causality assessment (WHO-UMC, Naranjo) - -โœ… **Patient Documentation** -- SOAP notes (S-O-A-P structure) -- History & Physical (13 components) -- Discharge summaries (10 required elements) -- Consultation notes - -### Regulatory Compliance - -โœ… **HIPAA** -- Safe Harbor de-identification -- 18 identifier removal -- Privacy protection -- Breach notification - -โœ… **FDA** -- 21 CFR Part 11 (electronic records) -- 21 CFR Part 50 (informed consent) -- 21 CFR Part 56 (IRB standards) -- 21 CFR Part 312 (IND regulations) - -โœ… **ICH-GCP** -- Good Clinical Practice principles -- Essential documents -- Source documentation -- Record retention - -### Medical Standards - -โœ… **Terminology** -- SNOMED-CT -- LOINC -- ICD-10-CM -- CPT codes -- RxNorm - -โœ… **Professional Organizations** -- ACR (American College of Radiology) -- CAP (College of American Pathologists) -- CLSI (Clinical Laboratory Standards Institute) -- JCAHO (Joint Commission) - ---- - -## ๐Ÿ”— Integration - -### With Existing Skills - -The clinical-reports skill integrates with: -- โœ… `scientific-writing` - Medical writing principles -- โœ… `peer-review` - Quality assessment -- โœ… `citation-management` - Literature references -- โœ… `research-grants` - Clinical trial protocols - -### MCP System - -- โœ… Skill accessible via MCP find_helpful_skills -- โœ… Compatible with existing skill structure -- โœ… Follows established patterns -- โœ… Auto-loaded by the system - ---- - -## ๐Ÿ“ Documentation Updates - -### Files Updated - -1. โœ… **README.md** - - Added clinical reports to features - - Added example command - - Added to document types table - - Updated "What's New" section - -2. โœ… **docs/SKILLS.md** - - Added Section 6: Clinical Reports (comprehensive) - - Renumbered subsequent sections (7-14) - - Added example usage for all report types - - Included all templates, references, and scripts - -3. โœ… **docs/FEATURES.md** - - Added Clinical Reports section - - Listed 4 report types - - Added key features - - Included usage examples - -4. โœ… **CHANGELOG.md** - - Added [Unreleased] section - - Documented new clinical-reports skill - - Listed all components and features - - Noted documentation updates - -5. โœ… **clinical-reports/README.md** (New) - - Quick start guide - - Template usage examples - - Script usage instructions - - Best practices - - Integration information - ---- - -## โœจ Highlights - -### Templates from Real-World Sources - -Templates based on: -- โœ… BMJ Case Reports (CARE guidelines) -- โœ… Journal of Osteopathic Medicine -- โœ… ACR radiology standards -- โœ… CAP pathology protocols -- โœ… ICH-E3 clinical study reports -- โœ… FDA guidance documents -- โœ… Academic medical centers - -### Comprehensive Reference Materials - -- 8 reference files totaling **4,825 lines** -- Covers all major standards and guidelines -- Includes practical examples throughout -- Cross-referenced between files -- Professional organization standards - -### Robust Validation Tools - -- 8 Python scripts totaling **1,132 lines** -- All executable and tested -- JSON output for automation -- Human-readable reports -- Error handling included - -### Professional Quality - -- Medical accuracy verified against standards -- Regulatory compliance built-in -- Industry-standard formatting -- Professional medical terminology -- Evidence-based best practices - ---- - -## ๐Ÿงช Testing - -### Verified - -โœ… Directory structure created correctly -โœ… All 30 files present -โœ… Scripts executable (chmod +x) -โœ… Template generator script functional -โœ… MCP skill discovery working -โœ… Integration with existing skills -โœ… Documentation updated across project - -### Script Tests - -โœ… **generate_report_template.py** - Lists all 10 template types correctly -โœ… File paths resolve properly -โœ… Python syntax valid (no import errors expected) -โœ… Command-line arguments work - ---- - -## ๐Ÿ“š Statistics - -### Content Breakdown - -| Category | Count | Lines | -|----------|-------|-------| -| Main skill file | 1 | 1,089 | -| Reference files | 8 | 4,825 | -| Template files | 12 | 3,574 | -| Python scripts | 8 | 1,132 | -| README | 1 | 197 | -| **Total** | **30** | **11,817** | - -### Reference Files Statistics - -| File | Lines | Coverage | -|------|-------|----------| -| patient_documentation.md | 745 | SOAP, H&P, discharge | -| clinical_trial_reporting.md | 694 | ICH-E3, CONSORT, SAE | -| medical_terminology.md | 589 | SNOMED, LOINC, ICD-10 | -| peer_review_standards.md | 586 | Review criteria | -| regulatory_compliance.md | 578 | HIPAA, FDA, GCP | -| case_report_guidelines.md | 571 | CARE guidelines | -| data_presentation.md | 531 | Tables, figures | -| diagnostic_reports_standards.md | 531 | ACR, CAP, CLSI | - -### Template Files Statistics - -| Template | Lines | Purpose | -|----------|-------|---------| -| clinical_trial_sae_template.md | 437 | Adverse event reporting | -| hipaa_compliance_checklist.md | 367 | Privacy verification | -| case_report_template.md | 353 | Journal case reports | -| lab_report_template.md | 349 | Laboratory results | -| discharge_summary_template.md | 338 | Hospital discharge | -| radiology_report_template.md | 317 | Imaging reports | -| clinical_trial_csr_template.md | 304 | Study reports | -| quality_checklist.md | 301 | QA for all types | -| pathology_report_template.md | 261 | Surgical pathology | -| soap_note_template.md | 254 | Progress notes | -| consult_note_template.md | 249 | Consultations | -| history_physical_template.md | 244 | H&P examination | - ---- - -## ๐Ÿš€ Usage Examples - -### Generate a Clinical Case Report - -```bash -# Interactive template generation -python scripts/generate_report_template.py -# Select: 1 (case_report) - -# Or via CLI -> Create a clinical case report for unusual presentation of acute appendicitis -``` - -### Validate Reports - -```bash -# Check CARE compliance -python scripts/validate_case_report.py my_report.md - -# Check de-identification -python scripts/check_deidentification.py my_report.md - -# Check trial report structure -python scripts/validate_trial_report.py my_csr.md -``` - -### Generate Documentation - -```bash -# SOAP note -> Create a SOAP note for follow-up diabetes visit - -# Discharge summary -> Generate discharge summary for CHF patient - -# SAE report -> Write serious adverse event report for clinical trial -``` - ---- - -## ๐Ÿ“‹ Standards Covered - -### Medical Standards -- โœ… CARE (CAse REport) guidelines -- โœ… ACR (American College of Radiology) -- โœ… CAP (College of American Pathologists) -- โœ… CLSI (Clinical Laboratory Standards Institute) -- โœ… CONSORT (clinical trial reporting) -- โœ… STARD (diagnostic accuracy) -- โœ… STROBE (observational studies) -- โœ… PRISMA (systematic reviews) - -### Regulatory Standards -- โœ… HIPAA Privacy Rule -- โœ… FDA 21 CFR Part 11 (electronic records) -- โœ… FDA 21 CFR Part 50 (informed consent) -- โœ… FDA 21 CFR Part 56 (IRB) -- โœ… FDA 21 CFR Part 312 (IND) -- โœ… ICH-E3 (clinical study reports) -- โœ… ICH-E6 (GCP) -- โœ… EU CTR 536/2014 - -### Coding Systems -- โœ… SNOMED-CT (clinical terms) -- โœ… LOINC (lab observations) -- โœ… ICD-10-CM (diagnoses) -- โœ… CPT (procedures) -- โœ… RxNorm (medications) -- โœ… MedDRA (adverse events) - ---- - -## ๐ŸŽ“ Educational Value - -### Learning Resources - -Each reference file serves as: -- Comprehensive learning material -- Quick reference guide -- Implementation checklist -- Best practices repository - -### Skill Development - -Supports development of: -- Medical writing skills -- Clinical documentation -- Regulatory knowledge -- Quality assurance -- Privacy compliance - ---- - -## ๐Ÿ”„ Next Steps - -### For Users - -1. Use the skill via CLI: `scientific-writer` -2. Generate templates: `python scripts/generate_report_template.py` -3. Validate reports before submission -4. Follow CARE/ICH-E3/HIPAA guidelines - -### For Developers - -1. Skill is ready for use in production -2. Scripts can be extended with additional features -3. Templates can be customized for specific institutions -4. Reference files can be updated as standards evolve - -### Future Enhancements (Optional) - -- [ ] Add institutional-specific templates -- [ ] Integrate with EHR systems -- [ ] Add more validation rules -- [ ] Create web-based template generator -- [ ] Add support for additional languages -- [ ] Integrate with medical terminology APIs - ---- - -## โœ… Quality Assurance - -### Code Quality -โœ… Python scripts follow PEP 8 style -โœ… Comprehensive error handling -โœ… Command-line argument parsing -โœ… JSON output for automation -โœ… Human-readable reports -โœ… Executable permissions set - -### Documentation Quality -โœ… Clear structure and organization -โœ… Comprehensive coverage -โœ… Real-world examples -โœ… Professional medical terminology -โœ… Cross-referenced between files -โœ… Consistent formatting - -### Template Quality -โœ… Based on professional standards -โœ… Complete with all required elements -โœ… Placeholder text with examples -โœ… Checklists included -โœ… Regulatory notes -โœ… Best practices documented - ---- - -## ๐Ÿ“– Documentation Summary - -| Document | Status | Content | -|----------|--------|---------| -| README.md (main) | โœ… Updated | Added clinical reports to features and examples | -| docs/SKILLS.md | โœ… Updated | Added Section 6 with full documentation | -| docs/FEATURES.md | โœ… Updated | Added clinical reports section with examples | -| CHANGELOG.md | โœ… Updated | Added [Unreleased] section documenting new skill | -| clinical-reports/README.md | โœ… Created | Quick start guide for the skill | -| clinical-reports/SKILL.md | โœ… Created | Main skill definition (1,089 lines) | - ---- - -## ๐ŸŽ‰ Success Metrics - -- โœ… 100% of planned deliverables completed -- โœ… All templates based on real-world standards -- โœ… Comprehensive regulatory compliance coverage -- โœ… Fully functional validation tools -- โœ… Complete integration with existing skills -- โœ… Professional-quality documentation -- โœ… Ready for immediate use - ---- - -**Implementation completed successfully on November 4, 2025** - -The clinical-reports skill is now fully integrated into the Claude Scientific Writer project and ready for use! - diff --git a/scientific-skills/clinical-reports/README.md b/scientific-skills/clinical-reports/README.md deleted file mode 100644 index 865798f..0000000 --- a/scientific-skills/clinical-reports/README.md +++ /dev/null @@ -1,236 +0,0 @@ -# Clinical Reports Skill - -## Overview - -Comprehensive skill for writing clinical reports including case reports, diagnostic reports, clinical trial reports, and patient documentation. Provides full support with templates, regulatory compliance, and validation tools. - -## What's Included - -### ๐Ÿ“‹ Four Major Report Types - -1. **Clinical Case Reports** - CARE-compliant case reports for medical journal publication -2. **Diagnostic Reports** - Radiology (ACR), pathology (CAP), and laboratory reports -3. **Clinical Trial Reports** - SAE reports, Clinical Study Reports (ICH-E3), DSMB reports -4. **Patient Documentation** - SOAP notes, H&P, discharge summaries, consultation notes - -### ๐Ÿ“š Reference Files (8 comprehensive guides) - -- `case_report_guidelines.md` - CARE guidelines, de-identification, journal requirements -- `diagnostic_reports_standards.md` - ACR, CAP, CLSI standards, structured reporting systems -- `clinical_trial_reporting.md` - ICH-E3, CONSORT, SAE reporting, MedDRA coding -- `patient_documentation.md` - SOAP notes, H&P, discharge summary standards -- `regulatory_compliance.md` - HIPAA, 21 CFR Part 11, ICH-GCP, FDA regulations -- `medical_terminology.md` - SNOMED-CT, LOINC, ICD-10, CPT codes -- `data_presentation.md` - Clinical tables, figures, Kaplan-Meier curves -- `peer_review_standards.md` - Review criteria for clinical manuscripts - -### ๐Ÿ“„ Templates (12 professional templates) - -- `case_report_template.md` - Structured case report following CARE guidelines -- `soap_note_template.md` - SOAP progress note format -- `history_physical_template.md` - Complete H&P examination template -- `discharge_summary_template.md` - Hospital discharge documentation -- `consult_note_template.md` - Specialist consultation format -- `radiology_report_template.md` - Imaging report with structured reporting -- `pathology_report_template.md` - Surgical pathology with CAP synoptic elements -- `lab_report_template.md` - Clinical laboratory test results -- `clinical_trial_sae_template.md` - Serious adverse event report form -- `clinical_trial_csr_template.md` - Clinical study report outline (ICH-E3) -- `quality_checklist.md` - Quality assurance for all report types -- `hipaa_compliance_checklist.md` - Privacy and de-identification verification - -### ๐Ÿ”ง Validation Scripts (8 automation tools) - -- `validate_case_report.py` - Check CARE guideline compliance and completeness -- `check_deidentification.py` - Scan for 18 HIPAA identifiers in reports -- `validate_trial_report.py` - Verify ICH-E3 structure and required elements -- `format_adverse_events.py` - Generate AE summary tables from CSV data -- `generate_report_template.py` - Interactive template selection and generation -- `extract_clinical_data.py` - Parse and extract structured clinical data -- `compliance_checker.py` - Verify regulatory compliance requirements -- `terminology_validator.py` - Validate medical terminology and prohibited abbreviations - -## Quick Start - -### Generate a Template - -```bash -cd .claude/skills/clinical-reports/scripts -python generate_report_template.py - -# Or specify type directly -python generate_report_template.py --type case_report --output my_case_report.md -``` - -### Validate a Case Report - -```bash -python validate_case_report.py my_case_report.md -``` - -### Check De-identification - -```bash -python check_deidentification.py my_case_report.md -``` - -### Validate Clinical Trial Report - -```bash -python validate_trial_report.py my_csr.md -``` - -## Key Features - -### CARE Guidelines Compliance -- Complete CARE checklist coverage -- De-identification verification -- Informed consent documentation -- Timeline creation assistance -- Literature review integration - -### Regulatory Compliance -- **HIPAA** - Privacy protection, 18 identifier removal, Safe Harbor method -- **FDA** - 21 CFR Parts 11, 50, 56, 312 compliance -- **ICH-GCP** - Good Clinical Practice standards -- **ALCOA-CCEA** - Data integrity principles - -### Professional Standards -- **ACR** - American College of Radiology reporting standards -- **CAP** - College of American Pathologists synoptic reporting -- **CLSI** - Clinical Laboratory Standards Institute -- **CONSORT** - Clinical trial reporting -- **ICH-E3** - Clinical study report structure - -### Medical Coding Systems -- **ICD-10-CM** - Diagnosis coding -- **CPT** - Procedure coding -- **SNOMED-CT** - Clinical terminology -- **LOINC** - Laboratory observation codes -- **MedDRA** - Medical dictionary for regulatory activities - -## Common Use Cases - -### 1. Publishing a Clinical Case Report - -``` -> Create a clinical case report for a 65-year-old patient with atypical - presentation of acute appendicitis - -> Check this case report for HIPAA compliance -> Validate against CARE guidelines -``` - -### 2. Writing Diagnostic Reports - -``` -> Generate a radiology report template for chest CT -> Create a pathology report for colon resection specimen with adenocarcinoma -> Write a laboratory report for complete blood count -``` - -### 3. Clinical Trial Documentation - -``` -> Write a serious adverse event report for hospitalization due to pneumonia -> Create a clinical study report outline for phase 3 diabetes trial -> Generate adverse events summary table from trial data -``` - -### 4. Patient Clinical Notes - -``` -> Create a SOAP note for follow-up visit -> Generate an H&P for patient admitted with chest pain -> Write a discharge summary for heart failure hospitalization -> Create a cardiology consultation note -``` - -## Workflow Examples - -### Case Report Workflow - -1. **Obtain informed consent** from patient -2. **Generate template**: `python generate_report_template.py --type case_report` -3. **Write case report** following CARE structure -4. **Validate compliance**: `python validate_case_report.py case_report.md` -5. **Check de-identification**: `python check_deidentification.py case_report.md` -6. **Submit to journal** with CARE checklist - -### Clinical Trial SAE Workflow - -1. **Generate SAE template**: `python generate_report_template.py --type sae` -2. **Complete SAE form** within 24 hours of event -3. **Assess causality** using WHO-UMC or Naranjo criteria -4. **Validate completeness**: `python validate_trial_report.py sae_report.md` -5. **Submit to sponsor** within regulatory timelines (7 or 15 days) -6. **Notify IRB** per institutional policy - -## Best Practices - -### Privacy and Ethics -โœ“ Always obtain informed consent for case reports -โœ“ Remove all 18 HIPAA identifiers before publication -โœ“ Use de-identification validation scripts -โœ“ Document consent in manuscript -โœ“ Consider re-identification risk for rare conditions - -### Clinical Quality -โœ“ Use professional medical terminology -โœ“ Follow structured reporting templates -โœ“ Include all required elements -โœ“ Document chronology clearly -โœ“ Support diagnoses with evidence - -### Regulatory Compliance -โœ“ Meet SAE reporting timelines (7-day, 15-day) -โœ“ Follow ICH-E3 structure for CSRs -โœ“ Maintain ALCOA-CCEA data integrity -โœ“ Document protocol adherence -โœ“ Use MedDRA coding for adverse events - -### Documentation Standards -โœ“ Sign and date all clinical notes -โœ“ Document medical necessity -โœ“ Use standard abbreviations only -โœ“ Avoid prohibited abbreviations (JCAHO "Do Not Use" list) -โœ“ Maintain legibility and completeness - -## Integration - -The clinical-reports skill integrates seamlessly with: - -- **scientific-writing** - For clear, professional medical writing -- **peer-review** - For quality assessment of case reports -- **citation-management** - For literature references in case reports -- **research-grants** - For clinical trial protocol development - -## Resources - -### External Standards -- CARE Guidelines: https://www.care-statement.org/ -- ICH-E3 Guideline: https://database.ich.org/sites/default/files/E3_Guideline.pdf -- CONSORT Statement: http://www.consort-statement.org/ -- HIPAA: https://www.hhs.gov/hipaa/ -- ACR Practice Parameters: https://www.acr.org/Clinical-Resources/Practice-Parameters-and-Technical-Standards -- CAP Cancer Protocols: https://www.cap.org/protocols-and-guidelines - -### Professional Organizations -- American Medical Association (AMA) -- American College of Radiology (ACR) -- College of American Pathologists (CAP) -- Clinical Laboratory Standards Institute (CLSI) -- International Council for Harmonisation (ICH) - -## Support - -For issues or questions about the clinical-reports skill: -1. Check the comprehensive reference files -2. Review templates for examples -3. Run validation scripts to identify issues -4. Consult the SKILL.md for detailed guidance - -## License - -Part of the Claude Scientific Writer project. See main LICENSE file. - diff --git a/scientific-skills/clinical-reports/SKILL.md b/scientific-skills/clinical-reports/SKILL.md index 996281a..c8b6259 100644 --- a/scientific-skills/clinical-reports/SKILL.md +++ b/scientific-skills/clinical-reports/SKILL.md @@ -2,6 +2,8 @@ name: clinical-reports description: "Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Clinical Report Writing diff --git a/scientific-skills/clinicaltrials-database/SKILL.md b/scientific-skills/clinicaltrials-database/SKILL.md index 54723c6..c9e57f9 100644 --- a/scientific-skills/clinicaltrials-database/SKILL.md +++ b/scientific-skills/clinicaltrials-database/SKILL.md @@ -1,6 +1,8 @@ --- name: clinicaltrials-database description: "Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching." +metadata: + skill-author: K-Dense Inc. --- # ClinicalTrials.gov Database diff --git a/scientific-skills/clinpgx-database/SKILL.md b/scientific-skills/clinpgx-database/SKILL.md index e3aa7c0..baeca06 100644 --- a/scientific-skills/clinpgx-database/SKILL.md +++ b/scientific-skills/clinpgx-database/SKILL.md @@ -1,6 +1,8 @@ --- name: clinpgx-database description: "Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions." +metadata: + skill-author: K-Dense Inc. --- # ClinPGx Database diff --git a/scientific-skills/clinvar-database/SKILL.md b/scientific-skills/clinvar-database/SKILL.md index 79cf40d..f959f69 100644 --- a/scientific-skills/clinvar-database/SKILL.md +++ b/scientific-skills/clinvar-database/SKILL.md @@ -1,6 +1,8 @@ --- name: clinvar-database description: "Query NCBI ClinVar for variant clinical significance. Search by gene/position, interpret pathogenicity classifications, access via E-utilities API or FTP, annotate VCFs, for genomic medicine." +metadata: + skill-author: K-Dense Inc. --- # ClinVar Database diff --git a/scientific-skills/cobrapy/SKILL.md b/scientific-skills/cobrapy/SKILL.md index 07135c2..140aeaa 100644 --- a/scientific-skills/cobrapy/SKILL.md +++ b/scientific-skills/cobrapy/SKILL.md @@ -1,6 +1,8 @@ --- name: cobrapy description: "Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis." +metadata: + skill-author: K-Dense Inc. --- # COBRApy - Constraint-Based Reconstruction and Analysis diff --git a/scientific-skills/cosmic-database/SKILL.md b/scientific-skills/cosmic-database/SKILL.md index 4f4a854..daa71ca 100644 --- a/scientific-skills/cosmic-database/SKILL.md +++ b/scientific-skills/cosmic-database/SKILL.md @@ -1,6 +1,8 @@ --- name: cosmic-database description: "Access COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions, for cancer research and precision oncology. Requires authentication." +metadata: + skill-author: K-Dense Inc. --- # COSMIC Database diff --git a/scientific-skills/dask/SKILL.md b/scientific-skills/dask/SKILL.md index 2903a85..ba921a6 100644 --- a/scientific-skills/dask/SKILL.md +++ b/scientific-skills/dask/SKILL.md @@ -1,6 +1,8 @@ --- name: dask description: "Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows." +metadata: + skill-author: K-Dense Inc. --- # Dask diff --git a/scientific-skills/datacommons-client/SKILL.md b/scientific-skills/datacommons-client/SKILL.md index 1617577..34b7f1a 100644 --- a/scientific-skills/datacommons-client/SKILL.md +++ b/scientific-skills/datacommons-client/SKILL.md @@ -1,6 +1,8 @@ --- name: datacommons-client description: Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities. +metadata: + skill-author: K-Dense Inc. --- # Data Commons Client diff --git a/scientific-skills/datamol/SKILL.md b/scientific-skills/datamol/SKILL.md index e9c6d61..873eea8 100644 --- a/scientific-skills/datamol/SKILL.md +++ b/scientific-skills/datamol/SKILL.md @@ -1,6 +1,8 @@ --- name: datamol description: "Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery: SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly." +metadata: + skill-author: K-Dense Inc. --- # Datamol Cheminformatics Skill diff --git a/scientific-skills/deepchem/SKILL.md b/scientific-skills/deepchem/SKILL.md index 557095e..25e5d7f 100644 --- a/scientific-skills/deepchem/SKILL.md +++ b/scientific-skills/deepchem/SKILL.md @@ -1,6 +1,8 @@ --- name: deepchem description: "Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML." +metadata: + skill-author: K-Dense Inc. --- # DeepChem diff --git a/scientific-skills/deeptools/SKILL.md b/scientific-skills/deeptools/SKILL.md index 4ee7ab1..78f4af8 100644 --- a/scientific-skills/deeptools/SKILL.md +++ b/scientific-skills/deeptools/SKILL.md @@ -1,6 +1,8 @@ --- name: deeptools description: "NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization." +metadata: + skill-author: K-Dense Inc. --- # deepTools: NGS Data Analysis Toolkit diff --git a/scientific-skills/denario/SKILL.md b/scientific-skills/denario/SKILL.md index 044ecdc..073d3a2 100644 --- a/scientific-skills/denario/SKILL.md +++ b/scientific-skills/denario/SKILL.md @@ -1,6 +1,8 @@ --- name: denario description: Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration. +metadata: + skill-author: K-Dense Inc. --- # Denario diff --git a/scientific-skills/diffdock/SKILL.md b/scientific-skills/diffdock/SKILL.md index 8ae09f7..5b1e668 100644 --- a/scientific-skills/diffdock/SKILL.md +++ b/scientific-skills/diffdock/SKILL.md @@ -1,6 +1,8 @@ --- name: diffdock description: "Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction." +metadata: + skill-author: K-Dense Inc. --- # DiffDock: Molecular Docking with Diffusion Models diff --git a/scientific-skills/dnanexus-integration/SKILL.md b/scientific-skills/dnanexus-integration/SKILL.md index 619c373..c638089 100644 --- a/scientific-skills/dnanexus-integration/SKILL.md +++ b/scientific-skills/dnanexus-integration/SKILL.md @@ -1,6 +1,8 @@ --- name: dnanexus-integration description: "DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution." +metadata: + skill-author: K-Dense Inc. --- # DNAnexus Integration diff --git a/scientific-skills/drugbank-database/SKILL.md b/scientific-skills/drugbank-database/SKILL.md index 488daa0..78fa9f8 100644 --- a/scientific-skills/drugbank-database/SKILL.md +++ b/scientific-skills/drugbank-database/SKILL.md @@ -1,6 +1,8 @@ --- name: drugbank-database description: Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data. This skill should be used when working with pharmaceutical data, drug discovery research, pharmacology studies, drug-drug interaction analysis, target identification, chemical similarity searches, ADMET predictions, or any task requiring detailed drug and drug target information from DrugBank. +metadata: + skill-author: K-Dense Inc. --- # DrugBank Database diff --git a/scientific-skills/ena-database/SKILL.md b/scientific-skills/ena-database/SKILL.md index 91b5928..a68cf32 100644 --- a/scientific-skills/ena-database/SKILL.md +++ b/scientific-skills/ena-database/SKILL.md @@ -1,6 +1,8 @@ --- name: ena-database description: "Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats." +metadata: + skill-author: K-Dense Inc. --- # ENA Database diff --git a/scientific-skills/ensembl-database/SKILL.md b/scientific-skills/ensembl-database/SKILL.md index 2359900..796e8f3 100644 --- a/scientific-skills/ensembl-database/SKILL.md +++ b/scientific-skills/ensembl-database/SKILL.md @@ -1,6 +1,8 @@ --- name: ensembl-database description: "Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research." +metadata: + skill-author: K-Dense Inc. --- # Ensembl Database diff --git a/scientific-skills/esm/SKILL.md b/scientific-skills/esm/SKILL.md index 9e205c1..f6f06a9 100644 --- a/scientific-skills/esm/SKILL.md +++ b/scientific-skills/esm/SKILL.md @@ -1,6 +1,8 @@ --- name: esm description: Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference. +metadata: + skill-author: K-Dense Inc. --- # ESM: Evolutionary Scale Modeling diff --git a/scientific-skills/etetoolkit/SKILL.md b/scientific-skills/etetoolkit/SKILL.md index 7686243..1dd8314 100644 --- a/scientific-skills/etetoolkit/SKILL.md +++ b/scientific-skills/etetoolkit/SKILL.md @@ -1,6 +1,8 @@ --- name: etetoolkit description: "Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics." +metadata: + skill-author: K-Dense Inc. --- # ETE Toolkit Skill diff --git a/scientific-skills/exploratory-data-analysis/SKILL.md b/scientific-skills/exploratory-data-analysis/SKILL.md index e6a23d4..a5d93bb 100644 --- a/scientific-skills/exploratory-data-analysis/SKILL.md +++ b/scientific-skills/exploratory-data-analysis/SKILL.md @@ -1,6 +1,8 @@ --- name: exploratory-data-analysis description: Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats. +metadata: + skill-author: K-Dense Inc. --- # Exploratory Data Analysis diff --git a/scientific-skills/fda-database/SKILL.md b/scientific-skills/fda-database/SKILL.md index cfebdc9..9e999ea 100644 --- a/scientific-skills/fda-database/SKILL.md +++ b/scientific-skills/fda-database/SKILL.md @@ -1,6 +1,8 @@ --- name: fda-database description: "Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research." +metadata: + skill-author: K-Dense Inc. --- # FDA Database Access diff --git a/scientific-skills/flowio/SKILL.md b/scientific-skills/flowio/SKILL.md index 3d09045..9985da9 100644 --- a/scientific-skills/flowio/SKILL.md +++ b/scientific-skills/flowio/SKILL.md @@ -1,6 +1,8 @@ --- name: flowio description: "Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing." +metadata: + skill-author: K-Dense Inc. --- # FlowIO: Flow Cytometry Standard File Handler diff --git a/scientific-skills/fluidsim/SKILL.md b/scientific-skills/fluidsim/SKILL.md index cdf16a6..f689a09 100644 --- a/scientific-skills/fluidsim/SKILL.md +++ b/scientific-skills/fluidsim/SKILL.md @@ -1,6 +1,8 @@ --- name: fluidsim description: Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis. +metadata: + skill-author: K-Dense Inc. --- # FluidSim diff --git a/scientific-skills/gene-database/SKILL.md b/scientific-skills/gene-database/SKILL.md index bade9be..8c09d76 100644 --- a/scientific-skills/gene-database/SKILL.md +++ b/scientific-skills/gene-database/SKILL.md @@ -1,6 +1,8 @@ --- name: gene-database description: "Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis." +metadata: + skill-author: K-Dense Inc. --- # Gene Database diff --git a/scientific-skills/generate-image/SKILL.md b/scientific-skills/generate-image/SKILL.md index 12dff2d..862410e 100644 --- a/scientific-skills/generate-image/SKILL.md +++ b/scientific-skills/generate-image/SKILL.md @@ -1,6 +1,8 @@ --- name: generate-image description: Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that isn't a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead. +metadata: + skill-author: K-Dense Inc. --- # Generate Image diff --git a/scientific-skills/geniml/SKILL.md b/scientific-skills/geniml/SKILL.md index c369f99..5efa878 100644 --- a/scientific-skills/geniml/SKILL.md +++ b/scientific-skills/geniml/SKILL.md @@ -1,6 +1,8 @@ --- name: geniml description: This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning. +metadata: + skill-author: K-Dense Inc. --- # Geniml: Genomic Interval Machine Learning diff --git a/scientific-skills/geo-database/SKILL.md b/scientific-skills/geo-database/SKILL.md index 09890e1..655d374 100644 --- a/scientific-skills/geo-database/SKILL.md +++ b/scientific-skills/geo-database/SKILL.md @@ -1,6 +1,8 @@ --- name: geo-database description: "Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis." +metadata: + skill-author: K-Dense Inc. --- # GEO Database diff --git a/scientific-skills/geopandas/SKILL.md b/scientific-skills/geopandas/SKILL.md index fe5ee5c..6d01f2c 100644 --- a/scientific-skills/geopandas/SKILL.md +++ b/scientific-skills/geopandas/SKILL.md @@ -1,6 +1,8 @@ --- name: geopandas description: Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats. +metadata: + skill-author: K-Dense Inc. --- # GeoPandas diff --git a/scientific-skills/get-available-resources/SKILL.md b/scientific-skills/get-available-resources/SKILL.md index 82a3efa..38e9b33 100644 --- a/scientific-skills/get-available-resources/SKILL.md +++ b/scientific-skills/get-available-resources/SKILL.md @@ -1,6 +1,8 @@ --- name: get-available-resources description: This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter. +metadata: + skill-author: K-Dense Inc. --- # Get Available Resources diff --git a/scientific-skills/gget/SKILL.md b/scientific-skills/gget/SKILL.md index 7e4ecff..812cf6c 100644 --- a/scientific-skills/gget/SKILL.md +++ b/scientific-skills/gget/SKILL.md @@ -1,6 +1,8 @@ --- name: gget description: "CLI/Python toolkit for rapid bioinformatics queries. Preferred for quick BLAST searches. Access to 20+ databases: gene info (Ensembl/UniProt), AlphaFold, ARCHS4, Enrichr, OpenTargets, COSMIC, genome downloads. For advanced BLAST/batch processing, use biopython. For multi-database integration, use bioservices." +metadata: + skill-author: K-Dense Inc. --- # gget diff --git a/scientific-skills/gtars/SKILL.md b/scientific-skills/gtars/SKILL.md index bdbc967..d3fd2a7 100644 --- a/scientific-skills/gtars/SKILL.md +++ b/scientific-skills/gtars/SKILL.md @@ -1,6 +1,8 @@ --- name: gtars description: High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications. +metadata: + skill-author: K-Dense Inc. --- # Gtars: Genomic Tools and Algorithms in Rust diff --git a/scientific-skills/gwas-database/SKILL.md b/scientific-skills/gwas-database/SKILL.md index 7dc8038..d4abcd3 100644 --- a/scientific-skills/gwas-database/SKILL.md +++ b/scientific-skills/gwas-database/SKILL.md @@ -1,6 +1,8 @@ --- name: gwas-database description: "Query NHGRI-EBI GWAS Catalog for SNP-trait associations. Search variants by rs ID, disease/trait, gene, retrieve p-values and summary statistics, for genetic epidemiology and polygenic risk scores." +metadata: + skill-author: K-Dense Inc. --- # GWAS Catalog Database diff --git a/scientific-skills/histolab/SKILL.md b/scientific-skills/histolab/SKILL.md index 74d233b..d907ee0 100644 --- a/scientific-skills/histolab/SKILL.md +++ b/scientific-skills/histolab/SKILL.md @@ -1,6 +1,8 @@ --- name: histolab description: Digital pathology image processing toolkit for whole slide images (WSI). Use this skill when working with histopathology slides, processing H&E or IHC stained tissue images, extracting tiles from gigapixel pathology images, detecting tissue regions, segmenting tissue masks, or preparing datasets for computational pathology deep learning pipelines. Applies to WSI formats (SVS, TIFF, NDPI), tile-based analysis, and histological image preprocessing workflows. +metadata: + skill-author: K-Dense Inc. --- # Histolab diff --git a/scientific-skills/hmdb-database/SKILL.md b/scientific-skills/hmdb-database/SKILL.md index 0582de3..6f292a4 100644 --- a/scientific-skills/hmdb-database/SKILL.md +++ b/scientific-skills/hmdb-database/SKILL.md @@ -1,6 +1,8 @@ --- name: hmdb-database description: "Access Human Metabolome Database (220K+ metabolites). Search by name/ID/structure, retrieve chemical properties, biomarker data, NMR/MS spectra, pathways, for metabolomics and identification." +metadata: + skill-author: K-Dense Inc. --- # HMDB Database diff --git a/scientific-skills/hypogenic/SKILL.md b/scientific-skills/hypogenic/SKILL.md index 05c5b97..d4674fd 100644 --- a/scientific-skills/hypogenic/SKILL.md +++ b/scientific-skills/hypogenic/SKILL.md @@ -1,6 +1,8 @@ --- name: hypogenic description: Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against observational data, or conducting systematic hypothesis exploration for research discovery in domains like deception detection, AI content detection, mental health analysis, or other empirical research tasks. +metadata: + skill-author: K-Dense Inc. --- # Hypogenic diff --git a/scientific-skills/hypothesis-generation/SKILL.md b/scientific-skills/hypothesis-generation/SKILL.md index b3ad479..9342b05 100644 --- a/scientific-skills/hypothesis-generation/SKILL.md +++ b/scientific-skills/hypothesis-generation/SKILL.md @@ -2,6 +2,8 @@ name: hypothesis-generation description: "Generate testable hypotheses. Formulate from observations, design experiments, explore competing explanations, develop predictions, propose mechanisms, for scientific inquiry across domains." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Scientific Hypothesis Generation diff --git a/scientific-skills/iso-13485-certification/SKILL.md b/scientific-skills/iso-13485-certification/SKILL.md index f5593bd..5006043 100644 --- a/scientific-skills/iso-13485-certification/SKILL.md +++ b/scientific-skills/iso-13485-certification/SKILL.md @@ -1,6 +1,8 @@ --- name: iso-13485-certification description: Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work instructions, (4) preparing Medical Device Files, (5) understanding ISO 13485 requirements, or (6) identifying missing documentation for medical device certification. Also use when users mention medical device regulations, QMS certification, FDA QMSR, EU MDR, or need help with quality system documentation. +metadata: + skill-author: K-Dense Inc. --- # ISO 13485 Certification Documentation Assistant diff --git a/scientific-skills/kegg-database/SKILL.md b/scientific-skills/kegg-database/SKILL.md index 9a96cf0..b6a9e03 100644 --- a/scientific-skills/kegg-database/SKILL.md +++ b/scientific-skills/kegg-database/SKILL.md @@ -1,6 +1,8 @@ --- name: kegg-database description: "Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control." +metadata: + skill-author: K-Dense Inc. --- # KEGG Database diff --git a/scientific-skills/labarchive-integration/SKILL.md b/scientific-skills/labarchive-integration/SKILL.md index aafa95d..3d4a4eb 100644 --- a/scientific-skills/labarchive-integration/SKILL.md +++ b/scientific-skills/labarchive-integration/SKILL.md @@ -1,6 +1,8 @@ --- name: labarchive-integration description: "Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows." +metadata: + skill-author: K-Dense Inc. --- # LabArchives Integration diff --git a/scientific-skills/lamindb/SKILL.md b/scientific-skills/lamindb/SKILL.md index a9341bc..2b4ff01 100644 --- a/scientific-skills/lamindb/SKILL.md +++ b/scientific-skills/lamindb/SKILL.md @@ -1,6 +1,8 @@ --- name: lamindb description: This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies. +metadata: + skill-author: K-Dense Inc. --- # LaminDB diff --git a/scientific-skills/latchbio-integration/SKILL.md b/scientific-skills/latchbio-integration/SKILL.md index 36d837d..39f866d 100644 --- a/scientific-skills/latchbio-integration/SKILL.md +++ b/scientific-skills/latchbio-integration/SKILL.md @@ -1,6 +1,8 @@ --- name: latchbio-integration description: "Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration." +metadata: + skill-author: K-Dense Inc. --- # LatchBio Integration diff --git a/scientific-skills/latex-posters/README.md b/scientific-skills/latex-posters/README.md deleted file mode 100644 index 64ecc9d..0000000 --- a/scientific-skills/latex-posters/README.md +++ /dev/null @@ -1,417 +0,0 @@ -# LaTeX Research Poster Generation Skill - -Create professional, publication-ready research posters for conferences and academic presentations using LaTeX. - -## Overview - -This skill provides comprehensive guidance for creating research posters with three major LaTeX packages: -- **beamerposter**: Traditional academic posters, familiar Beamer syntax -- **tikzposter**: Modern, colorful designs with TikZ integration -- **baposter**: Structured multi-column layouts with automatic positioning - -## Quick Start - -### 1. Choose a Template - -Browse templates in `assets/`: -- `beamerposter_template.tex` - Classic academic style -- `tikzposter_template.tex` - Modern, colorful design -- `baposter_template.tex` - Structured multi-column layout - -### 2. Customize Content - -Edit the template with your research: -- Title, authors, affiliations -- Introduction, methods, results, conclusions -- Replace placeholder figures with your images -- Update references and acknowledgments - -### 3. Configure for Full Page - -Posters should span the entire page with minimal margins: - -```latex -% beamerposter - full page setup -\documentclass[final,t]{beamer} -\usepackage[size=a0,scale=1.4,orientation=portrait]{beamerposter} -\setbeamersize{text margin left=5mm, text margin right=5mm} -\usepackage[margin=10mm]{geometry} - -% tikzposter - full page setup -\documentclass[25pt,a0paper,portrait,margin=10mm,innermargin=15mm]{tikzposter} - -% baposter - full page setup -\documentclass[a0paper,portrait,fontscale=0.285]{baposter} -``` - -### 4. Compile - -```bash -pdflatex poster.tex - -# Or for better font support: -lualatex poster.tex -xelatex poster.tex -``` - -### 5. Review PDF Quality - -**Essential before printing!** - -```bash -# Run automated checks -./scripts/review_poster.sh poster.pdf - -# Manual verification (see checklist below) -``` - -## Key Features - -### Full Page Coverage - -All templates configured to maximize content area: -- Minimal outer margins (5-15mm) -- Optimal spacing between columns (15-20mm) -- Proper block padding for readability -- No wasted white space - -### PDF Quality Control - -**Automated Checks** (`review_poster.sh`): -- Page size verification -- Font embedding check -- Image resolution analysis -- File size optimization - -**Manual Verification** (`assets/poster_quality_checklist.md`): -- Visual inspection at 100% zoom -- Reduced-scale print test (25%) -- Typography and spacing review -- Content completeness check - -### Design Principles - -All templates follow evidence-based poster design: -- **Typography**: 72pt+ title, 48-72pt headers, 24-36pt body text -- **Color**: High contrast (โ‰ฅ4.5:1), color-blind friendly palettes -- **Layout**: Clear visual hierarchy, logical flow -- **Content**: 300-800 words maximum, 40-50% visual content - -## Common Poster Sizes - -Templates support all standard sizes: - -| Size | Dimensions | Configuration | -|------|------------|---------------| -| A0 | 841 ร— 1189 mm | `size=a0` or `a0paper` | -| A1 | 594 ร— 841 mm | `size=a1` or `a1paper` | -| 36ร—48" | 914 ร— 1219 mm | Custom page size | -| 42ร—56" | 1067 ร— 1422 mm | Custom page size | - -## Documentation - -### Reference Guides - -**Comprehensive Documentation** (in `references/`): - -1. **`latex_poster_packages.md`** (746 lines) - - Detailed comparison of beamerposter, tikzposter, baposter - - Package-specific syntax and examples - - Strengths, limitations, best use cases - - Theme and color customization - - Compilation tips and troubleshooting - -2. **`poster_design_principles.md`** (807 lines) - - Visual hierarchy and white space - - Typography: font selection, sizing, readability - - Color theory: schemes, contrast, accessibility - - Color-blind friendly palettes - - Icons, graphics, and visual elements - - Common design mistakes to avoid - -3. **`poster_layout_design.md`** (650+ lines) - - Grid systems (2, 3, 4-column layouts) - - Visual flow and reading patterns - - Spatial organization strategies - - White space management - - Block and box design - - Layout patterns by research type - -4. **`poster_content_guide.md`** (900+ lines) - - Content strategy (3-5 minute rule) - - Word budgets by section - - Visual-to-text ratio (40-50% visual) - - Section-specific writing guidance - - Figure integration and captions - - From paper to poster adaptation - -### Tools and Assets - -**Scripts** (in `scripts/`): -- `review_poster.sh`: Automated PDF quality check - - Page size verification - - Font embedding check - - Image resolution analysis - - File size assessment - -**Checklists** (in `assets/`): -- `poster_quality_checklist.md`: Comprehensive pre-printing checklist - - Pre-compilation checks - - PDF quality verification - - Visual inspection items - - Accessibility checks - - Peer review guidelines - - Final printing checklist - -**Templates** (in `assets/`): -- `beamerposter_template.tex`: Full working template -- `tikzposter_template.tex`: Full working template -- `baposter_template.tex`: Full working template - -## Workflow - -### Recommended Poster Creation Process - -**1. Planning** (before LaTeX) -- Determine conference requirements (size, orientation) -- Identify 3-5 key results to highlight -- Create figures (300+ DPI) -- Draft 300-800 word content outline - -**2. Template Selection** -- Choose package based on needs: - - **beamerposter**: Traditional conferences, institutional branding - - **tikzposter**: Modern conferences, creative fields - - **baposter**: Multi-section posters, structured layouts - -**3. Content Integration** -- Copy template and customize -- Replace placeholder text -- Add figures and ensure high resolution -- Configure colors to match branding - -**4. Compilation & Review** -- Compile to PDF -- Run `review_poster.sh` for automated checks -- Review visually at 100% zoom -- Check against `poster_quality_checklist.md` - -**5. Test Print** -- **Critical step!** Print at 25% scale -- A0 โ†’ A4 paper, 36ร—48" โ†’ Letter paper -- View from 2-3 feet (simulates 8-12 feet for full poster) -- Verify readability and colors - -**6. Revisions** -- Fix any issues identified -- Proofread carefully (errors are magnified!) -- Get colleague feedback -- Final compilation - -**7. Printing** -- Verify page size: `pdfinfo poster.pdf` -- Check fonts embedded: `pdffonts poster.pdf` -- Send to professional printer 2-3 days before deadline -- Keep backup copy - -## Troubleshooting - -### Large White Margins - -**Problem**: Excessive white space around poster edges - -**Solution**: -```latex -% beamerposter -\setbeamersize{text margin left=5mm, text margin right=5mm} -\usepackage[margin=10mm]{geometry} - -% tikzposter -\documentclass[..., margin=5mm, innermargin=10mm]{tikzposter} - -% baposter -\documentclass[a0paper, margin=5mm]{baposter} -``` - -### Content Cut Off - -**Problem**: Text or figures extending beyond page - -**Solution**: -- Check total width: columns + spacing + margins = pagewidth -- Reduce column widths or spacing -- Debug with visible page boundary: -```latex -\usepackage{eso-pic} -\AddToShipoutPictureBG{ - \AtPageLowerLeft{ - \put(0,0){\framebox(\LenToUnit{\paperwidth},\LenToUnit{\paperheight}){}} - } -} -``` - -### Blurry Images - -**Problem**: Pixelated or low-quality figures - -**Solution**: -- Use vector graphics (PDF, SVG) when possible -- Raster images: minimum 300 DPI at final print size -- For A0 width (33.1"): 300 DPI = 9930 pixels minimum -- Check with: `pdfimages -list poster.pdf` - -### Fonts Not Embedded - -**Problem**: Printer rejects PDF due to missing fonts - -**Solution**: -```bash -# Recompile with embedded fonts -pdflatex -dEmbedAllFonts=true poster.tex - -# Verify embedding -pdffonts poster.pdf -# All fonts should show "yes" in "emb" column -``` - -### File Too Large - -**Problem**: PDF exceeds email size limit (>50MB) - -**Solution**: -```bash -# Compress for digital sharing -gs -sDEVICE=pdfwrite -dCompatibilityLevel=1.4 \ - -dPDFSETTINGS=/printer -dNOPAUSE -dQUIET -dBATCH \ - -sOutputFile=poster_compressed.pdf poster.pdf - -# Keep original uncompressed version for printing -``` - -## Common Mistakes to Avoid - -### Content -- โŒ Too much text (>1000 words) -- โŒ Font sizes too small (<24pt body text) -- โŒ No clear main message -- โœ… 300-800 words, 30pt+ body text, 1-3 key findings - -### Design -- โŒ Poor color contrast (<4.5:1) -- โŒ Red-green color combinations (color-blind issue) -- โŒ Cluttered layout with no white space -- โœ… High contrast, accessible colors, generous spacing - -### Technical -- โŒ Wrong poster dimensions -- โŒ Low resolution images (<300 DPI) -- โŒ Fonts not embedded -- โœ… Verify specs, high-res images, embedded fonts - -## Package Comparison - -Quick reference for choosing the right package: - -| Feature | beamerposter | tikzposter | baposter | -|---------|--------------|------------|----------| -| **Learning Curve** | Easy (Beamer users) | Moderate | Moderate | -| **Aesthetics** | Traditional | Modern | Professional | -| **Customization** | Moderate | High (TikZ) | Structured | -| **Compilation Speed** | Fast | Slower | Fast-Medium | -| **Best For** | Academic conferences | Creative designs | Multi-column layouts | - -**Recommendation**: -- First-time poster makers: **beamerposter** (familiar, simple) -- Modern conferences: **tikzposter** (beautiful, flexible) -- Complex layouts: **baposter** (automatic positioning) - -## Example Usage - -### In Scientific Writer CLI - -``` -> Create a research poster for NeurIPS conference on transformer attention - -The assistant will: -1. Ask about poster size and orientation -2. Generate complete LaTeX poster with your content -3. Configure for full page coverage -4. Provide compilation instructions -5. Run quality checks on generated PDF -``` - -### Manual Creation - -```bash -# 1. Copy template -cp assets/tikzposter_template.tex my_poster.tex - -# 2. Edit content -vim my_poster.tex - -# 3. Compile -pdflatex my_poster.tex - -# 4. Review -./scripts/review_poster.sh my_poster.pdf - -# 5. Test print at 25% scale -# (A0 on A4 paper) - -# 6. Final printing -``` - -## Tips for Success - -### Content Strategy -1. **One main message**: What's the one thing viewers should remember? -2. **3-5 key figures**: Visual content dominates -3. **300-800 words**: Less is more -4. **Bullet points**: More scannable than paragraphs - -### Design Strategy -1. **High contrast**: Dark on light or light on dark -2. **Large fonts**: 30pt+ body text for readability from distance -3. **White space**: 30-40% of poster should be empty -4. **Visual hierarchy**: Vary sizes significantly (title 3ร— body text) - -### Technical Strategy -1. **Test early**: Print at 25% scale before final printing -2. **Vector graphics**: Use PDF/SVG when possible -3. **Verify specs**: Check page size, fonts, resolution -4. **Get feedback**: Ask colleague to review before printing - -## Additional Resources - -### Online Tools -- **Color contrast checker**: https://webaim.org/resources/contrastchecker/ -- **Color blindness simulator**: https://www.color-blindness.com/coblis-color-blindness-simulator/ -- **Color palette generator**: https://coolors.co/ - -### LaTeX Packages -- `beamerposter`: Extends Beamer for poster-sized documents -- `tikzposter`: Modern poster creation with TikZ -- `baposter`: Box-based automatic poster layout -- `qrcode`: Generate QR codes in LaTeX -- `graphicx`: Include images -- `tcolorbox`: Colored boxes and frames - -### Further Reading -- All reference documents in `references/` directory -- Quality checklist in `assets/poster_quality_checklist.md` -- Package comparison in `references/latex_poster_packages.md` - -## Support - -For issues or questions: -- Review reference documentation in `references/` -- Check troubleshooting section above -- Run automated review: `./scripts/review_poster.sh` -- Use quality checklist: `assets/poster_quality_checklist.md` - -## Version - -LaTeX Poster Skill v1.0 -Compatible with: beamerposter, tikzposter, baposter -Last updated: January 2025 - diff --git a/scientific-skills/latex-posters/SKILL.md b/scientific-skills/latex-posters/SKILL.md index 3ba3ef9..b3d3e2a 100644 --- a/scientific-skills/latex-posters/SKILL.md +++ b/scientific-skills/latex-posters/SKILL.md @@ -2,6 +2,8 @@ name: latex-posters description: "Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # LaTeX Research Posters diff --git a/scientific-skills/literature-review/SKILL.md b/scientific-skills/literature-review/SKILL.md index 9a55eea..70979c0 100644 --- a/scientific-skills/literature-review/SKILL.md +++ b/scientific-skills/literature-review/SKILL.md @@ -2,6 +2,8 @@ name: literature-review description: Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.). allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Literature Review diff --git a/scientific-skills/market-research-reports/SKILL.md b/scientific-skills/market-research-reports/SKILL.md index 90435c0..c4e3848 100644 --- a/scientific-skills/market-research-reports/SKILL.md +++ b/scientific-skills/market-research-reports/SKILL.md @@ -2,6 +2,8 @@ name: market-research-reports description: "Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Market Research Reports diff --git a/scientific-skills/markitdown/INSTALLATION_GUIDE.md b/scientific-skills/markitdown/INSTALLATION_GUIDE.md deleted file mode 100644 index 4bd1fc1..0000000 --- a/scientific-skills/markitdown/INSTALLATION_GUIDE.md +++ /dev/null @@ -1,318 +0,0 @@ -# MarkItDown Installation Guide - -## Prerequisites - -- Python 3.10 or higher -- pip package manager -- Virtual environment (recommended) - -## Basic Installation - -### Install All Features (Recommended) - -```bash -pip install 'markitdown[all]' -``` - -This installs support for all file formats and features. - -### Install Specific Features - -If you only need certain file formats, you can install specific dependencies: - -```bash -# PDF support only -pip install 'markitdown[pdf]' - -# Office documents -pip install 'markitdown[docx,pptx,xlsx]' - -# Multiple formats -pip install 'markitdown[pdf,docx,pptx,xlsx,audio-transcription]' -``` - -### Install from Source - -```bash -git clone https://github.com/microsoft/markitdown.git -cd markitdown -pip install -e 'packages/markitdown[all]' -``` - -## Optional Dependencies - -| Feature | Installation | Use Case | -|---------|--------------|----------| -| All formats | `pip install 'markitdown[all]'` | Everything | -| PDF | `pip install 'markitdown[pdf]'` | PDF documents | -| Word | `pip install 'markitdown[docx]'` | DOCX files | -| PowerPoint | `pip install 'markitdown[pptx]'` | PPTX files | -| Excel (new) | `pip install 'markitdown[xlsx]'` | XLSX files | -| Excel (old) | `pip install 'markitdown[xls]'` | XLS files | -| Outlook | `pip install 'markitdown[outlook]'` | MSG files | -| Azure DI | `pip install 'markitdown[az-doc-intel]'` | Enhanced PDF | -| Audio | `pip install 'markitdown[audio-transcription]'` | WAV/MP3 | -| YouTube | `pip install 'markitdown[youtube-transcription]'` | YouTube videos | - -## System Dependencies - -### OCR Support (for scanned documents and images) - -#### macOS -```bash -brew install tesseract -``` - -#### Ubuntu/Debian -```bash -sudo apt-get update -sudo apt-get install tesseract-ocr -``` - -#### Windows -Download from: https://github.com/UB-Mannheim/tesseract/wiki - -### Poppler Utils (for advanced PDF operations) - -#### macOS -```bash -brew install poppler -``` - -#### Ubuntu/Debian -```bash -sudo apt-get install poppler-utils -``` - -## Verification - -Test your installation: - -```bash -# Check version -python -c "import markitdown; print('MarkItDown installed successfully')" - -# Test basic conversion -echo "Test" > test.txt -markitdown test.txt -rm test.txt -``` - -## Virtual Environment Setup - -### Using venv - -```bash -# Create virtual environment -python -m venv markitdown-env - -# Activate (macOS/Linux) -source markitdown-env/bin/activate - -# Activate (Windows) -markitdown-env\Scripts\activate - -# Install -pip install 'markitdown[all]' -``` - -### Using conda - -```bash -# Create environment -conda create -n markitdown python=3.12 - -# Activate -conda activate markitdown - -# Install -pip install 'markitdown[all]' -``` - -### Using uv - -```bash -# Create virtual environment -uv venv --python=3.12 .venv - -# Activate -source .venv/bin/activate - -# Install -uv pip install 'markitdown[all]' -``` - -## AI Enhancement Setup (Optional) - -For AI-powered image descriptions using OpenRouter: - -### OpenRouter API - -OpenRouter provides unified access to multiple AI models (GPT-4, Claude, Gemini, etc.) through a single API. - -```bash -# Install OpenAI SDK (required, already included with markitdown) -pip install openai - -# Get API key from https://openrouter.ai/keys - -# Set API key -export OPENROUTER_API_KEY="sk-or-v1-..." - -# Add to shell profile for persistence -echo 'export OPENROUTER_API_KEY="sk-or-v1-..."' >> ~/.bashrc # Linux -echo 'export OPENROUTER_API_KEY="sk-or-v1-..."' >> ~/.zshrc # macOS -``` - -**Why OpenRouter?** -- Access to 100+ AI models through one API -- Choose between GPT-4, Claude, Gemini, and more -- Competitive pricing -- No vendor lock-in -- Simple OpenAI-compatible interface - -**Popular Models for Image Description:** -- `anthropic/claude-sonnet-4.5` - **Recommended** - Best for scientific vision -- `anthropic/claude-opus-4.5` - Excellent technical analysis -- `openai/gpt-4o` - Good vision understanding -- `google/gemini-pro-vision` - Cost-effective option - -See https://openrouter.ai/models for complete model list and pricing. - -## Azure Document Intelligence Setup (Optional) - -For enhanced PDF conversion: - -1. Create Azure Document Intelligence resource in Azure Portal -2. Get endpoint and key -3. Set environment variables: - -```bash -export AZURE_DOCUMENT_INTELLIGENCE_KEY="your-key" -export AZURE_DOCUMENT_INTELLIGENCE_ENDPOINT="https://your-endpoint.cognitiveservices.azure.com/" -``` - -## Docker Installation (Alternative) - -```bash -# Clone repository -git clone https://github.com/microsoft/markitdown.git -cd markitdown - -# Build image -docker build -t markitdown:latest . - -# Run -docker run --rm -i markitdown:latest < input.pdf > output.md -``` - -## Troubleshooting - -### Import Error -``` -ModuleNotFoundError: No module named 'markitdown' -``` - -**Solution**: Ensure you're in the correct virtual environment and markitdown is installed: -```bash -pip install 'markitdown[all]' -``` - -### Missing Feature -``` -Error: PDF conversion not supported -``` - -**Solution**: Install the specific feature: -```bash -pip install 'markitdown[pdf]' -``` - -### OCR Not Working - -**Solution**: Install Tesseract OCR (see System Dependencies above) - -### Permission Errors - -**Solution**: Use virtual environment or install with `--user` flag: -```bash -pip install --user 'markitdown[all]' -``` - -## Upgrading - -```bash -# Upgrade to latest version -pip install --upgrade 'markitdown[all]' - -# Check version -pip show markitdown -``` - -## Uninstallation - -```bash -pip uninstall markitdown -``` - -## Next Steps - -After installation: -1. Read `QUICK_REFERENCE.md` for basic usage -2. See `SKILL.md` for comprehensive guide -3. Try example scripts in `scripts/` directory -4. Check `assets/example_usage.md` for practical examples - -## Skill Scripts Setup - -To use the skill scripts: - -```bash -# Navigate to scripts directory -cd /Users/vinayak/Documents/claude-scientific-writer/.claude/skills/markitdown/scripts - -# Scripts are already executable, just run them -python batch_convert.py --help -python convert_with_ai.py --help -python convert_literature.py --help -``` - -## Testing Installation - -Create a test file to verify everything works: - -```python -# test_markitdown.py -from markitdown import MarkItDown - -def test_basic(): - md = MarkItDown() - # Create a simple test file - with open("test.txt", "w") as f: - f.write("Hello MarkItDown!") - - # Convert it - result = md.convert("test.txt") - print("โœ“ Basic conversion works") - print(result.text_content) - - # Cleanup - import os - os.remove("test.txt") - -if __name__ == "__main__": - test_basic() -``` - -Run it: -```bash -python test_markitdown.py -``` - -## Getting Help - -- **Documentation**: See `SKILL.md` and `README.md` -- **GitHub Issues**: https://github.com/microsoft/markitdown/issues -- **Examples**: `assets/example_usage.md` -- **API Reference**: `references/api_reference.md` - diff --git a/scientific-skills/markitdown/LICENSE.txt b/scientific-skills/markitdown/LICENSE.txt deleted file mode 100644 index 72196cb..0000000 --- a/scientific-skills/markitdown/LICENSE.txt +++ /dev/null @@ -1,22 +0,0 @@ -MIT License - -Copyright (c) Microsoft Corporation. - -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to deal -in the Software without restriction, including without limitation the rights -to use, copy, modify, merge, publish, distribute, sublicense, and/or sell -copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in all -copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, -OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE -SOFTWARE. - diff --git a/scientific-skills/markitdown/OPENROUTER_INTEGRATION.md b/scientific-skills/markitdown/OPENROUTER_INTEGRATION.md deleted file mode 100644 index f15af23..0000000 --- a/scientific-skills/markitdown/OPENROUTER_INTEGRATION.md +++ /dev/null @@ -1,359 +0,0 @@ -# OpenRouter Integration for MarkItDown - -## Overview - -This MarkItDown skill has been configured to use **OpenRouter** instead of direct OpenAI API access. OpenRouter provides a unified API gateway to access 100+ AI models from different providers through a single, OpenAI-compatible interface. - -## Why OpenRouter? - -### Benefits - -1. **Multiple Model Access**: Access GPT-4, Claude, Gemini, and 100+ other models through one API -2. **No Vendor Lock-in**: Switch between models without code changes -3. **Competitive Pricing**: Often better rates than going direct -4. **Simple Migration**: OpenAI-compatible API means minimal code changes -5. **Flexible Choice**: Choose the best model for each task - -### Popular Models for Image Description - -| Model | Provider | Use Case | Vision Support | -|-------|----------|----------|----------------| -| `anthropic/claude-sonnet-4.5` | Anthropic | **Recommended** - Best overall for scientific analysis | โœ… | -| `anthropic/claude-opus-4.5` | Anthropic | Excellent technical analysis | โœ… | -| `openai/gpt-4o` | OpenAI | Strong vision understanding | โœ… | -| `openai/gpt-4-vision` | OpenAI | GPT-4 with vision | โœ… | -| `google/gemini-pro-vision` | Google | Cost-effective option | โœ… | - -See https://openrouter.ai/models for the complete list. - -## Getting Started - -### 1. Get an API Key - -1. Visit https://openrouter.ai/keys -2. Sign up or log in -3. Create a new API key -4. Copy the key (starts with `sk-or-v1-...`) - -### 2. Set Environment Variable - -```bash -# Add to your environment -export OPENROUTER_API_KEY="sk-or-v1-..." - -# Make it permanent -echo 'export OPENROUTER_API_KEY="sk-or-v1-..."' >> ~/.zshrc # macOS -echo 'export OPENROUTER_API_KEY="sk-or-v1-..."' >> ~/.bashrc # Linux - -# Reload shell -source ~/.zshrc # or source ~/.bashrc -``` - -### 3. Use in Python - -```python -from markitdown import MarkItDown -from openai import OpenAI - -# Initialize OpenRouter client (OpenAI-compatible) -client = OpenAI( - api_key="your-openrouter-api-key", # or use env var - base_url="https://openrouter.ai/api/v1" -) - -# Create MarkItDown with AI support -md = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5" # Choose your model -) - -# Convert with AI-enhanced descriptions -result = md.convert("presentation.pptx") -print(result.text_content) -``` - -## Using the Scripts - -All skill scripts have been updated to use OpenRouter: - -### convert_with_ai.py - -```bash -# Set API key -export OPENROUTER_API_KEY="sk-or-v1-..." - -# Convert with default model (advanced vision model) -python scripts/convert_with_ai.py paper.pdf output.md --prompt-type scientific - -# Use GPT-4o as alternative -python scripts/convert_with_ai.py paper.pdf output.md \ - --model openai/gpt-4o \ - --prompt-type scientific - -# Use Gemini Pro Vision (cost-effective) -python scripts/convert_with_ai.py slides.pptx output.md \ - --model google/gemini-pro-vision \ - --prompt-type presentation - -# List available prompt types -python scripts/convert_with_ai.py --list-prompts -``` - -### Choosing the Right Model - -```bash -# For scientific papers - use advanced vision model for technical analysis -python scripts/convert_with_ai.py research.pdf output.md \ - --model anthropic/claude-sonnet-4.5 \ - --prompt-type scientific - -# For presentations - use advanced vision model -python scripts/convert_with_ai.py slides.pptx output.md \ - --model anthropic/claude-sonnet-4.5 \ - --prompt-type presentation - -# For data visualizations - use advanced vision model -python scripts/convert_with_ai.py charts.pdf output.md \ - --model anthropic/claude-sonnet-4.5 \ - --prompt-type data_viz - -# For medical images - use advanced vision model for detailed analysis -python scripts/convert_with_ai.py xray.jpg output.md \ - --model anthropic/claude-sonnet-4.5 \ - --prompt-type medical -``` - -## Code Examples - -### Basic Usage - -```python -from markitdown import MarkItDown -from openai import OpenAI -import os - -# Initialize OpenRouter client -client = OpenAI( - api_key=os.environ.get("OPENROUTER_API_KEY"), - base_url="https://openrouter.ai/api/v1" -) - -# Use advanced vision model for image descriptions -md = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5" -) - -result = md.convert("document.pptx") -print(result.text_content) -``` - -### Switching Models Dynamically - -```python -from markitdown import MarkItDown -from openai import OpenAI -import os - -client = OpenAI( - api_key=os.environ["OPENROUTER_API_KEY"], - base_url="https://openrouter.ai/api/v1" -) - -# Use different models for different file types -def convert_with_best_model(filepath): - if filepath.endswith('.pdf'): - # Use advanced vision model for technical PDFs - md = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5", - llm_prompt="Describe scientific figures with technical precision" - ) - elif filepath.endswith('.pptx'): - # Use advanced vision model for presentations - md = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5", - llm_prompt="Describe slide content and visual elements" - ) - else: - # Use advanced vision model as default - md = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5" - ) - - return md.convert(filepath) - -# Use it -result = convert_with_best_model("paper.pdf") -``` - -### Custom Prompts per Model - -```python -from markitdown import MarkItDown -from openai import OpenAI - -client = OpenAI( - api_key="your-openrouter-api-key", - base_url="https://openrouter.ai/api/v1" -) - -# Scientific analysis with advanced vision model -scientific_prompt = """ -Analyze this scientific figure. Provide: -1. Type of visualization and methodology -2. Quantitative data points and trends -3. Statistical significance -4. Technical interpretation -Be precise and use scientific terminology. -""" - -md_scientific = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5", - llm_prompt=scientific_prompt -) - -# Visual analysis with advanced vision model -visual_prompt = """ -Describe this image comprehensively: -1. Main visual elements and composition -2. Colors, layout, and design -3. Text and labels -4. Overall message -""" - -md_visual = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5", - llm_prompt=visual_prompt -) -``` - -## Model Comparison - -### For Scientific Content - -**Recommended: anthropic/claude-sonnet-4.5** -- Excellent at technical analysis -- Superior reasoning capabilities -- Best at understanding scientific figures -- Most detailed and accurate explanations -- Advanced vision capabilities - -**Alternative: openai/gpt-4o** -- Good vision understanding -- Fast processing -- Good at charts and graphs - -### For Presentations - -**Recommended: anthropic/claude-sonnet-4.5** -- Superior vision capabilities -- Excellent at understanding slide layouts -- Fast and reliable -- Best technical comprehension - -### For Cost-Effectiveness - -**Recommended: google/gemini-pro-vision** -- Lower cost per request -- Good quality -- Fast processing - -## Pricing Considerations - -OpenRouter pricing varies by model. Check current rates at https://openrouter.ai/models - -**Tips for Cost Optimization:** -1. Use advanced vision models for best quality on complex scientific content -2. Use cheaper models (Gemini) for simple images -3. Batch process similar content with the same model -4. Use appropriate prompts to get better results in fewer retries - -## Troubleshooting - -### API Key Issues - -```bash -# Check if key is set -echo $OPENROUTER_API_KEY - -# Should show: sk-or-v1-... -# If empty, set it: -export OPENROUTER_API_KEY="sk-or-v1-..." -``` - -### Model Not Found - -If you get a "model not found" error, check: -1. Model name format: `provider/model-name` -2. Model availability: https://openrouter.ai/models -3. Vision support: Ensure model supports vision for image description - -### Rate Limits - -OpenRouter has rate limits. If you hit them: -1. Add delays between requests -2. Use batch processing scripts with `--workers` parameter -3. Consider upgrading your OpenRouter plan - -## Migration Notes - -This skill was updated from direct OpenAI API to OpenRouter. Key changes: - -1. **Environment Variable**: `OPENAI_API_KEY` โ†’ `OPENROUTER_API_KEY` -2. **Client Initialization**: Added `base_url="https://openrouter.ai/api/v1"` -3. **Model Names**: `gpt-4o` โ†’ `openai/gpt-4o` (with provider prefix) -4. **Script Updates**: All scripts now use OpenRouter by default - -## Resources - -- **OpenRouter Website**: https://openrouter.ai -- **Get API Keys**: https://openrouter.ai/keys -- **Model List**: https://openrouter.ai/models -- **Pricing**: https://openrouter.ai/models (click on model for details) -- **Documentation**: https://openrouter.ai/docs -- **Support**: https://openrouter.ai/discord - -## Example Workflow - -Here's a complete workflow using OpenRouter: - -```bash -# 1. Set up API key -export OPENROUTER_API_KEY="sk-or-v1-your-key-here" - -# 2. Convert a scientific paper with Claude -python scripts/convert_with_ai.py \ - research_paper.pdf \ - output.md \ - --model anthropic/claude-opus-4.5 \ - --prompt-type scientific - -# 3. Convert presentation with GPT-4o -python scripts/convert_with_ai.py \ - talk_slides.pptx \ - slides.md \ - --model openai/gpt-4o \ - --prompt-type presentation - -# 4. Batch convert with cost-effective model -python scripts/batch_convert.py \ - images/ \ - markdown_output/ \ - --extensions .jpg .png -``` - -## Support - -For OpenRouter-specific issues: -- Discord: https://openrouter.ai/discord -- Email: support@openrouter.ai - -For MarkItDown skill issues: -- Check documentation in this skill directory -- Review examples in `assets/example_usage.md` - diff --git a/scientific-skills/markitdown/QUICK_REFERENCE.md b/scientific-skills/markitdown/QUICK_REFERENCE.md deleted file mode 100644 index 09e2dc8..0000000 --- a/scientific-skills/markitdown/QUICK_REFERENCE.md +++ /dev/null @@ -1,309 +0,0 @@ -# MarkItDown Quick Reference - -## Installation - -```bash -# All features -pip install 'markitdown[all]' - -# Specific formats -pip install 'markitdown[pdf,docx,pptx,xlsx]' -``` - -## Basic Usage - -```python -from markitdown import MarkItDown - -md = MarkItDown() -result = md.convert("file.pdf") -print(result.text_content) -``` - -## Command Line - -```bash -# Simple conversion -markitdown input.pdf > output.md -markitdown input.pdf -o output.md - -# With plugins -markitdown --use-plugins file.pdf -o output.md -``` - -## Common Tasks - -### Convert PDF -```python -md = MarkItDown() -result = md.convert("paper.pdf") -``` - -### Convert with AI -```python -from openai import OpenAI - -# Use OpenRouter for multiple model access -client = OpenAI( - api_key="your-openrouter-api-key", - base_url="https://openrouter.ai/api/v1" -) - -md = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5" # recommended for vision -) -result = md.convert("slides.pptx") -``` - -### Batch Convert -```bash -python scripts/batch_convert.py input/ output/ --extensions .pdf .docx -``` - -### Literature Conversion -```bash -python scripts/convert_literature.py papers/ markdown/ --create-index -``` - -## Supported Formats - -| Format | Extension | Notes | -|--------|-----------|-------| -| PDF | `.pdf` | Full text + OCR | -| Word | `.docx` | Tables, formatting | -| PowerPoint | `.pptx` | Slides + notes | -| Excel | `.xlsx`, `.xls` | Tables | -| Images | `.jpg`, `.png`, `.gif`, `.webp` | EXIF + OCR | -| Audio | `.wav`, `.mp3` | Transcription | -| HTML | `.html`, `.htm` | Clean conversion | -| Data | `.csv`, `.json`, `.xml` | Structured | -| Archives | `.zip` | Iterates contents | -| E-books | `.epub` | Full text | -| YouTube | URLs | Transcripts | - -## Optional Dependencies - -```bash -[all] # All features -[pdf] # PDF support -[docx] # Word documents -[pptx] # PowerPoint -[xlsx] # Excel -[xls] # Old Excel -[outlook] # Outlook messages -[az-doc-intel] # Azure Document Intelligence -[audio-transcription] # Audio files -[youtube-transcription] # YouTube videos -``` - -## AI-Enhanced Conversion - -### Scientific Papers -```python -from openai import OpenAI - -# Initialize OpenRouter client -client = OpenAI( - api_key="your-openrouter-api-key", - base_url="https://openrouter.ai/api/v1" -) - -md = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5", # recommended for scientific vision - llm_prompt="Describe scientific figures with technical precision" -) -result = md.convert("paper.pdf") -``` - -### Custom Prompts -```python -prompt = """ -Analyze this data visualization. Describe: -- Type of chart/graph -- Key trends and patterns -- Notable data points -""" - -md = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5", - llm_prompt=prompt -) -``` - -### Available Models via OpenRouter -- `anthropic/claude-sonnet-4.5` - **Recommended for scientific vision** -- `anthropic/claude-opus-4.5` - Advanced vision model -- `openai/gpt-4o` - GPT-4 Omni (vision) -- `openai/gpt-4-vision` - GPT-4 Vision -- `google/gemini-pro-vision` - Gemini Pro Vision - -See https://openrouter.ai/models for full list - -## Azure Document Intelligence - -```python -md = MarkItDown(docintel_endpoint="https://YOUR-ENDPOINT.cognitiveservices.azure.com/") -result = md.convert("complex_layout.pdf") -``` - -## Batch Processing - -### Python -```python -from markitdown import MarkItDown -from pathlib import Path - -md = MarkItDown() - -for file in Path("input/").glob("*.pdf"): - result = md.convert(str(file)) - output = Path("output") / f"{file.stem}.md" - output.write_text(result.text_content) -``` - -### Script -```bash -# Parallel conversion -python scripts/batch_convert.py input/ output/ --workers 8 - -# Recursive -python scripts/batch_convert.py input/ output/ -r -``` - -## Error Handling - -```python -try: - result = md.convert("file.pdf") -except FileNotFoundError: - print("File not found") -except Exception as e: - print(f"Error: {e}") -``` - -## Streaming - -```python -with open("large_file.pdf", "rb") as f: - result = md.convert_stream(f, file_extension=".pdf") -``` - -## Common Prompts - -### Scientific -``` -Analyze this scientific figure. Describe: -- Type of visualization -- Key data points and trends -- Axes, labels, and legends -- Scientific significance -``` - -### Medical -``` -Describe this medical image. Include: -- Type of imaging (X-ray, MRI, CT, etc.) -- Anatomical structures visible -- Notable findings -- Clinical relevance -``` - -### Data Visualization -``` -Analyze this data visualization: -- Chart type -- Variables and axes -- Data ranges -- Key patterns and outliers -``` - -## Performance Tips - -1. **Reuse instance**: Create once, use many times -2. **Parallel processing**: Use ThreadPoolExecutor for multiple files -3. **Stream large files**: Use `convert_stream()` for big files -4. **Choose right format**: Install only needed dependencies - -## Environment Variables - -```bash -# OpenRouter for AI-enhanced conversions -export OPENROUTER_API_KEY="sk-or-v1-..." - -# Azure Document Intelligence (optional) -export AZURE_DOCUMENT_INTELLIGENCE_KEY="key..." -export AZURE_DOCUMENT_INTELLIGENCE_ENDPOINT="https://..." -``` - -## Scripts Quick Reference - -### batch_convert.py -```bash -python scripts/batch_convert.py INPUT OUTPUT [OPTIONS] - -Options: - --extensions .pdf .docx File types to convert - --recursive, -r Search subdirectories - --workers 4 Parallel workers - --verbose, -v Detailed output - --plugins, -p Enable plugins -``` - -### convert_with_ai.py -```bash -python scripts/convert_with_ai.py INPUT OUTPUT [OPTIONS] - -Options: - --api-key KEY OpenRouter API key - --model MODEL Model name (default: anthropic/claude-sonnet-4.5) - --prompt-type TYPE Preset prompt (scientific, medical, etc.) - --custom-prompt TEXT Custom prompt - --list-prompts Show available prompts -``` - -### convert_literature.py -```bash -python scripts/convert_literature.py INPUT OUTPUT [OPTIONS] - -Options: - --organize-by-year, -y Organize by year - --create-index, -i Create index file - --recursive, -r Search subdirectories -``` - -## Troubleshooting - -### Missing Dependencies -```bash -pip install 'markitdown[pdf]' # Install PDF support -``` - -### Binary File Error -```python -# Wrong -with open("file.pdf", "r") as f: - -# Correct -with open("file.pdf", "rb") as f: # Binary mode -``` - -### OCR Not Working -```bash -# macOS -brew install tesseract - -# Ubuntu -sudo apt-get install tesseract-ocr -``` - -## More Information - -- **Full Documentation**: See `SKILL.md` -- **API Reference**: See `references/api_reference.md` -- **Format Details**: See `references/file_formats.md` -- **Examples**: See `assets/example_usage.md` -- **GitHub**: https://github.com/microsoft/markitdown - diff --git a/scientific-skills/markitdown/README.md b/scientific-skills/markitdown/README.md deleted file mode 100644 index 9769486..0000000 --- a/scientific-skills/markitdown/README.md +++ /dev/null @@ -1,184 +0,0 @@ -# MarkItDown Skill - -This skill provides comprehensive support for converting various file formats to Markdown using Microsoft's MarkItDown tool. - -## Overview - -MarkItDown is a Python tool that converts files and office documents to Markdown format. This skill includes: - -- Complete API documentation -- Format-specific conversion guides -- Utility scripts for batch processing -- AI-enhanced conversion examples -- Integration with scientific workflows - -## Contents - -### Main Skill File -- **SKILL.md** - Complete guide to using MarkItDown with quick start, examples, and best practices - -### References -- **api_reference.md** - Detailed API documentation, class references, and method signatures -- **file_formats.md** - Format-specific details for all supported file types - -### Scripts -- **batch_convert.py** - Batch convert multiple files with parallel processing -- **convert_with_ai.py** - AI-enhanced conversion with custom prompts -- **convert_literature.py** - Scientific literature conversion with metadata extraction - -### Assets -- **example_usage.md** - Practical examples for common use cases - -## Installation - -```bash -# Install with all features -pip install 'markitdown[all]' - -# Or install specific features -pip install 'markitdown[pdf,docx,pptx,xlsx]' -``` - -## Quick Start - -```python -from markitdown import MarkItDown - -md = MarkItDown() -result = md.convert("document.pdf") -print(result.text_content) -``` - -## Supported Formats - -- **Documents**: PDF, DOCX, PPTX, XLSX, EPUB -- **Images**: JPEG, PNG, GIF, WebP (with OCR) -- **Audio**: WAV, MP3 (with transcription) -- **Web**: HTML, YouTube URLs -- **Data**: CSV, JSON, XML -- **Archives**: ZIP files - -## Key Features - -### 1. AI-Enhanced Conversions -Use AI models via OpenRouter to generate detailed image descriptions: - -```python -from openai import OpenAI - -# OpenRouter provides access to 100+ AI models -client = OpenAI( - api_key="your-openrouter-api-key", - base_url="https://openrouter.ai/api/v1" -) - -md = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5" # recommended for vision -) -result = md.convert("presentation.pptx") -``` - -### 2. Batch Processing -Convert multiple files efficiently: - -```bash -python scripts/batch_convert.py papers/ output/ --extensions .pdf .docx -``` - -### 3. Scientific Literature -Convert and organize research papers: - -```bash -python scripts/convert_literature.py papers/ output/ --organize-by-year --create-index -``` - -### 4. Azure Document Intelligence -Enhanced PDF conversion with Microsoft Document Intelligence: - -```python -md = MarkItDown(docintel_endpoint="https://YOUR-ENDPOINT.cognitiveservices.azure.com/") -result = md.convert("complex_document.pdf") -``` - -## Use Cases - -### Literature Review -Convert research papers to Markdown for easier analysis and note-taking. - -### Data Extraction -Extract tables from Excel files into Markdown format. - -### Presentation Processing -Convert PowerPoint slides with AI-generated descriptions. - -### Document Analysis -Process documents for LLM consumption with token-efficient Markdown. - -### YouTube Transcripts -Fetch and convert YouTube video transcriptions. - -## Scripts Usage - -### Batch Convert -```bash -# Convert all PDFs in a directory -python scripts/batch_convert.py input_dir/ output_dir/ --extensions .pdf - -# Recursive with multiple formats -python scripts/batch_convert.py docs/ markdown/ --extensions .pdf .docx .pptx -r -``` - -### AI-Enhanced Conversion -```bash -# Convert with AI descriptions via OpenRouter -export OPENROUTER_API_KEY="sk-or-v1-..." -python scripts/convert_with_ai.py paper.pdf output.md --prompt-type scientific - -# Use different models -python scripts/convert_with_ai.py image.png output.md --model anthropic/claude-sonnet-4.5 - -# Use custom prompt -python scripts/convert_with_ai.py image.png output.md --custom-prompt "Describe this diagram" -``` - -### Literature Conversion -```bash -# Convert papers with metadata extraction -python scripts/convert_literature.py papers/ markdown/ --organize-by-year --create-index -``` - -## Integration with Scientific Writer - -This skill integrates seamlessly with the Scientific Writer CLI for: -- Converting source materials for paper writing -- Processing literature for reviews -- Extracting data from various document formats -- Preparing documents for LLM analysis - -## Resources - -- **MarkItDown GitHub**: https://github.com/microsoft/markitdown -- **PyPI**: https://pypi.org/project/markitdown/ -- **OpenRouter**: https://openrouter.ai (AI model access) -- **OpenRouter API Keys**: https://openrouter.ai/keys -- **OpenRouter Models**: https://openrouter.ai/models -- **License**: MIT - -## Requirements - -- Python 3.10+ -- Optional dependencies based on formats needed -- OpenRouter API key (for AI-enhanced conversions) - Get at https://openrouter.ai/keys -- Azure subscription (optional, for Document Intelligence) - -## Examples - -See `assets/example_usage.md` for comprehensive examples covering: -- Basic conversions -- Scientific workflows -- AI-enhanced processing -- Batch operations -- Error handling -- Integration patterns - diff --git a/scientific-skills/markitdown/SKILL.md b/scientific-skills/markitdown/SKILL.md index 3ad7f94..2ea0d57 100644 --- a/scientific-skills/markitdown/SKILL.md +++ b/scientific-skills/markitdown/SKILL.md @@ -3,7 +3,8 @@ name: markitdown description: "Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more." allowed-tools: [Read, Write, Edit, Bash] license: MIT -source: https://github.com/microsoft/markitdown +metadata: + skill-author: K-Dense Inc. --- # MarkItDown - File to Markdown Conversion diff --git a/scientific-skills/markitdown/SKILL_SUMMARY.md b/scientific-skills/markitdown/SKILL_SUMMARY.md deleted file mode 100644 index 33612d3..0000000 --- a/scientific-skills/markitdown/SKILL_SUMMARY.md +++ /dev/null @@ -1,307 +0,0 @@ -# MarkItDown Skill - Creation Summary - -## Overview - -A comprehensive skill for using Microsoft's MarkItDown tool has been created for the Claude Scientific Writer. This skill enables conversion of 15+ file formats to Markdown, optimized for LLM processing and scientific workflows. - -## What Was Created - -### Core Documentation - -1. **SKILL.md** (Main skill file) - - Complete guide to MarkItDown - - Quick start examples - - All supported formats - - Advanced features (AI, Azure DI) - - Best practices - - Use cases and examples - -2. **README.md** - - Skill overview - - Key features - - Quick reference - - Integration guide - -3. **QUICK_REFERENCE.md** - - Cheat sheet for common tasks - - Quick syntax reference - - Common commands - - Troubleshooting tips - -4. **INSTALLATION_GUIDE.md** - - Step-by-step installation - - System dependencies - - Virtual environment setup - - Optional features - - Troubleshooting - -### Reference Documentation - -Located in `references/`: - -1. **api_reference.md** - - Complete API documentation - - Class and method references - - Custom converter development - - Plugin system - - Error handling - - Breaking changes guide - -2. **file_formats.md** - - Detailed format-specific guides - - 15+ supported formats - - Format capabilities and limitations - - Best practices per format - - Example outputs - -### Utility Scripts - -Located in `scripts/`: - -1. **batch_convert.py** - - Parallel batch conversion - - Multi-format support - - Recursive directory search - - Progress tracking - - Error reporting - - Command-line interface - -2. **convert_with_ai.py** - - AI-enhanced conversions - - Predefined prompt types (scientific, medical, data viz, etc.) - - Custom prompt support - - Multiple model support - - OpenRouter integration (advanced vision models) - -3. **convert_literature.py** - - Scientific literature conversion - - Metadata extraction from filenames - - Year-based organization - - Automatic index generation - - JSON catalog creation - - Front matter support - -### Assets - -Located in `assets/`: - -1. **example_usage.md** - - 20+ practical examples - - Basic conversions - - Scientific workflows - - AI-enhanced processing - - Batch operations - - Error handling patterns - - Integration examples - -### License - -- **LICENSE.txt** - MIT License from Microsoft - -## Skill Structure - -``` -.claude/skills/markitdown/ -โ”œโ”€โ”€ SKILL.md # Main skill documentation -โ”œโ”€โ”€ README.md # Skill overview -โ”œโ”€โ”€ QUICK_REFERENCE.md # Quick reference guide -โ”œโ”€โ”€ INSTALLATION_GUIDE.md # Installation instructions -โ”œโ”€โ”€ SKILL_SUMMARY.md # This file -โ”œโ”€โ”€ LICENSE.txt # MIT License -โ”œโ”€โ”€ references/ -โ”‚ โ”œโ”€โ”€ api_reference.md # Complete API docs -โ”‚ โ””โ”€โ”€ file_formats.md # Format-specific guides -โ”œโ”€โ”€ scripts/ -โ”‚ โ”œโ”€โ”€ batch_convert.py # Batch conversion utility -โ”‚ โ”œโ”€โ”€ convert_with_ai.py # AI-enhanced conversion -โ”‚ โ””โ”€โ”€ convert_literature.py # Literature conversion -โ””โ”€โ”€ assets/ - โ””โ”€โ”€ example_usage.md # Practical examples -``` - -## Capabilities - -### File Format Support - -- **Documents**: PDF, DOCX, PPTX, XLSX, XLS, EPUB -- **Images**: JPEG, PNG, GIF, WebP (with OCR) -- **Audio**: WAV, MP3 (with transcription) -- **Web**: HTML, YouTube URLs -- **Data**: CSV, JSON, XML -- **Archives**: ZIP files -- **Email**: Outlook MSG files - -### Advanced Features - -1. **AI Enhancement via OpenRouter** - - Access to 100+ AI models through OpenRouter - - Multiple preset prompts (scientific, medical, data viz) - - Custom prompt support - - Default: Advanced vision model (best for scientific vision) - - Choose best model for each task - -2. **Azure Integration** - - Azure Document Intelligence for complex PDFs - - Enhanced layout understanding - - Better table extraction - -3. **Batch Processing** - - Parallel conversion with configurable workers - - Recursive directory processing - - Progress tracking and error reporting - - Format-specific organization - -4. **Scientific Workflows** - - Literature conversion with metadata - - Automatic index generation - - Year-based organization - - Citation-friendly output - -## Integration with Scientific Writer - -The skill has been added to the Scientific Writer's skill catalog: - -- **Location**: `.claude/skills/markitdown/` -- **Skill Number**: #5 in Document Manipulation Skills -- **SKILLS.md**: Updated with complete skill description - -### Usage Examples - -``` -> Convert all PDFs in the literature folder to Markdown -> Convert this PowerPoint presentation to Markdown with AI-generated descriptions -> Extract tables from this Excel file -> Transcribe this lecture recording -``` - -## Scripts Usage - -### Batch Convert -```bash -python scripts/batch_convert.py input_dir/ output_dir/ --extensions .pdf .docx --workers 4 -``` - -### AI-Enhanced Convert -```bash -export OPENROUTER_API_KEY="sk-or-v1-..." -python scripts/convert_with_ai.py paper.pdf output.md \ - --model anthropic/claude-sonnet-4.5 \ - --prompt-type scientific -``` - -### Literature Convert -```bash -python scripts/convert_literature.py papers/ markdown/ --organize-by-year --create-index -``` - -## Key Features - -1. **Token-Efficient Output**: Markdown optimized for LLM processing -2. **Comprehensive Format Support**: 15+ file types -3. **AI Enhancement**: Detailed image descriptions via OpenAI -4. **OCR Support**: Extract text from scanned documents -5. **Audio Transcription**: Speech-to-text for audio files -6. **YouTube Support**: Video transcript extraction -7. **Plugin System**: Extensible architecture -8. **Batch Processing**: Efficient parallel conversion -9. **Error Handling**: Robust error management -10. **Scientific Focus**: Optimized for research workflows - -## Installation - -```bash -# Full installation -pip install 'markitdown[all]' - -# Selective installation -pip install 'markitdown[pdf,docx,pptx,xlsx]' -``` - -## Quick Start - -```python -from markitdown import MarkItDown - -# Basic usage -md = MarkItDown() -result = md.convert("document.pdf") -print(result.text_content) - -# With AI via OpenRouter -from openai import OpenAI -client = OpenAI( - api_key="your-openrouter-api-key", - base_url="https://openrouter.ai/api/v1" -) -md = MarkItDown( - llm_client=client, - llm_model="anthropic/claude-sonnet-4.5" # or openai/gpt-4o -) -result = md.convert("presentation.pptx") -``` - -## Documentation Files - -| File | Purpose | Lines | -|------|---------|-------| -| SKILL.md | Main documentation | 400+ | -| api_reference.md | API documentation | 500+ | -| file_formats.md | Format guides | 600+ | -| example_usage.md | Practical examples | 500+ | -| batch_convert.py | Batch conversion | 200+ | -| convert_with_ai.py | AI conversion | 200+ | -| convert_literature.py | Literature conversion | 250+ | -| QUICK_REFERENCE.md | Quick reference | 300+ | -| INSTALLATION_GUIDE.md | Installation guide | 300+ | - -**Total**: ~3,000+ lines of documentation and code - -## Use Cases - -1. **Literature Review**: Convert research papers to Markdown for analysis -2. **Data Extraction**: Extract tables from Excel/PDF for processing -3. **Presentation Processing**: Convert slides with AI descriptions -4. **Document Analysis**: Prepare documents for LLM consumption -5. **Lecture Transcription**: Convert audio recordings to text -6. **YouTube Analysis**: Extract video transcripts -7. **Archive Processing**: Batch convert document collections - -## Next Steps - -1. Install MarkItDown: `pip install 'markitdown[all]'` -2. Read `QUICK_REFERENCE.md` for common tasks -3. Try example scripts in `scripts/` directory -4. Explore `SKILL.md` for comprehensive guide -5. Check `example_usage.md` for practical examples - -## Resources - -- **MarkItDown GitHub**: https://github.com/microsoft/markitdown -- **PyPI**: https://pypi.org/project/markitdown/ -- **OpenRouter**: https://openrouter.ai (AI model access) -- **OpenRouter API Keys**: https://openrouter.ai/keys -- **OpenRouter Models**: https://openrouter.ai/models -- **License**: MIT (Microsoft Corporation) -- **Python**: 3.10+ required -- **Skill Location**: `.claude/skills/markitdown/` - -## Success Criteria - -โœ… Comprehensive skill documentation created -โœ… Complete API reference provided -โœ… Format-specific guides included -โœ… Utility scripts implemented -โœ… Practical examples documented -โœ… Installation guide created -โœ… Quick reference guide added -โœ… Integration with Scientific Writer complete -โœ… SKILLS.md updated -โœ… Scripts made executable -โœ… MIT License included - -## Skill Status - -**Status**: โœ… Complete and Ready to Use - -The MarkItDown skill is fully integrated into the Claude Scientific Writer and ready for use. All documentation, scripts, and examples are in place. - diff --git a/scientific-skills/matchms/SKILL.md b/scientific-skills/matchms/SKILL.md index 002d83b..afd73a3 100644 --- a/scientific-skills/matchms/SKILL.md +++ b/scientific-skills/matchms/SKILL.md @@ -1,6 +1,8 @@ --- name: matchms description: "Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing." +metadata: + skill-author: K-Dense Inc. --- # Matchms diff --git a/scientific-skills/matplotlib/SKILL.md b/scientific-skills/matplotlib/SKILL.md index 032fb51..b650bef 100644 --- a/scientific-skills/matplotlib/SKILL.md +++ b/scientific-skills/matplotlib/SKILL.md @@ -1,6 +1,8 @@ --- name: matplotlib description: "Foundational plotting library. Create line plots, scatter, bar, histograms, heatmaps, 3D, subplots, export PNG/PDF/SVG, for scientific visualization and publication figures." +metadata: + skill-author: K-Dense Inc. --- # Matplotlib diff --git a/scientific-skills/medchem/SKILL.md b/scientific-skills/medchem/SKILL.md index 6fd59aa..f45d98c 100644 --- a/scientific-skills/medchem/SKILL.md +++ b/scientific-skills/medchem/SKILL.md @@ -1,6 +1,8 @@ --- name: medchem description: "Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering." +metadata: + skill-author: K-Dense Inc. --- # Medchem diff --git a/scientific-skills/metabolomics-workbench-database/SKILL.md b/scientific-skills/metabolomics-workbench-database/SKILL.md index 730a793..375ab3f 100644 --- a/scientific-skills/metabolomics-workbench-database/SKILL.md +++ b/scientific-skills/metabolomics-workbench-database/SKILL.md @@ -1,6 +1,8 @@ --- name: metabolomics-workbench-database description: "Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery." +metadata: + skill-author: K-Dense Inc. --- # Metabolomics Workbench Database diff --git a/scientific-skills/modal/SKILL.md b/scientific-skills/modal/SKILL.md index 1850e54..0bfe58b 100644 --- a/scientific-skills/modal/SKILL.md +++ b/scientific-skills/modal/SKILL.md @@ -1,6 +1,8 @@ --- name: modal description: Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling. +metadata: + skill-author: K-Dense Inc. --- # Modal diff --git a/scientific-skills/molfeat/SKILL.md b/scientific-skills/molfeat/SKILL.md index 7ae2192..136fc2f 100644 --- a/scientific-skills/molfeat/SKILL.md +++ b/scientific-skills/molfeat/SKILL.md @@ -1,6 +1,8 @@ --- name: molfeat description: "Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML." +metadata: + skill-author: K-Dense Inc. --- # Molfeat - Molecular Featurization Hub diff --git a/scientific-skills/networkx/SKILL.md b/scientific-skills/networkx/SKILL.md index 89a07de..3cd36a0 100644 --- a/scientific-skills/networkx/SKILL.md +++ b/scientific-skills/networkx/SKILL.md @@ -1,6 +1,8 @@ --- name: networkx description: Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships. +metadata: + skill-author: K-Dense Inc. --- # NetworkX diff --git a/scientific-skills/neurokit2/SKILL.md b/scientific-skills/neurokit2/SKILL.md index 2874fac..2503669 100644 --- a/scientific-skills/neurokit2/SKILL.md +++ b/scientific-skills/neurokit2/SKILL.md @@ -1,6 +1,8 @@ --- name: neurokit2 description: Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration. +metadata: + skill-author: K-Dense Inc. --- # NeuroKit2 diff --git a/scientific-skills/neuropixels-analysis/LICENSE.txt b/scientific-skills/neuropixels-analysis/LICENSE.txt deleted file mode 100644 index 50e3ad8..0000000 --- a/scientific-skills/neuropixels-analysis/LICENSE.txt +++ /dev/null @@ -1,21 +0,0 @@ -MIT License - -Copyright (c) 2025 Shen Lab - -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to deal -in the Software without restriction, including without limitation the rights -to use, copy, modify, merge, publish, distribute, sublicense, and/or sell -copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in all -copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, -OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE -SOFTWARE. diff --git a/scientific-skills/neuropixels-analysis/SKILL.md b/scientific-skills/neuropixels-analysis/SKILL.md index 77a2868..b81599a 100644 --- a/scientific-skills/neuropixels-analysis/SKILL.md +++ b/scientific-skills/neuropixels-analysis/SKILL.md @@ -1,6 +1,9 @@ --- name: neuropixels-analysis description: "Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation." +license: MIT License +metadata: + skill-author: K-Dense Inc. --- # Neuropixels Data Analysis @@ -280,16 +283,16 @@ Comprehensive visualization guide for publication-quality figures. | Topic | Reference | |-------|-----------| -| Full workflow | [reference/standard_workflow.md](reference/standard_workflow.md) | -| API reference | [reference/api_reference.md](reference/api_reference.md) | -| Plotting guide | [reference/plotting_guide.md](reference/plotting_guide.md) | -| Preprocessing | [PREPROCESSING.md](PREPROCESSING.md) | -| Spike sorting | [SPIKE_SORTING.md](SPIKE_SORTING.md) | -| Motion correction | [MOTION_CORRECTION.md](MOTION_CORRECTION.md) | -| Quality metrics | [QUALITY_METRICS.md](QUALITY_METRICS.md) | -| Automated curation | [AUTOMATED_CURATION.md](AUTOMATED_CURATION.md) | -| AI-assisted curation | [AI_CURATION.md](AI_CURATION.md) | -| Waveform analysis | [ANALYSIS.md](ANALYSIS.md) | +| Full workflow | [references/standard_workflow.md](reference/standard_workflow.md) | +| API reference | [references/api_reference.md](reference/api_reference.md) | +| Plotting guide | [references/plotting_guide.md](reference/plotting_guide.md) | +| Preprocessing | [references/PREPROCESSING.md](reference/PREPROCESSING.md) | +| Spike sorting | [references/SPIKE_SORTING.md](reference/SPIKE_SORTING.md) | +| Motion correction | [references/MOTION_CORRECTION.md](reference/MOTION_CORRECTION.md) | +| Quality metrics | [references/QUALITY_METRICS.md](reference/QUALITY_METRICS.md) | +| Automated curation | [references/AUTOMATED_CURATION.md](reference/AUTOMATED_CURATION.md) | +| AI-assisted curation | [references/AI_CURATION.md](reference/AI_CURATION.md) | +| Waveform analysis | [references/ANALYSIS.md](reference/ANALYSIS.md) | ## Installation diff --git a/scientific-skills/neuropixels-analysis/AI_CURATION.md b/scientific-skills/neuropixels-analysis/references/AI_CURATION.md similarity index 100% rename from scientific-skills/neuropixels-analysis/AI_CURATION.md rename to scientific-skills/neuropixels-analysis/references/AI_CURATION.md diff --git a/scientific-skills/neuropixels-analysis/ANALYSIS.md b/scientific-skills/neuropixels-analysis/references/ANALYSIS.md similarity index 100% rename from scientific-skills/neuropixels-analysis/ANALYSIS.md rename to scientific-skills/neuropixels-analysis/references/ANALYSIS.md diff --git a/scientific-skills/neuropixels-analysis/AUTOMATED_CURATION.md b/scientific-skills/neuropixels-analysis/references/AUTOMATED_CURATION.md similarity index 100% rename from scientific-skills/neuropixels-analysis/AUTOMATED_CURATION.md rename to scientific-skills/neuropixels-analysis/references/AUTOMATED_CURATION.md diff --git a/scientific-skills/neuropixels-analysis/MOTION_CORRECTION.md b/scientific-skills/neuropixels-analysis/references/MOTION_CORRECTION.md similarity index 100% rename from scientific-skills/neuropixels-analysis/MOTION_CORRECTION.md rename to scientific-skills/neuropixels-analysis/references/MOTION_CORRECTION.md diff --git a/scientific-skills/neuropixels-analysis/PREPROCESSING.md b/scientific-skills/neuropixels-analysis/references/PREPROCESSING.md similarity index 100% rename from scientific-skills/neuropixels-analysis/PREPROCESSING.md rename to scientific-skills/neuropixels-analysis/references/PREPROCESSING.md diff --git a/scientific-skills/neuropixels-analysis/QUALITY_METRICS.md b/scientific-skills/neuropixels-analysis/references/QUALITY_METRICS.md similarity index 100% rename from scientific-skills/neuropixels-analysis/QUALITY_METRICS.md rename to scientific-skills/neuropixels-analysis/references/QUALITY_METRICS.md diff --git a/scientific-skills/neuropixels-analysis/SPIKE_SORTING.md b/scientific-skills/neuropixels-analysis/references/SPIKE_SORTING.md similarity index 100% rename from scientific-skills/neuropixels-analysis/SPIKE_SORTING.md rename to scientific-skills/neuropixels-analysis/references/SPIKE_SORTING.md diff --git a/scientific-skills/omero-integration/SKILL.md b/scientific-skills/omero-integration/SKILL.md index c668cc5..b9fe445 100644 --- a/scientific-skills/omero-integration/SKILL.md +++ b/scientific-skills/omero-integration/SKILL.md @@ -1,6 +1,8 @@ --- name: omero-integration description: "Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows." +metadata: + skill-author: K-Dense Inc. --- # OMERO Integration diff --git a/scientific-skills/openalex-database/SKILL.md b/scientific-skills/openalex-database/SKILL.md index 391e07f..939a994 100644 --- a/scientific-skills/openalex-database/SKILL.md +++ b/scientific-skills/openalex-database/SKILL.md @@ -1,6 +1,8 @@ --- name: openalex-database description: Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries. +metadata: + skill-author: K-Dense Inc. --- # OpenAlex Database diff --git a/scientific-skills/opentargets-database/SKILL.md b/scientific-skills/opentargets-database/SKILL.md index b627633..10c6f0b 100644 --- a/scientific-skills/opentargets-database/SKILL.md +++ b/scientific-skills/opentargets-database/SKILL.md @@ -1,6 +1,8 @@ --- name: opentargets-database description: "Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification." +metadata: + skill-author: K-Dense Inc. --- # Open Targets Database diff --git a/scientific-skills/opentrons-integration/SKILL.md b/scientific-skills/opentrons-integration/SKILL.md index 903e6f7..c1b3dff 100644 --- a/scientific-skills/opentrons-integration/SKILL.md +++ b/scientific-skills/opentrons-integration/SKILL.md @@ -1,6 +1,8 @@ --- name: opentrons-integration description: "Lab automation platform for Flex/OT-2 robots. Write Protocol API v2 protocols, liquid handling, hardware modules (heater-shaker, thermocycler), labware management, for automated pipetting workflows." +metadata: + skill-author: K-Dense Inc. --- # Opentrons Integration diff --git a/scientific-skills/paper-2-web/SKILL.md b/scientific-skills/paper-2-web/SKILL.md index 8793722..e358370 100644 --- a/scientific-skills/paper-2-web/SKILL.md +++ b/scientific-skills/paper-2-web/SKILL.md @@ -2,6 +2,8 @@ name: paper-2-web description: This skill should be used when converting academic papers into promotional and presentation formats including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). Use this skill for tasks involving paper dissemination, conference preparation, creating explorable academic homepages, generating video abstracts, or producing print-ready posters from LaTeX or PDF sources. allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Paper2All: Academic Paper Transformation Pipeline diff --git a/scientific-skills/pathml/SKILL.md b/scientific-skills/pathml/SKILL.md index a1e40c4..8dbf7e9 100644 --- a/scientific-skills/pathml/SKILL.md +++ b/scientific-skills/pathml/SKILL.md @@ -1,6 +1,8 @@ --- name: pathml description: Computational pathology toolkit for analyzing whole-slide images (WSI) and multiparametric imaging data. Use this skill when working with histopathology slides, H&E stained images, multiplex immunofluorescence (CODEX, Vectra), spatial proteomics, nucleus detection/segmentation, tissue graph construction, or training ML models on pathology data. Supports 160+ slide formats including Aperio SVS, NDPI, DICOM, OME-TIFF for digital pathology workflows. +metadata: + skill-author: K-Dense Inc. --- # PathML diff --git a/scientific-skills/pdb-database/SKILL.md b/scientific-skills/pdb-database/SKILL.md index f199de9..3e2aed9 100644 --- a/scientific-skills/pdb-database/SKILL.md +++ b/scientific-skills/pdb-database/SKILL.md @@ -1,6 +1,8 @@ --- name: pdb-database description: "Access RCSB PDB for 3D protein/nucleic acid structures. Search by text/sequence/structure, download coordinates (PDB/mmCIF), retrieve metadata, for structural biology and drug discovery." +metadata: + skill-author: K-Dense Inc. --- # PDB Database diff --git a/scientific-skills/peer-review/SKILL.md b/scientific-skills/peer-review/SKILL.md index 5a6a691..7f99313 100644 --- a/scientific-skills/peer-review/SKILL.md +++ b/scientific-skills/peer-review/SKILL.md @@ -2,6 +2,8 @@ name: peer-review description: "Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Scientific Critical Evaluation and Peer Review diff --git a/scientific-skills/pennylane/SKILL.md b/scientific-skills/pennylane/SKILL.md index 9adf839..2db54de 100644 --- a/scientific-skills/pennylane/SKILL.md +++ b/scientific-skills/pennylane/SKILL.md @@ -1,6 +1,8 @@ --- name: pennylane description: Cross-platform Python library for quantum computing, quantum machine learning, and quantum chemistry. Enables building and training quantum circuits with automatic differentiation, seamless integration with PyTorch/JAX/TensorFlow, and device-independent execution across simulators and quantum hardware (IBM, Amazon Braket, Google, Rigetti, IonQ, etc.). Use when working with quantum circuits, variational quantum algorithms (VQE, QAOA), quantum neural networks, hybrid quantum-classical models, molecular simulations, quantum chemistry calculations, or any quantum computing tasks requiring gradient-based optimization, hardware-agnostic programming, or quantum machine learning workflows. +metadata: + skill-author: K-Dense Inc. --- # PennyLane diff --git a/scientific-skills/perplexity-search/SKILL.md b/scientific-skills/perplexity-search/SKILL.md index f317be1..77ac1bf 100644 --- a/scientific-skills/perplexity-search/SKILL.md +++ b/scientific-skills/perplexity-search/SKILL.md @@ -1,6 +1,8 @@ --- name: perplexity-search description: Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model's knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key. +metadata: + skill-author: K-Dense Inc. --- # Perplexity Search diff --git a/scientific-skills/plotly/SKILL.md b/scientific-skills/plotly/SKILL.md index 7e03645..bcd8af1 100644 --- a/scientific-skills/plotly/SKILL.md +++ b/scientific-skills/plotly/SKILL.md @@ -1,6 +1,8 @@ --- name: plotly description: Interactive scientific and statistical data visualization library for Python. Use when creating charts, plots, or visualizations including scatter plots, line charts, bar charts, heatmaps, 3D plots, geographic maps, statistical distributions, financial charts, and dashboards. Supports both quick visualizations (Plotly Express) and fine-grained customization (graph objects). Outputs interactive HTML or static images (PNG, PDF, SVG). +metadata: + skill-author: K-Dense Inc. --- # Plotly diff --git a/scientific-skills/polars/SKILL.md b/scientific-skills/polars/SKILL.md index a2f48e7..42a4627 100644 --- a/scientific-skills/polars/SKILL.md +++ b/scientific-skills/polars/SKILL.md @@ -1,6 +1,8 @@ --- name: polars description: "Fast DataFrame library (Apache Arrow). Select, filter, group_by, joins, lazy evaluation, CSV/Parquet I/O, expression API, for high-performance data analysis workflows." +metadata: + skill-author: K-Dense Inc. --- # Polars diff --git a/scientific-skills/pptx-posters/SKILL.md b/scientific-skills/pptx-posters/SKILL.md index 3ba3ef9..b3d3e2a 100644 --- a/scientific-skills/pptx-posters/SKILL.md +++ b/scientific-skills/pptx-posters/SKILL.md @@ -2,6 +2,8 @@ name: latex-posters description: "Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # LaTeX Research Posters diff --git a/scientific-skills/protocolsio-integration/SKILL.md b/scientific-skills/protocolsio-integration/SKILL.md index deb0c03..3f76701 100644 --- a/scientific-skills/protocolsio-integration/SKILL.md +++ b/scientific-skills/protocolsio-integration/SKILL.md @@ -1,6 +1,8 @@ --- name: protocolsio-integration description: Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation. +metadata: + skill-author: K-Dense Inc. --- # Protocols.io Integration diff --git a/scientific-skills/pubchem-database/SKILL.md b/scientific-skills/pubchem-database/SKILL.md index bae7f5d..3ded1bc 100644 --- a/scientific-skills/pubchem-database/SKILL.md +++ b/scientific-skills/pubchem-database/SKILL.md @@ -1,6 +1,8 @@ --- name: pubchem-database description: "Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics." +metadata: + skill-author: K-Dense Inc. --- # PubChem Database diff --git a/scientific-skills/pubmed-database/SKILL.md b/scientific-skills/pubmed-database/SKILL.md index b79ae77..2416f1b 100644 --- a/scientific-skills/pubmed-database/SKILL.md +++ b/scientific-skills/pubmed-database/SKILL.md @@ -1,6 +1,8 @@ --- name: pubmed-database description: "Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations." +metadata: + skill-author: K-Dense Inc. --- # PubMed Database diff --git a/scientific-skills/pufferlib/SKILL.md b/scientific-skills/pufferlib/SKILL.md index cbb2702..8813495 100644 --- a/scientific-skills/pufferlib/SKILL.md +++ b/scientific-skills/pufferlib/SKILL.md @@ -1,6 +1,8 @@ --- name: pufferlib description: This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs. +metadata: + skill-author: K-Dense Inc. --- # PufferLib - High-Performance Reinforcement Learning diff --git a/scientific-skills/pydeseq2/SKILL.md b/scientific-skills/pydeseq2/SKILL.md index 111b8fb..1edde56 100644 --- a/scientific-skills/pydeseq2/SKILL.md +++ b/scientific-skills/pydeseq2/SKILL.md @@ -1,6 +1,8 @@ --- name: pydeseq2 description: "Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis." +metadata: + skill-author: K-Dense Inc. --- # PyDESeq2 diff --git a/scientific-skills/pydicom/SKILL.md b/scientific-skills/pydicom/SKILL.md index 9d3ccc6..54a2f4c 100644 --- a/scientific-skills/pydicom/SKILL.md +++ b/scientific-skills/pydicom/SKILL.md @@ -1,6 +1,8 @@ --- name: pydicom description: Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications. +metadata: + skill-author: K-Dense Inc. --- # Pydicom diff --git a/scientific-skills/pyhealth/SKILL.md b/scientific-skills/pyhealth/SKILL.md index bde84c9..2aad3b8 100644 --- a/scientific-skills/pyhealth/SKILL.md +++ b/scientific-skills/pyhealth/SKILL.md @@ -1,6 +1,8 @@ --- name: pyhealth description: Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN). +metadata: + skill-author: K-Dense Inc. --- # PyHealth: Healthcare AI Toolkit diff --git a/scientific-skills/pylabrobot/SKILL.md b/scientific-skills/pylabrobot/SKILL.md index 92cd9ba..5c709b4 100644 --- a/scientific-skills/pylabrobot/SKILL.md +++ b/scientific-skills/pylabrobot/SKILL.md @@ -1,6 +1,8 @@ --- name: pylabrobot description: Laboratory automation toolkit for controlling liquid handlers, plate readers, pumps, heater shakers, incubators, centrifuges, and analytical equipment. Use this skill when automating laboratory workflows, programming liquid handling robots (Hamilton STAR, Opentrons OT-2, Tecan EVO), integrating lab equipment, managing deck layouts and resources (plates, tips, containers), reading plates, or creating reproducible laboratory protocols. Applicable for both simulated protocols and physical hardware control. +metadata: + skill-author: K-Dense Inc. --- # PyLabRobot diff --git a/scientific-skills/pymatgen/SKILL.md b/scientific-skills/pymatgen/SKILL.md index 667e6cb..b50ad04 100644 --- a/scientific-skills/pymatgen/SKILL.md +++ b/scientific-skills/pymatgen/SKILL.md @@ -1,6 +1,8 @@ --- name: pymatgen description: "Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science." +metadata: + skill-author: K-Dense Inc. --- # Pymatgen - Python Materials Genomics diff --git a/scientific-skills/pymc/SKILL.md b/scientific-skills/pymc/SKILL.md index 1d30dfd..6acbcc8 100644 --- a/scientific-skills/pymc/SKILL.md +++ b/scientific-skills/pymc/SKILL.md @@ -1,6 +1,8 @@ --- name: pymc-bayesian-modeling description: "Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference." +metadata: + skill-author: K-Dense Inc. --- # PyMC Bayesian Modeling diff --git a/scientific-skills/pymoo/SKILL.md b/scientific-skills/pymoo/SKILL.md index 955b18b..fc946de 100644 --- a/scientific-skills/pymoo/SKILL.md +++ b/scientific-skills/pymoo/SKILL.md @@ -1,6 +1,8 @@ --- name: pymoo description: "Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems." +metadata: + skill-author: K-Dense Inc. --- # Pymoo - Multi-Objective Optimization in Python diff --git a/scientific-skills/pyopenms/SKILL.md b/scientific-skills/pyopenms/SKILL.md index 9e2723f..68d4e20 100644 --- a/scientific-skills/pyopenms/SKILL.md +++ b/scientific-skills/pyopenms/SKILL.md @@ -1,6 +1,8 @@ --- name: pyopenms description: Python interface to OpenMS for mass spectrometry data analysis. Use for LC-MS/MS proteomics and metabolomics workflows including file handling (mzML, mzXML, mzTab, FASTA, pepXML, protXML, mzIdentML), signal processing, feature detection, peptide identification, and quantitative analysis. Apply when working with mass spectrometry data, analyzing proteomics experiments, or processing metabolomics datasets. +metadata: + skill-author: K-Dense Inc. --- # PyOpenMS diff --git a/scientific-skills/pysam/SKILL.md b/scientific-skills/pysam/SKILL.md index 7dda627..02491f6 100644 --- a/scientific-skills/pysam/SKILL.md +++ b/scientific-skills/pysam/SKILL.md @@ -1,6 +1,8 @@ --- name: pysam description: "Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines." +metadata: + skill-author: K-Dense Inc. --- # Pysam diff --git a/scientific-skills/pytdc/SKILL.md b/scientific-skills/pytdc/SKILL.md index dd53a4d..6f1d66c 100644 --- a/scientific-skills/pytdc/SKILL.md +++ b/scientific-skills/pytdc/SKILL.md @@ -1,6 +1,8 @@ --- name: pytdc description: "Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction." +metadata: + skill-author: K-Dense Inc. --- # PyTDC (Therapeutics Data Commons) diff --git a/scientific-skills/pytorch-lightning/SKILL.md b/scientific-skills/pytorch-lightning/SKILL.md index 82b700c..921d0e7 100644 --- a/scientific-skills/pytorch-lightning/SKILL.md +++ b/scientific-skills/pytorch-lightning/SKILL.md @@ -1,6 +1,8 @@ --- name: pytorch-lightning description: "Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training." +metadata: + skill-author: K-Dense Inc. --- # PyTorch Lightning diff --git a/scientific-skills/qiskit/SKILL.md b/scientific-skills/qiskit/SKILL.md index 7e8af94..a866fbc 100644 --- a/scientific-skills/qiskit/SKILL.md +++ b/scientific-skills/qiskit/SKILL.md @@ -1,6 +1,8 @@ --- name: qiskit description: Comprehensive quantum computing toolkit for building, optimizing, and executing quantum circuits. Use when working with quantum algorithms, simulations, or quantum hardware including (1) Building quantum circuits with gates and measurements, (2) Running quantum algorithms (VQE, QAOA, Grover), (3) Transpiling/optimizing circuits for hardware, (4) Executing on IBM Quantum or other providers, (5) Quantum chemistry and materials science, (6) Quantum machine learning, (7) Visualizing circuits and results, or (8) Any quantum computing development task. +metadata: + skill-author: K-Dense Inc. --- # Qiskit diff --git a/scientific-skills/qutip/SKILL.md b/scientific-skills/qutip/SKILL.md index 3fdf70e..0fe6e37 100644 --- a/scientific-skills/qutip/SKILL.md +++ b/scientific-skills/qutip/SKILL.md @@ -1,6 +1,8 @@ --- name: qutip description: "Quantum mechanics simulations and analysis using QuTiP (Quantum Toolbox in Python). Use when working with quantum systems including: (1) quantum states (kets, bras, density matrices), (2) quantum operators and gates, (3) time evolution and dynamics (Schrรถdinger, master equations, Monte Carlo), (4) open quantum systems with dissipation, (5) quantum measurements and entanglement, (6) visualization (Bloch sphere, Wigner functions), (7) steady states and correlation functions, or (8) advanced methods (Floquet theory, HEOM, stochastic solvers). Handles both closed and open quantum systems across various domains including quantum optics, quantum computing, and condensed matter physics." +metadata: + skill-author: K-Dense Inc. --- # QuTiP: Quantum Toolbox in Python diff --git a/scientific-skills/rdkit/SKILL.md b/scientific-skills/rdkit/SKILL.md index 0326db7..460ea15 100644 --- a/scientific-skills/rdkit/SKILL.md +++ b/scientific-skills/rdkit/SKILL.md @@ -1,6 +1,8 @@ --- name: rdkit description: "Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms." +metadata: + skill-author: K-Dense Inc. --- # RDKit Cheminformatics Toolkit diff --git a/scientific-skills/reactome-database/SKILL.md b/scientific-skills/reactome-database/SKILL.md index 0d7f464..f63c3ca 100644 --- a/scientific-skills/reactome-database/SKILL.md +++ b/scientific-skills/reactome-database/SKILL.md @@ -1,6 +1,8 @@ --- name: reactome-database description: "Query Reactome REST API for pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis, for systems biology studies." +metadata: + skill-author: K-Dense Inc. --- # Reactome Database diff --git a/scientific-skills/research-grants/README.md b/scientific-skills/research-grants/README.md deleted file mode 100644 index a27e8b7..0000000 --- a/scientific-skills/research-grants/README.md +++ /dev/null @@ -1,285 +0,0 @@ -# Research Grants Skill - -## Overview - -Comprehensive skill for writing competitive research grant proposals focused on four major U.S. funding agencies: -- **NSF** (National Science Foundation) -- **NIH** (National Institutes of Health) -- **DOE** (Department of Energy) -- **DARPA** (Defense Advanced Research Projects Agency) - -## What This Skill Provides - -### Agency-Specific Guidance - -Detailed reference materials for each funding agency including: -- Mission and priorities -- Review criteria and scoring -- Proposal structure and page limits -- Budget requirements -- Submission processes -- Tips for competitive applications - -### Core Components - -- **Specific Aims Pages** (NIH): Template and detailed guide for the critical 1-page aims page -- **Project Summaries** (NSF): Template for the required Overview, Intellectual Merit, and Broader Impacts -- **Broader Impacts**: Comprehensive strategies for NSF's equally-weighted review criterion -- **Budget Justification**: Templates and examples for personnel, equipment, travel, and supplies -- **Review Criteria**: Understanding what reviewers look for at each agency - -### Templates - -Ready-to-use templates for: -- NSF Project Summary -- NIH Specific Aims Page -- Budget Justifications -- (Additional templates in development) - -## How to Use This Skill - -### Quick Start - -When writing a grant proposal, specify the agency and grant type: - -``` -> Help me write an NSF proposal for computational biology research -> I need to draft NIH R01 Specific Aims for my cancer research project -> What should I include in a DOE ARPA-E concept paper? -> I'm applying for a DARPA program - help me structure the proposal -``` - -### Detailed Guidance - -For in-depth help on specific components: - -``` -> Help me write compelling broader impacts for my NSF proposal -> Review my NIH Specific Aims page -> What should I include in my budget justification? -> How do I respond to reviewer comments in an NIH resubmission? -``` - -### Agency Comparison - -``` -> What are the key differences between NSF and NIH proposals? -> Should I apply to DOE or DARPA for my energy technology project? -``` - -## Key Features - -### NSF Proposals - -- **Intellectual Merit + Broader Impacts** (equally weighted) -- Strategies for substantive, measurable broader impacts -- Integration of research and education -- Broadening participation in STEM -- 15-page project description limits (most programs) - -### NIH Proposals - -- **Specific Aims Page**: The most critical page (detailed 1-page guide included) -- **Research Strategy**: Significance, Innovation, Approach sections -- **Preliminary Data**: Essential for R01 applications -- Rigor and reproducibility requirements -- Modular vs. detailed budgets -- Resubmission strategies (A1 applications) - -### DOE Proposals - -- **Energy relevance** and alignment with DOE mission -- **Technology readiness levels** (TRLs) -- National laboratory collaborations -- Cost sharing requirements (especially ARPA-E) -- Commercialization pathways -- User facilities access - -### DARPA Proposals - -- **DARPA-hard problems**: High-risk, high-reward -- **Heilmeier Catechism**: The 8 critical questions -- Program Manager engagement (critical!) -- Phase-based structure with milestones -- Technology transition planning -- Demonstration and prototypes - -## Reference Materials - -### Agency Guidelines -- `references/nsf_guidelines.md` - Comprehensive NSF guidance -- `references/nih_guidelines.md` - NIH mechanisms and review criteria -- `references/doe_guidelines.md` - DOE offices and programs -- `references/darpa_guidelines.md` - DARPA structure and strategy - -### Specialized Guides -- `references/broader_impacts.md` - NSF broader impacts strategies -- `references/specific_aims_guide.md` - NIH Specific Aims page mastery -- `references/budget_preparation.md` - Budget development (coming soon) -- `references/review_criteria.md` - Comparative review criteria (coming soon) -- `references/timeline_planning.md` - Project management (coming soon) - -### Templates -- `assets/nsf_project_summary_template.md` -- `assets/nih_specific_aims_template.md` -- `assets/budget_justification_template.md` - -## Success Metrics - -Typical success rates by agency: -- **NSF**: 15-30% (varies by program) -- **NIH R01**: ~20% overall (~27% for Early Stage Investigators) -- **DOE Office of Science**: 20-40% (varies by program) -- **ARPA-E**: 2-5% (concept papers to awards) -- **DARPA**: Highly variable by program - -## Common Use Cases - -### First-Time Applicants -``` -> I've never written a grant before. Help me understand NSF proposal structure. -> What are the most common mistakes in first NIH R01 applications? -``` - -### Experienced Investigators -``` -> Help me strengthen the innovation section for my NIH resubmission -> I need to address broader impacts more substantively for NSF -> What's the best way to show technology transition for DARPA? -``` - -### Career Development -``` -> Help me write a competitive NSF CAREER proposal -> What should I emphasize in an NIH K99/R00 application? -``` - -### Multi-Agency Strategy -``` -> Should I submit this to NSF or NIH? -> Can I submit similar proposals to DOE and DARPA? -``` - -## Best Practices - -### Start Early -- NSF/NIH proposals: Start 3-6 months before deadline -- DOE/DARPA proposals: 4-6 months (especially if involving national labs) - -### Get Feedback -- Mock review sessions -- Colleagues in and outside your field -- Institutional grant support offices -- Program officers (when appropriate) - -### Understand Review Criteria -- NSF: Intellectual Merit + Broader Impacts (equal weight) -- NIH: Significance, Investigator, Innovation, Approach, Environment (scored 1-9) -- DOE: Technical merit, qualifications, budget, relevance -- DARPA: Innovation, impact, team, feasibility, transition - -### Common Success Factors - -โœ… Clear, compelling significance and innovation -โœ… Strong preliminary data (NIH, DOE) -โœ… Detailed, rigorous methodology -โœ… Realistic timeline and budget -โœ… Specific, measurable outcomes -โœ… Strong team with relevant expertise -โœ… Integration of broader impacts (NSF) -โœ… Technology transition plan (DOE, DARPA) - -## Integration with Other Skills - -This skill works well with: -- **Scientific Writing**: For clear, compelling prose -- **Literature Review**: For background sections -- **Research Lookup**: For finding relevant citations -- **Peer Review**: For self-assessment before submission - -## Updates and Additions - -This skill is continuously updated with: -- Current agency priorities -- Recent policy changes -- New funding mechanisms -- Additional templates and examples - -### Coming Soon -- More budget examples -- Timeline templates -- Collaboration letter templates -- Data management plan templates -- Facilities and equipment description templates - -## Tips for Maximum Effectiveness - -### For NSF Proposals -1. Start with Specific Aims/Objectives (even though not required) -2. Develop broader impacts with same rigor as research plan -3. Use figures and diagrams liberally (make it skimmable) -4. Address both review criteria explicitly -5. Get feedback from outside your immediate field - -### For NIH Proposals -1. Perfect your Specific Aims page first (10+ drafts) -2. Include substantial preliminary data -3. Address rigor and reproducibility explicitly -4. Identify potential problems proactively with alternatives -5. Make sure your aims are independent but synergistic - -### For DOE Proposals -1. Emphasize energy relevance and impact -2. Include quantitative metrics (cost, efficiency, emissions) -3. Develop pathway to deployment or commercialization -4. Consider national laboratory partnerships -5. Address technology readiness levels - -### For DARPA Proposals -1. Contact the Program Manager early (essential!) -2. Attend Proposers Day events -3. Focus on breakthrough innovation (10x, not 10%) -4. Answer the Heilmeier Catechism explicitly -5. Develop clear transition strategy - -## Resources Beyond This Skill - -### Official Resources -- NSF: https://www.nsf.gov/funding/ -- NIH: https://grants.nih.gov/ -- DOE: https://science.osti.gov/grants/ -- DARPA: https://www.darpa.mil/work-with-us/opportunities - -### Institutional Resources -- Your institution's Office of Sponsored Research -- Grant writing workshops -- Internal review programs -- Successful proposal archives - -### Professional Development -- Grant writing courses and webinars -- Agency-specific guidance documents -- Professional society resources -- Mentoring networks - -## Questions or Issues? - -This skill is designed to be comprehensive but may not cover every specific situation. When using this skill: - -1. **Be specific** about your agency, program, and grant type -2. **Provide context** about your research area and career stage -3. **Ask follow-up questions** for clarification -4. **Request examples** for specific sections you're working on - -## Version History - -- **v1.0** (January 2025): Initial release with NSF, NIH, DOE, DARPA guidance -- Comprehensive reference materials for all four agencies -- Templates for key proposal components -- Specific Aims and Broader Impacts detailed guides - ---- - -**Remember**: Grant writing is both an art and a science. This skill provides the frameworks, strategies, and best practicesโ€”but your unique research vision, preliminary data, and team expertise are what will ultimately win funding. Start early, seek feedback, revise extensively, and don't be discouraged by rejection. Even the most successful scientists face many declined proposals before achieving funding success. - -Good luck with your proposals! ๐ŸŽฏ diff --git a/scientific-skills/research-grants/SKILL.md b/scientific-skills/research-grants/SKILL.md index a70d7f0..66e6720 100644 --- a/scientific-skills/research-grants/SKILL.md +++ b/scientific-skills/research-grants/SKILL.md @@ -2,6 +2,8 @@ name: research-grants description: "Write competitive research proposals for NSF, NIH, DOE, and DARPA. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Research Grant Writing diff --git a/scientific-skills/research-lookup/README.md b/scientific-skills/research-lookup/README.md deleted file mode 100644 index cb748df..0000000 --- a/scientific-skills/research-lookup/README.md +++ /dev/null @@ -1,117 +0,0 @@ -# Research Lookup Skill - -This skill provides real-time research information lookup using Perplexity's Sonar Pro Search model through OpenRouter. - -## Setup - -1. **Get OpenRouter API Key:** - - Visit [openrouter.ai](https://openrouter.ai) - - Create account and generate API key - - Add credits to your account - -2. **Configure Environment:** - ```bash - export OPENROUTER_API_KEY="your_api_key_here" - ``` - -3. **Test Setup:** - ```bash - python scripts/research_lookup.py --model-info - ``` - -## Usage - -### Command Line Usage - -```bash -# Single research query -python scripts/research_lookup.py "Recent advances in CRISPR gene editing 2024" - -# Multiple queries with delay -python scripts/research_lookup.py --batch "CRISPR applications" "gene therapy trials" "ethical considerations" - -# Claude Code integration (called automatically) -python lookup.py "your research query here" -``` - -### Claude Code Integration - -The research lookup tool is automatically available in Claude Code when you: - -1. **Ask research questions:** "Research recent advances in quantum computing" -2. **Request literature reviews:** "Find current studies on climate change impacts" -3. **Need citations:** "What are the latest papers on transformer attention mechanisms?" -4. **Want technical information:** "Standard protocols for flow cytometry" - -## Features - -- **Academic Focus:** Prioritizes peer-reviewed papers and reputable sources -- **Current Information:** Focuses on recent publications (2020-2024) -- **Complete Citations:** Provides full bibliographic information with DOIs -- **Multiple Formats:** Supports various query types and research needs -- **High Search Context:** Always uses high search context for deeper, more comprehensive research -- **Cost Effective:** Typically $0.01-0.05 per research query - -## Query Examples - -### Academic Research -- "Recent systematic reviews on AI in medical diagnosis 2024" -- "Meta-analysis of randomized controlled trials for depression treatment" -- "Current state of quantum computing error correction research" - -### Technical Methods -- "Standard protocols for immunohistochemistry in tissue samples" -- "Best practices for machine learning model validation" -- "Statistical methods for analyzing longitudinal data" - -### Statistical Data -- "Global renewable energy adoption statistics 2024" -- "Prevalence of diabetes in different populations" -- "Market size for autonomous vehicles industry" - -## Response Format - -Each research result includes: -- **Summary:** Brief overview of key findings -- **Key Studies:** 3-5 most relevant recent papers -- **Citations:** Complete bibliographic information -- **Usage Stats:** Token usage for cost tracking -- **Timestamp:** When the research was performed - -## Integration with Scientific Writing - -This skill enhances the scientific writing process by providing: - -1. **Literature Reviews:** Current research for introduction sections -2. **Methods Validation:** Verify protocols against current standards -3. **Results Context:** Compare findings with recent similar studies -4. **Discussion Support:** Latest evidence for arguments -5. **Citation Management:** Properly formatted references - -## Troubleshooting - -**"API key not found"** -- Ensure `OPENROUTER_API_KEY` environment variable is set -- Check that you have credits in your OpenRouter account - -**"Model not available"** -- Verify your API key has access to Perplexity models -- Check OpenRouter status page for service issues - -**"Rate limit exceeded"** -- Add delays between requests using `--delay` option -- Check your OpenRouter account limits - -**"No relevant results"** -- Try more specific or broader queries -- Include time frames (e.g., "2023-2024") -- Use academic keywords and technical terms - -## Cost Management - -- Monitor usage through OpenRouter dashboard -- Typical costs: $0.01-0.05 per research query -- Batch processing available for multiple queries -- Consider query specificity to optimize token usage - -This skill is designed for academic and research purposes, providing high-quality, cited information to support scientific writing and research activities. diff --git a/scientific-skills/research-lookup/SKILL.md b/scientific-skills/research-lookup/SKILL.md index 711f0f5..b31284e 100644 --- a/scientific-skills/research-lookup/SKILL.md +++ b/scientific-skills/research-lookup/SKILL.md @@ -2,6 +2,8 @@ name: research-lookup description: "Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Research Information Lookup diff --git a/scientific-skills/research-lookup/research_lookup.py b/scientific-skills/research-lookup/research_lookup.py deleted file mode 100644 index 3d75d90..0000000 --- a/scientific-skills/research-lookup/research_lookup.py +++ /dev/null @@ -1,406 +0,0 @@ -#!/usr/bin/env python3 -""" -Research Information Lookup Tool -Uses Perplexity's Sonar Pro Search model through OpenRouter for academic research queries. -""" - -import os -import json -import requests -import time -from datetime import datetime -from typing import Dict, List, Optional, Any -from urllib.parse import quote - - -class ResearchLookup: - """Research information lookup using Perplexity Sonar models via OpenRouter.""" - - # Available models - MODELS = { - "pro": "perplexity/sonar-pro-search", # Fast lookup with search, cost-effective - "reasoning": "perplexity/sonar-reasoning-pro", # Deep analysis with reasoning and online search - } - - # Keywords that indicate complex queries requiring reasoning model - REASONING_KEYWORDS = [ - "compare", "contrast", "analyze", "analysis", "evaluate", "critique", - "versus", "vs", "vs.", "compared to", "differences between", "similarities", - "meta-analysis", "systematic review", "synthesis", "integrate", - "mechanism", "why", "how does", "how do", "explain", "relationship", - "theoretical framework", "implications", "interpret", "reasoning", - "controversy", "conflicting", "paradox", "debate", "reconcile", - "pros and cons", "advantages and disadvantages", "trade-off", "tradeoff", - ] - - def __init__(self, force_model: Optional[str] = None): - """ - Initialize the research lookup tool. - - Args: - force_model: Optional model override ('pro' or 'reasoning'). - If None, model is auto-selected based on query complexity. - """ - self.api_key = os.getenv("OPENROUTER_API_KEY") - if not self.api_key: - raise ValueError("OPENROUTER_API_KEY environment variable not set") - - self.base_url = "https://openrouter.ai/api/v1" - self.force_model = force_model - self.headers = { - "Authorization": f"Bearer {self.api_key}", - "Content-Type": "application/json", - "HTTP-Referer": "https://scientific-writer.local", - "X-Title": "Scientific Writer Research Tool" - } - - def _select_model(self, query: str) -> str: - """ - Select the appropriate model based on query complexity. - - Args: - query: The research query - - Returns: - Model identifier string - """ - if self.force_model: - return self.MODELS.get(self.force_model, self.MODELS["reasoning"]) - - # Check for reasoning keywords (case-insensitive) - query_lower = query.lower() - for keyword in self.REASONING_KEYWORDS: - if keyword in query_lower: - return self.MODELS["reasoning"] - - # Check for multiple questions or complex structure - question_count = query.count("?") - if question_count >= 2: - return self.MODELS["reasoning"] - - # Check for very long queries (likely complex) - if len(query) > 200: - return self.MODELS["reasoning"] - - # Default to pro for simple lookups - return self.MODELS["pro"] - - def _make_request(self, messages: List[Dict[str, str]], model: str, **kwargs) -> Dict[str, Any]: - """Make a request to the OpenRouter API with academic search mode.""" - data = { - "model": model, - "messages": messages, - "max_tokens": 8000, - "temperature": 0.1, # Low temperature for factual research - # Perplexity-specific parameters for academic search - "search_mode": "academic", # Prioritize scholarly sources (peer-reviewed papers, journals) - "search_context_size": "high", # Always use high context for deeper research - **kwargs - } - - try: - response = requests.post( - f"{self.base_url}/chat/completions", - headers=self.headers, - json=data, - timeout=90 # Increased timeout for academic search - ) - response.raise_for_status() - return response.json() - except requests.exceptions.RequestException as e: - raise Exception(f"API request failed: {str(e)}") - - def _format_research_prompt(self, query: str) -> str: - """Format the query for optimal research results.""" - return f"""You are an expert research assistant. Please provide comprehensive, accurate research information for the following query: "{query}" - -IMPORTANT INSTRUCTIONS: -1. Focus on ACADEMIC and SCIENTIFIC sources (peer-reviewed papers, reputable journals, institutional research) -2. Include RECENT information (prioritize 2020-2026 publications) -3. Provide COMPLETE citations with authors, title, journal/conference, year, and DOI when available -4. Structure your response with clear sections and proper attribution -5. Be comprehensive but concise - aim for 800-1200 words -6. Include key findings, methodologies, and implications when relevant -7. Note any controversies, limitations, or conflicting evidence - -RESPONSE FORMAT: -- Start with a brief summary (2-3 sentences) -- Present key findings and studies in organized sections -- End with future directions or research gaps if applicable -- Include 5-8 high-quality citations at the end - -Remember: This is for academic research purposes. Prioritize accuracy, completeness, and proper attribution.""" - - def lookup(self, query: str) -> Dict[str, Any]: - """Perform a research lookup for the given query.""" - timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S") - - # Select model based on query complexity - model = self._select_model(query) - - # Format the research prompt - research_prompt = self._format_research_prompt(query) - - # Prepare messages for the API with system message for academic mode - messages = [ - { - "role": "system", - "content": "You are an academic research assistant. Focus exclusively on scholarly sources: peer-reviewed journals, academic papers, research institutions, and reputable scientific publications. Prioritize recent academic literature (2020-2026) and provide complete citations with DOIs. Use academic/scholarly search mode." - }, - {"role": "user", "content": research_prompt} - ] - - try: - # Make the API request - response = self._make_request(messages, model) - - # Extract the response content - if "choices" in response and len(response["choices"]) > 0: - choice = response["choices"][0] - if "message" in choice and "content" in choice["message"]: - content = choice["message"]["content"] - - # Extract citations from API response (Perplexity provides these) - api_citations = self._extract_api_citations(response, choice) - - # Also extract citations from text as fallback - text_citations = self._extract_citations_from_text(content) - - # Combine: prioritize API citations, add text citations if no duplicates - citations = api_citations + text_citations - - return { - "success": True, - "query": query, - "response": content, - "citations": citations, - "sources": api_citations, # Separate field for API-provided sources - "timestamp": timestamp, - "model": model, - "usage": response.get("usage", {}) - } - else: - raise Exception("Invalid response format from API") - else: - raise Exception("No response choices received from API") - - except Exception as e: - return { - "success": False, - "query": query, - "error": str(e), - "timestamp": timestamp, - "model": model - } - - def _extract_api_citations(self, response: Dict[str, Any], choice: Dict[str, Any]) -> List[Dict[str, str]]: - """Extract citations from Perplexity API response fields.""" - citations = [] - - # Perplexity returns citations in search_results field (new format) - # Check multiple possible locations where OpenRouter might place them - search_results = ( - response.get("search_results") or - choice.get("search_results") or - choice.get("message", {}).get("search_results") or - [] - ) - - for result in search_results: - citation = { - "type": "source", - "title": result.get("title", ""), - "url": result.get("url", ""), - "date": result.get("date", ""), - } - # Add snippet if available (newer API feature) - if result.get("snippet"): - citation["snippet"] = result.get("snippet") - citations.append(citation) - - # Also check for legacy citations field (backward compatibility) - legacy_citations = ( - response.get("citations") or - choice.get("citations") or - choice.get("message", {}).get("citations") or - [] - ) - - for url in legacy_citations: - if isinstance(url, str): - # Legacy format was just URLs - citations.append({ - "type": "source", - "url": url, - "title": "", - "date": "" - }) - elif isinstance(url, dict): - citations.append({ - "type": "source", - "url": url.get("url", ""), - "title": url.get("title", ""), - "date": url.get("date", "") - }) - - return citations - - def _extract_citations_from_text(self, text: str) -> List[Dict[str, str]]: - """Extract potential citations from the response text as fallback.""" - import re - citations = [] - - # Look for DOI patterns first (most reliable) - # Matches: doi:10.xxx, DOI: 10.xxx, https://doi.org/10.xxx - doi_pattern = r'(?:doi[:\s]*|https?://(?:dx\.)?doi\.org/)(10\.[0-9]{4,}/[^\s\)\]\,\[\<\>]+)' - doi_matches = re.findall(doi_pattern, text, re.IGNORECASE) - seen_dois = set() - - for doi in doi_matches: - # Clean up DOI - remove trailing punctuation and brackets - doi_clean = doi.strip().rstrip('.,;:)]') - if doi_clean and doi_clean not in seen_dois: - seen_dois.add(doi_clean) - citations.append({ - "type": "doi", - "doi": doi_clean, - "url": f"https://doi.org/{doi_clean}" - }) - - # Look for URLs that might be sources - url_pattern = r'https?://[^\s\)\]\,\<\>\"\']+(?:arxiv\.org|pubmed|ncbi\.nlm\.nih\.gov|nature\.com|science\.org|wiley\.com|springer\.com|ieee\.org|acm\.org)[^\s\)\]\,\<\>\"\']*' - url_matches = re.findall(url_pattern, text, re.IGNORECASE) - seen_urls = set() - - for url in url_matches: - url_clean = url.rstrip('.') - if url_clean not in seen_urls: - seen_urls.add(url_clean) - citations.append({ - "type": "url", - "url": url_clean - }) - - return citations - - def batch_lookup(self, queries: List[str], delay: float = 1.0) -> List[Dict[str, Any]]: - """Perform multiple research lookups with optional delay between requests.""" - results = [] - - for i, query in enumerate(queries): - if i > 0 and delay > 0: - time.sleep(delay) # Rate limiting - - result = self.lookup(query) - results.append(result) - - # Print progress - print(f"[Research] Completed query {i+1}/{len(queries)}: {query[:50]}...") - - return results - - def get_model_info(self) -> Dict[str, Any]: - """Get information about available models from OpenRouter.""" - try: - response = requests.get( - f"{self.base_url}/models", - headers=self.headers, - timeout=30 - ) - response.raise_for_status() - return response.json() - except Exception as e: - return {"error": str(e)} - - -def main(): - """Command-line interface for testing the research lookup tool.""" - import argparse - - parser = argparse.ArgumentParser(description="Research Information Lookup Tool") - parser.add_argument("query", nargs="?", help="Research query to look up") - parser.add_argument("--model-info", action="store_true", help="Show available models") - parser.add_argument("--batch", nargs="+", help="Run multiple queries") - parser.add_argument("--force-model", choices=["pro", "reasoning"], - help="Force specific model: 'pro' for fast lookup, 'reasoning' for deep analysis") - - args = parser.parse_args() - - # Check for API key - if not os.getenv("OPENROUTER_API_KEY"): - print("Error: OPENROUTER_API_KEY environment variable not set") - print("Please set it in your .env file or export it:") - print(" export OPENROUTER_API_KEY='your_openrouter_api_key'") - return 1 - - try: - research = ResearchLookup(force_model=args.force_model) - - if args.model_info: - print("Available models from OpenRouter:") - models = research.get_model_info() - if "data" in models: - for model in models["data"]: - if "perplexity" in model["id"].lower(): - print(f" - {model['id']}: {model.get('name', 'N/A')}") - return 0 - - if not args.query and not args.batch: - print("Error: No query provided. Use --model-info to see available models.") - return 1 - - if args.batch: - print(f"Running batch research for {len(args.batch)} queries...") - results = research.batch_lookup(args.batch) - else: - print(f"Researching: {args.query}") - results = [research.lookup(args.query)] - - # Display results - for i, result in enumerate(results): - if result["success"]: - print(f"\n{'='*80}") - print(f"Query {i+1}: {result['query']}") - print(f"Timestamp: {result['timestamp']}") - print(f"Model: {result['model']}") - print(f"{'='*80}") - print(result["response"]) - - # Display API-provided sources first (most reliable) - sources = result.get("sources", []) - if sources: - print(f"\n๐Ÿ“š Sources ({len(sources)}):") - for j, source in enumerate(sources): - title = source.get("title", "Untitled") - url = source.get("url", "") - date = source.get("date", "") - date_str = f" ({date})" if date else "" - print(f" [{j+1}] {title}{date_str}") - if url: - print(f" {url}") - - # Display additional text-extracted citations - citations = result.get("citations", []) - text_citations = [c for c in citations if c.get("type") in ("doi", "url")] - if text_citations: - print(f"\n๐Ÿ”— Additional References ({len(text_citations)}):") - for j, citation in enumerate(text_citations): - if citation.get("type") == "doi": - print(f" [{j+1}] DOI: {citation.get('doi', '')} - {citation.get('url', '')}") - elif citation.get("type") == "url": - print(f" [{j+1}] {citation.get('url', '')}") - - if result.get("usage"): - print(f"\nUsage: {result['usage']}") - else: - print(f"\nError in query {i+1}: {result['error']}") - - return 0 - - except Exception as e: - print(f"Error: {str(e)}") - return 1 - - -if __name__ == "__main__": - exit(main()) diff --git a/scientific-skills/research-lookup/examples.py b/scientific-skills/research-lookup/scripts/examples.py similarity index 100% rename from scientific-skills/research-lookup/examples.py rename to scientific-skills/research-lookup/scripts/examples.py diff --git a/scientific-skills/research-lookup/lookup.py b/scientific-skills/research-lookup/scripts/lookup.py similarity index 100% rename from scientific-skills/research-lookup/lookup.py rename to scientific-skills/research-lookup/scripts/lookup.py diff --git a/scientific-skills/scanpy/SKILL.md b/scientific-skills/scanpy/SKILL.md index 3c5c51c..dc3264c 100644 --- a/scientific-skills/scanpy/SKILL.md +++ b/scientific-skills/scanpy/SKILL.md @@ -1,6 +1,8 @@ --- name: scanpy description: "Single-cell RNA-seq analysis. Load .h5ad/10X data, QC, normalization, PCA/UMAP/t-SNE, Leiden clustering, marker genes, cell type annotation, trajectory, for scRNA-seq analysis." +metadata: + skill-author: K-Dense Inc. --- # Scanpy: Single-Cell Analysis diff --git a/scientific-skills/scholar-evaluation/SKILL.md b/scientific-skills/scholar-evaluation/SKILL.md index 29c95fe..d960f86 100644 --- a/scientific-skills/scholar-evaluation/SKILL.md +++ b/scientific-skills/scholar-evaluation/SKILL.md @@ -1,3 +1,10 @@ +--- +name: scholar-evaluation +description: Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback. +metadata: + skill-author: K-Dense Inc. +--- + # Scholar Evaluation ## Overview diff --git a/scientific-skills/scientific-brainstorming/SKILL.md b/scientific-skills/scientific-brainstorming/SKILL.md index 8bd52ef..54d9d24 100644 --- a/scientific-skills/scientific-brainstorming/SKILL.md +++ b/scientific-skills/scientific-brainstorming/SKILL.md @@ -1,6 +1,8 @@ --- name: scientific-brainstorming description: "Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving." +metadata: + skill-author: K-Dense Inc. --- # Scientific Brainstorming diff --git a/scientific-skills/scientific-critical-thinking/SKILL.md b/scientific-skills/scientific-critical-thinking/SKILL.md index 75827d6..6caa824 100644 --- a/scientific-skills/scientific-critical-thinking/SKILL.md +++ b/scientific-skills/scientific-critical-thinking/SKILL.md @@ -2,6 +2,8 @@ name: scientific-critical-thinking description: "Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Scientific Critical Thinking diff --git a/scientific-skills/scientific-schematics/QUICK_REFERENCE.md b/scientific-skills/scientific-schematics/QUICK_REFERENCE.md deleted file mode 100644 index 985892a..0000000 --- a/scientific-skills/scientific-schematics/QUICK_REFERENCE.md +++ /dev/null @@ -1,207 +0,0 @@ -# Scientific Schematics - Quick Reference - -**How it works:** Describe your diagram โ†’ Nano Banana Pro generates it automatically - -## Setup (One-Time) - -```bash -# Get API key from https://openrouter.ai/keys -export OPENROUTER_API_KEY='sk-or-v1-your_key_here' - -# Add to shell profile for persistence -echo 'export OPENROUTER_API_KEY="sk-or-v1-your_key"' >> ~/.bashrc # or ~/.zshrc -``` - -## Basic Usage - -```bash -# Describe your diagram, Nano Banana Pro creates it -python scripts/generate_schematic.py "your diagram description" -o output.png - -# That's it! Automatic: -# - Iterative refinement (3 rounds) -# - Quality review and improvement -# - Publication-ready output -``` - -## Common Examples - -### CONSORT Flowchart -```bash -python scripts/generate_schematic.py \ - "CONSORT flow: screened n=500, excluded n=150, randomized n=350" \ - -o consort.png -``` - -### Neural Network -```bash -python scripts/generate_schematic.py \ - "Transformer architecture with encoder and decoder stacks" \ - -o transformer.png -``` - -### Biological Pathway -```bash -python scripts/generate_schematic.py \ - "MAPK pathway: EGFR โ†’ RAS โ†’ RAF โ†’ MEK โ†’ ERK" \ - -o mapk.png -``` - -### Circuit Diagram -```bash -python scripts/generate_schematic.py \ - "Op-amp circuit with 1kฮฉ resistor and 10ยตF capacitor" \ - -o circuit.png -``` - -## Command Options - -| Option | Description | Example | -|--------|-------------|---------| -| `-o, --output` | Output file path | `-o figures/diagram.png` | -| `--iterations N` | Number of refinements (1-2) | `--iterations 2` | -| `-v, --verbose` | Show detailed output | `-v` | -| `--api-key KEY` | Provide API key | `--api-key sk-or-v1-...` | - -## Prompt Tips - -### โœ“ Good Prompts (Specific) -- "CONSORT flowchart with screening (n=500), exclusion (n=150), randomization (n=350)" -- "Transformer architecture: encoder on left with 6 layers, decoder on right, cross-attention connections" -- "MAPK signaling: receptor โ†’ RAS โ†’ RAF โ†’ MEK โ†’ ERK โ†’ nucleus, label each phosphorylation" - -### โœ— Avoid (Too Vague) -- "Make a flowchart" -- "Neural network" -- "Pathway diagram" - -## Output Files - -For input `diagram.png`, you get: -- `diagram_v1.png` - First iteration -- `diagram_v2.png` - Second iteration -- `diagram_v3.png` - Final iteration -- `diagram.png` - Copy of final -- `diagram_review_log.json` - Quality scores and critiques - -## Review Log - -```json -{ - "iterations": [ - { - "iteration": 1, - "score": 7.0, - "critique": "Good start. Font too small..." - }, - { - "iteration": 2, - "score": 8.5, - "critique": "Much improved. Minor spacing issues..." - }, - { - "iteration": 3, - "score": 9.5, - "critique": "Excellent. Publication ready." - } - ], - "final_score": 9.5 -} -``` - -## Python API - -```python -from scripts.generate_schematic_ai import ScientificSchematicGenerator - -# Initialize -gen = ScientificSchematicGenerator(api_key="your_key") - -# Generate -results = gen.generate_iterative( - user_prompt="diagram description", - output_path="output.png", - iterations=2 -) - -# Check quality -print(f"Score: {results['final_score']}/10") -``` - -## Troubleshooting - -### API Key Not Found -```bash -# Check if set -echo $OPENROUTER_API_KEY - -# Set it -export OPENROUTER_API_KEY='your_key' -``` - -### Import Error -```bash -# Install requests -pip install requests -``` - -### Low Quality Score -- Make prompt more specific -- Include layout details (left-to-right, top-to-bottom) -- Specify label requirements -- Increase iterations: `--iterations 2` - -## Testing - -```bash -# Verify installation -python test_ai_generation.py - -# Should show: "6/6 tests passed" -``` - -## Cost - -Typical cost per diagram (max 2 iterations): -- Simple (1 iteration): $0.05-0.15 -- Complex (2 iterations): $0.10-0.30 - -## How Nano Banana Pro Works - -**Simply describe your diagram in natural language:** -- โœ“ No coding required -- โœ“ No templates needed -- โœ“ No manual drawing -- โœ“ Automatic quality review -- โœ“ Publication-ready output -- โœ“ Works for any diagram type - -**Just describe what you want, and it's generated automatically.** - -## Getting Help - -```bash -# Show help -python scripts/generate_schematic.py --help - -# Verbose mode for debugging -python scripts/generate_schematic.py "diagram" -o out.png -v -``` - -## Quick Start Checklist - -- [ ] Set `OPENROUTER_API_KEY` environment variable -- [ ] Run `python test_ai_generation.py` (should pass 6/6) -- [ ] Try: `python scripts/generate_schematic.py "test diagram" -o test.png` -- [ ] Review output files (test_v1.png, v2, v3, review_log.json) -- [ ] Read SKILL.md for detailed documentation -- [ ] Check README.md for examples - -## Resources - -- Full documentation: `SKILL.md` -- Detailed guide: `README.md` -- Implementation details: `IMPLEMENTATION_SUMMARY.md` -- Example script: `example_usage.sh` -- Get API key: https://openrouter.ai/keys - diff --git a/scientific-skills/scientific-schematics/README.md b/scientific-skills/scientific-schematics/README.md deleted file mode 100644 index 655727b..0000000 --- a/scientific-skills/scientific-schematics/README.md +++ /dev/null @@ -1,327 +0,0 @@ -# Scientific Schematics - Nano Banana Pro - -**Generate any scientific diagram by describing it in natural language.** - -Nano Banana Pro creates publication-quality diagrams automatically - no coding, no templates, no manual drawing required. - -## Quick Start - -### Generate Any Diagram - -```bash -# Set your OpenRouter API key -export OPENROUTER_API_KEY='your_api_key_here' - -# Generate any scientific diagram -python scripts/generate_schematic.py "CONSORT participant flow diagram" -o figures/consort.png - -# Neural network architecture -python scripts/generate_schematic.py "Transformer encoder-decoder architecture" -o figures/transformer.png - -# Biological pathway -python scripts/generate_schematic.py "MAPK signaling pathway" -o figures/pathway.png -``` - -### What You Get - -- **Up to two iterations** (v1, v2) with progressive refinement -- **Automatic quality review** after each iteration -- **Detailed review log** with scores and critiques (JSON format) -- **Publication-ready images** following scientific standards - -## Features - -### Iterative Refinement Process - -1. **Generation 1**: Create initial diagram from your description -2. **Review 1**: AI evaluates clarity, labels, accuracy, accessibility -3. **Generation 2**: Improve based on critique -4. **Review 2**: Second evaluation with specific feedback -5. **Generation 3**: Final polished version - -### Automatic Quality Standards - -All diagrams automatically follow: -- Clean white/light background -- High contrast for readability -- Clear labels (minimum 10pt font) -- Professional typography -- Colorblind-friendly colors -- Proper spacing between elements -- Scale bars, legends, axes where appropriate - -## Installation - -### For AI Generation - -```bash -# Get OpenRouter API key -# Visit: https://openrouter.ai/keys - -# Set environment variable -export OPENROUTER_API_KEY='sk-or-v1-...' - -# Or add to .env file -echo "OPENROUTER_API_KEY=sk-or-v1-..." >> .env - -# Install Python dependencies (if not already installed) -pip install requests -``` - -## Usage Examples - -### Example 1: CONSORT Flowchart - -```bash -python scripts/generate_schematic.py \ - "CONSORT participant flow diagram for RCT. \ - Assessed for eligibility (n=500). \ - Excluded (n=150): age<18 (n=80), declined (n=50), other (n=20). \ - Randomized (n=350) into Treatment (n=175) and Control (n=175). \ - Lost to follow-up: 15 and 10 respectively. \ - Final analysis: 160 and 165." \ - -o figures/consort.png -``` - -**Output:** -- `figures/consort_v1.png` - Initial generation -- `figures/consort_v2.png` - After first review -- `figures/consort_v3.png` - Final version -- `figures/consort.png` - Copy of final version -- `figures/consort_review_log.json` - Detailed review log - -### Example 2: Neural Network Architecture - -```bash -python scripts/generate_schematic.py \ - "Transformer architecture with encoder on left (input embedding, \ - positional encoding, multi-head attention, feed-forward) and \ - decoder on right (masked attention, cross-attention, feed-forward). \ - Show cross-attention connection from encoder to decoder." \ - -o figures/transformer.png \ - --iterations 2 -``` - -### Example 3: Biological Pathway - -```bash -python scripts/generate_schematic.py \ - "MAPK signaling pathway: EGFR receptor โ†’ RAS โ†’ RAF โ†’ MEK โ†’ ERK โ†’ nucleus. \ - Label each step with phosphorylation. Use different colors for each kinase." \ - -o figures/mapk.png -``` - -### Example 4: System Architecture - -```bash -python scripts/generate_schematic.py \ - "IoT system block diagram: sensors (bottom) โ†’ microcontroller โ†’ \ - WiFi module and display (middle) โ†’ cloud server โ†’ mobile app (top). \ - Label all connections with protocols." \ - -o figures/iot_system.png -``` - -## Command-Line Options - -```bash -python scripts/generate_schematic.py [OPTIONS] "description" -o output.png - -Options: - --iterations N Number of AI refinement iterations (default: 2, max: 2) - --api-key KEY OpenRouter API key (or use env var) - -v, --verbose Verbose output - -h, --help Show help message -``` - -## Python API - -```python -from scripts.generate_schematic_ai import ScientificSchematicGenerator - -# Initialize -generator = ScientificSchematicGenerator( - api_key="your_key", - verbose=True -) - -# Generate with iterative refinement -results = generator.generate_iterative( - user_prompt="CONSORT flowchart", - output_path="figures/consort.png", - iterations=2 -) - -# Access results -print(f"Final score: {results['final_score']}/10") -print(f"Final image: {results['final_image']}") - -# Review iterations -for iteration in results['iterations']: - print(f"Iteration {iteration['iteration']}: {iteration['score']}/10") - print(f"Critique: {iteration['critique']}") -``` - -## Prompt Engineering Tips - -### Be Specific About Layout -โœ“ "Flowchart with vertical flow, top to bottom" -โœ“ "Architecture diagram with encoder on left, decoder on right" -โœ— "Make a diagram" (too vague) - -### Include Quantitative Details -โœ“ "Neural network: input (784), hidden (128), output (10)" -โœ“ "Flowchart: n=500 screened, n=150 excluded, n=350 randomized" -โœ— "Some numbers" (not specific) - -### Specify Visual Style -โœ“ "Minimalist block diagram with clean lines" -โœ“ "Detailed biological pathway with protein structures" -โœ“ "Technical schematic with engineering notation" - -### Request Specific Labels -โœ“ "Label all arrows with activation/inhibition" -โœ“ "Include layer dimensions in each box" -โœ“ "Show time progression with timestamps" - -### Mention Color Requirements -โœ“ "Use colorblind-friendly colors" -โœ“ "Grayscale-compatible design" -โœ“ "Color-code by function: blue=input, green=processing, red=output" - -## Review Log Format - -Each generation produces a JSON review log: - -```json -{ - "user_prompt": "CONSORT participant flow diagram...", - "iterations": [ - { - "iteration": 1, - "image_path": "figures/consort_v1.png", - "prompt": "Full generation prompt...", - "critique": "Score: 7/10. Issues: font too small...", - "score": 7.0, - "success": true - }, - { - "iteration": 2, - "image_path": "figures/consort_v2.png", - "score": 8.5, - "critique": "Much improved. Remaining issues..." - }, - { - "iteration": 3, - "image_path": "figures/consort_v3.png", - "score": 9.5, - "critique": "Excellent. Publication ready." - } - ], - "final_image": "figures/consort_v3.png", - "final_score": 9.5, - "success": true -} -``` - -## Why Use Nano Banana Pro - -**Simply describe what you want - Nano Banana Pro creates it:** - -- โœ“ **Fast**: Results in minutes -- โœ“ **Easy**: Natural language descriptions (no coding) -- โœ“ **Quality**: Automatic review and refinement -- โœ“ **Universal**: Works for all diagram types -- โœ“ **Publication-ready**: High-quality output immediately - -**Just describe your diagram, and it's generated automatically.** - -## Troubleshooting - -### API Key Issues - -```bash -# Check if key is set -echo $OPENROUTER_API_KEY - -# Set temporarily -export OPENROUTER_API_KEY='your_key' - -# Set permanently (add to ~/.bashrc or ~/.zshrc) -echo 'export OPENROUTER_API_KEY="your_key"' >> ~/.bashrc -``` - -### Import Errors - -```bash -# Install requests library -pip install requests - -# Or use the package manager -pip install -r requirements.txt -``` - -### Generation Fails - -```bash -# Use verbose mode to see detailed errors -python scripts/generate_schematic.py "diagram" -o out.png -v - -# Check API status -curl https://openrouter.ai/api/v1/models -``` - -### Low Quality Scores - -If iterations consistently score below 7/10: -1. Make your prompt more specific -2. Include more details about layout and labels -3. Specify visual requirements explicitly -4. Increase iterations: `--iterations 2` - -## Testing - -Run verification tests: - -```bash -python test_ai_generation.py -``` - -This tests: -- File structure -- Module imports -- Class initialization -- Error handling -- Prompt engineering -- Wrapper script - -## Cost Considerations - -OpenRouter pricing for models used: -- **Nano Banana Pro**: ~$2/M input tokens, ~$12/M output tokens - -Typical costs per diagram: -- Simple diagram (1 iteration): ~$0.05-0.15 -- Complex diagram (2 iterations): ~$0.10-0.30 - -## Examples Gallery - -See the full SKILL.md for extensive examples including: -- CONSORT flowcharts -- Neural network architectures (Transformers, CNNs, RNNs) -- Biological pathways -- Circuit diagrams -- System architectures -- Block diagrams - -## Support - -For issues or questions: -1. Check SKILL.md for detailed documentation -2. Run test_ai_generation.py to verify setup -3. Use verbose mode (-v) to see detailed errors -4. Review the review_log.json for quality feedback - -## License - -Part of the scientific-writer package. See main repository for license information. - diff --git a/scientific-skills/scientific-schematics/SKILL.md b/scientific-skills/scientific-schematics/SKILL.md index 00c184b..191c711 100644 --- a/scientific-skills/scientific-schematics/SKILL.md +++ b/scientific-skills/scientific-schematics/SKILL.md @@ -2,6 +2,8 @@ name: scientific-schematics description: "Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Scientific Schematics and Diagrams diff --git a/scientific-skills/scientific-schematics/example_usage.sh b/scientific-skills/scientific-schematics/example_usage.sh deleted file mode 100755 index 2e638d9..0000000 --- a/scientific-skills/scientific-schematics/example_usage.sh +++ /dev/null @@ -1,89 +0,0 @@ -#!/bin/bash -# Example usage of AI-powered scientific schematic generation -# -# Prerequisites: -# 1. Set OPENROUTER_API_KEY environment variable -# 2. Ensure Python 3.10+ is installed -# 3. Install requests: pip install requests - -set -e - -echo "==========================================" -echo "Scientific Schematics - AI Generation" -echo "Example Usage Demonstrations" -echo "==========================================" -echo "" - -# Check for API key -if [ -z "$OPENROUTER_API_KEY" ]; then - echo "โŒ Error: OPENROUTER_API_KEY environment variable not set" - echo "" - echo "Get an API key at: https://openrouter.ai/keys" - echo "Then set it with: export OPENROUTER_API_KEY='your_key'" - exit 1 -fi - -echo "โœ“ OPENROUTER_API_KEY is set" -echo "" - -# Create output directory -mkdir -p figures -echo "โœ“ Created figures/ directory" -echo "" - -# Example 1: Simple flowchart -echo "Example 1: CONSORT Flowchart" -echo "----------------------------" -python scripts/generate_schematic.py \ - "CONSORT participant flow diagram. Assessed for eligibility (n=500). Excluded (n=150) with reasons: age<18 (n=80), declined (n=50), other (n=20). Randomized (n=350) into Treatment (n=175) and Control (n=175). Lost to follow-up: 15 and 10. Final analysis: 160 and 165." \ - -o figures/consort_example.png \ - --iterations 2 - -echo "" -echo "โœ“ Generated: figures/consort_example.png" -echo " - Also created: consort_example_v1.png, v2.png, v3.png" -echo " - Review log: consort_example_review_log.json" -echo "" - -# Example 2: Neural network (shorter for demo) -echo "Example 2: Simple Neural Network" -echo "--------------------------------" -python scripts/generate_schematic.py \ - "Simple feedforward neural network diagram. Input layer with 4 nodes, hidden layer with 6 nodes, output layer with 2 nodes. Show all connections. Label layers clearly." \ - -o figures/neural_net_example.png \ - --iterations 2 - -echo "" -echo "โœ“ Generated: figures/neural_net_example.png" -echo "" - -# Example 3: Biological pathway (minimal) -echo "Example 3: Signaling Pathway" -echo "---------------------------" -python scripts/generate_schematic.py \ - "Simple signaling pathway: Receptor โ†’ Kinase A โ†’ Kinase B โ†’ Transcription Factor โ†’ Gene. Show arrows with 'activation' labels. Use different colors for each component." \ - -o figures/pathway_example.png \ - --iterations 2 - -echo "" -echo "โœ“ Generated: figures/pathway_example.png" -echo "" - -echo "==========================================" -echo "All examples completed successfully!" -echo "==========================================" -echo "" -echo "Generated files in figures/:" -ls -lh figures/*example*.png 2>/dev/null || echo " (Files will appear after running with valid API key)" -echo "" -echo "Review the review_log.json files to see:" -echo " - Quality scores for each iteration" -echo " - Detailed critiques and suggestions" -echo " - Improvement progression" -echo "" -echo "Next steps:" -echo " 1. View the generated images" -echo " 2. Review the quality scores in *_review_log.json" -echo " 3. Try your own prompts!" -echo "" - diff --git a/scientific-skills/scientific-schematics/test_ai_generation.py b/scientific-skills/scientific-schematics/test_ai_generation.py deleted file mode 100644 index 0c4db82..0000000 --- a/scientific-skills/scientific-schematics/test_ai_generation.py +++ /dev/null @@ -1,243 +0,0 @@ -#!/usr/bin/env python3 -""" -Test script to verify AI generation implementation. - -This script performs dry-run tests without making actual API calls. -It verifies: -1. Script structure and imports -2. Class initialization -3. Method signatures -4. Error handling -5. Command-line interface - -Usage: - python test_ai_generation.py -""" - -import sys -import os -from pathlib import Path - -# Add scripts directory to path -scripts_dir = Path(__file__).parent / "scripts" -sys.path.insert(0, str(scripts_dir)) - -def test_imports(): - """Test that all required modules can be imported.""" - print("Testing imports...") - try: - from generate_schematic_ai import ScientificSchematicGenerator - print("โœ“ generate_schematic_ai imports successfully") - return True - except ImportError as e: - print(f"โœ— Import failed: {e}") - return False - -def test_class_structure(): - """Test class initialization and structure.""" - print("\nTesting class structure...") - try: - from generate_schematic_ai import ScientificSchematicGenerator - - # Test initialization with dummy key - generator = ScientificSchematicGenerator(api_key="test_key", verbose=False) - print("โœ“ Class initializes successfully") - - # Check required methods exist - required_methods = [ - 'generate_image', - 'review_image', - 'improve_prompt', - 'generate_iterative' - ] - - for method in required_methods: - if not hasattr(generator, method): - print(f"โœ— Missing method: {method}") - return False - print(f"โœ“ Method exists: {method}") - - # Check attributes - if not hasattr(generator, 'api_key'): - print("โœ— Missing attribute: api_key") - return False - print("โœ“ Attribute exists: api_key") - - if not hasattr(generator, 'image_model'): - print("โœ— Missing attribute: image_model") - return False - print(f"โœ“ Image model: {generator.image_model}") - - if not hasattr(generator, 'review_model'): - print("โœ— Missing attribute: review_model") - return False - print(f"โœ“ Review model: {generator.review_model}") - - return True - except Exception as e: - print(f"โœ— Class structure test failed: {e}") - return False - -def test_error_handling(): - """Test error handling for missing API key.""" - print("\nTesting error handling...") - try: - from generate_schematic_ai import ScientificSchematicGenerator - - # Clear environment variable - old_key = os.environ.get("OPENROUTER_API_KEY") - if old_key: - del os.environ["OPENROUTER_API_KEY"] - - # Try to initialize without key - try: - generator = ScientificSchematicGenerator() - print("โœ— Should have raised ValueError for missing API key") - return False - except ValueError as e: - if "OPENROUTER_API_KEY" in str(e): - print("โœ“ Correctly raises ValueError for missing API key") - else: - print(f"โœ— Wrong error message: {e}") - return False - - # Restore environment variable - if old_key: - os.environ["OPENROUTER_API_KEY"] = old_key - - return True - except Exception as e: - print(f"โœ— Error handling test failed: {e}") - return False - -def test_wrapper_script(): - """Test wrapper script structure.""" - print("\nTesting wrapper script...") - try: - import generate_schematic - print("โœ“ generate_schematic imports successfully") - - # Check main functions exist - if not hasattr(generate_schematic, 'main'): - print("โœ— Missing function: main") - return False - print("โœ“ Function exists: main") - - return True - except Exception as e: - print(f"โœ— Wrapper script test failed: {e}") - return False - -def test_prompt_engineering(): - """Test prompt construction.""" - print("\nTesting prompt engineering...") - try: - from generate_schematic_ai import ScientificSchematicGenerator - - generator = ScientificSchematicGenerator(api_key="test_key", verbose=False) - - # Test improve_prompt method - original = "Create a flowchart" - critique = "Add more spacing between boxes" - improved = generator.improve_prompt(original, critique, 2) - - if not improved: - print("โœ— improve_prompt returned empty string") - return False - - if original not in improved: - print("โœ— Improved prompt doesn't include original") - return False - - if critique not in improved: - print("โœ— Improved prompt doesn't include critique") - return False - - if "ITERATION 2" not in improved: - print("โœ— Improved prompt doesn't include iteration number") - return False - - print("โœ“ Prompt engineering works correctly") - print(f" Original length: {len(original)} chars") - print(f" Improved length: {len(improved)} chars") - - return True - except Exception as e: - print(f"โœ— Prompt engineering test failed: {e}") - return False - -def test_file_paths(): - """Test that all required files exist.""" - print("\nTesting file structure...") - - base_dir = Path(__file__).parent - required_files = [ - "scripts/generate_schematic_ai.py", - "scripts/generate_schematic.py", - "SKILL.md", - "README.md" - ] - - all_exist = True - for file_path in required_files: - full_path = base_dir / file_path - if full_path.exists(): - print(f"โœ“ {file_path}") - else: - print(f"โœ— Missing: {file_path}") - all_exist = False - - return all_exist - -def main(): - """Run all tests.""" - print("="*60) - print("Scientific Schematics AI Generation - Verification Tests") - print("="*60) - - tests = [ - ("File Structure", test_file_paths), - ("Imports", test_imports), - ("Class Structure", test_class_structure), - ("Error Handling", test_error_handling), - ("Wrapper Script", test_wrapper_script), - ("Prompt Engineering", test_prompt_engineering), - ] - - results = [] - for test_name, test_func in tests: - try: - result = test_func() - results.append((test_name, result)) - except Exception as e: - print(f"\nโœ— Test '{test_name}' crashed: {e}") - results.append((test_name, False)) - - # Summary - print("\n" + "="*60) - print("Test Summary") - print("="*60) - - passed = sum(1 for _, result in results if result) - total = len(results) - - for test_name, result in results: - status = "โœ“ PASS" if result else "โœ— FAIL" - print(f"{status}: {test_name}") - - print(f"\nTotal: {passed}/{total} tests passed") - - if passed == total: - print("\nโœ“ All tests passed! Implementation verified.") - print("\nNext steps:") - print("1. Set OPENROUTER_API_KEY environment variable") - print("2. Test with actual API call:") - print(" python scripts/generate_schematic.py 'test diagram' -o test.png") - return 0 - else: - print(f"\nโœ— {total - passed} test(s) failed. Please review errors above.") - return 1 - -if __name__ == "__main__": - sys.exit(main()) - diff --git a/scientific-skills/scientific-slides/SKILL.md b/scientific-skills/scientific-slides/SKILL.md index c87dbea..b8afe68 100644 --- a/scientific-skills/scientific-slides/SKILL.md +++ b/scientific-skills/scientific-slides/SKILL.md @@ -2,6 +2,8 @@ name: scientific-slides description: "Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Scientific Slides diff --git a/scientific-skills/scientific-visualization/SKILL.md b/scientific-skills/scientific-visualization/SKILL.md index d6140fe..e6a5038 100644 --- a/scientific-skills/scientific-visualization/SKILL.md +++ b/scientific-skills/scientific-visualization/SKILL.md @@ -1,6 +1,8 @@ --- name: scientific-visualization description: "Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots." +metadata: + skill-author: K-Dense Inc. --- # Scientific Visualization diff --git a/scientific-skills/scientific-writing/SKILL.md b/scientific-skills/scientific-writing/SKILL.md index 16fc9d2..a5c2138 100644 --- a/scientific-skills/scientific-writing/SKILL.md +++ b/scientific-skills/scientific-writing/SKILL.md @@ -2,6 +2,8 @@ name: scientific-writing description: "Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process: (1) create section outlines with key points using research-lookup, (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Scientific Writing diff --git a/scientific-skills/scikit-bio/SKILL.md b/scientific-skills/scikit-bio/SKILL.md index c792e42..16fd933 100644 --- a/scientific-skills/scikit-bio/SKILL.md +++ b/scientific-skills/scikit-bio/SKILL.md @@ -1,6 +1,8 @@ --- name: scikit-bio description: "Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis." +metadata: + skill-author: K-Dense Inc. --- # scikit-bio diff --git a/scientific-skills/scikit-learn/SKILL.md b/scientific-skills/scikit-learn/SKILL.md index f3715ea..4fbb10f 100644 --- a/scientific-skills/scikit-learn/SKILL.md +++ b/scientific-skills/scikit-learn/SKILL.md @@ -1,6 +1,8 @@ --- name: scikit-learn description: Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices. +metadata: + skill-author: K-Dense Inc. --- # Scikit-learn diff --git a/scientific-skills/scikit-survival/SKILL.md b/scientific-skills/scikit-survival/SKILL.md index c8427c5..95d1a43 100644 --- a/scientific-skills/scikit-survival/SKILL.md +++ b/scientific-skills/scikit-survival/SKILL.md @@ -1,6 +1,8 @@ --- name: scikit-survival description: Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library. +metadata: + skill-author: K-Dense Inc. --- # scikit-survival: Survival Analysis in Python diff --git a/scientific-skills/scvi-tools/SKILL.md b/scientific-skills/scvi-tools/SKILL.md index 165ff77..f1f9a04 100644 --- a/scientific-skills/scvi-tools/SKILL.md +++ b/scientific-skills/scvi-tools/SKILL.md @@ -1,6 +1,8 @@ --- name: scvi-tools description: This skill should be used when working with single-cell omics data analysis using scvi-tools, including scRNA-seq, scATAC-seq, CITE-seq, spatial transcriptomics, and other single-cell modalities. Use this skill for probabilistic modeling, batch correction, dimensionality reduction, differential expression, cell type annotation, multimodal integration, and spatial analysis tasks. +metadata: + skill-author: K-Dense Inc. --- # scvi-tools diff --git a/scientific-skills/seaborn/SKILL.md b/scientific-skills/seaborn/SKILL.md index 82ab3e3..0fe360e 100644 --- a/scientific-skills/seaborn/SKILL.md +++ b/scientific-skills/seaborn/SKILL.md @@ -1,6 +1,8 @@ --- name: seaborn description: "Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures." +metadata: + skill-author: K-Dense Inc. --- # Seaborn Statistical Visualization diff --git a/scientific-skills/shap/SKILL.md b/scientific-skills/shap/SKILL.md index b011249..f25e71d 100644 --- a/scientific-skills/shap/SKILL.md +++ b/scientific-skills/shap/SKILL.md @@ -1,6 +1,8 @@ --- name: shap description: Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model. +metadata: + skill-author: K-Dense Inc. --- # SHAP (SHapley Additive exPlanations) diff --git a/scientific-skills/simpy/SKILL.md b/scientific-skills/simpy/SKILL.md index d48d1d0..30c5c72 100644 --- a/scientific-skills/simpy/SKILL.md +++ b/scientific-skills/simpy/SKILL.md @@ -1,6 +1,8 @@ --- name: simpy description: Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems, service operations, network traffic, logistics, or any system where entities interact with shared resources over time. +metadata: + skill-author: K-Dense Inc. --- # SimPy - Discrete-Event Simulation diff --git a/scientific-skills/stable-baselines3/SKILL.md b/scientific-skills/stable-baselines3/SKILL.md index c689332..4d09184 100644 --- a/scientific-skills/stable-baselines3/SKILL.md +++ b/scientific-skills/stable-baselines3/SKILL.md @@ -1,6 +1,8 @@ --- name: stable-baselines3 description: Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation. +metadata: + skill-author: K-Dense Inc. --- # Stable Baselines3 diff --git a/scientific-skills/statistical-analysis/SKILL.md b/scientific-skills/statistical-analysis/SKILL.md index bbf6198..55f9523 100644 --- a/scientific-skills/statistical-analysis/SKILL.md +++ b/scientific-skills/statistical-analysis/SKILL.md @@ -1,6 +1,8 @@ --- name: statistical-analysis description: "Statistical analysis toolkit. Hypothesis tests (t-test, ANOVA, chi-square), regression, correlation, Bayesian stats, power analysis, assumption checks, APA reporting, for academic research." +metadata: + skill-author: K-Dense Inc. --- # Statistical Analysis diff --git a/scientific-skills/statsmodels/SKILL.md b/scientific-skills/statsmodels/SKILL.md index 909a2ae..98930cd 100644 --- a/scientific-skills/statsmodels/SKILL.md +++ b/scientific-skills/statsmodels/SKILL.md @@ -1,6 +1,8 @@ --- name: statsmodels description: "Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis." +metadata: + skill-author: K-Dense Inc. --- # Statsmodels: Statistical Modeling and Econometrics diff --git a/scientific-skills/string-database/SKILL.md b/scientific-skills/string-database/SKILL.md index e9347a8..e91b912 100644 --- a/scientific-skills/string-database/SKILL.md +++ b/scientific-skills/string-database/SKILL.md @@ -1,6 +1,8 @@ --- name: string-database description: "Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology." +metadata: + skill-author: K-Dense Inc. --- # STRING Database diff --git a/scientific-skills/sympy/SKILL.md b/scientific-skills/sympy/SKILL.md index 70823b5..14a33f8 100644 --- a/scientific-skills/sympy/SKILL.md +++ b/scientific-skills/sympy/SKILL.md @@ -1,6 +1,8 @@ --- name: sympy description: Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working with matrices symbolically, physics calculations, number theory problems, geometry computations, and generating executable code from mathematical expressions. Apply this skill when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters. +metadata: + skill-author: K-Dense Inc. --- # SymPy - Symbolic Mathematics in Python diff --git a/scientific-skills/torch_geometric/SKILL.md b/scientific-skills/torch_geometric/SKILL.md index 23d966d..fc2ca99 100644 --- a/scientific-skills/torch_geometric/SKILL.md +++ b/scientific-skills/torch_geometric/SKILL.md @@ -1,6 +1,8 @@ --- name: torch-geometric description: "Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning." +metadata: + skill-author: K-Dense Inc. --- # PyTorch Geometric (PyG) diff --git a/scientific-skills/torchdrug/SKILL.md b/scientific-skills/torchdrug/SKILL.md index ab746db..e84847a 100644 --- a/scientific-skills/torchdrug/SKILL.md +++ b/scientific-skills/torchdrug/SKILL.md @@ -1,6 +1,8 @@ --- name: torchdrug description: "Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs." +metadata: + skill-author: K-Dense Inc. --- # TorchDrug diff --git a/scientific-skills/transformers/SKILL.md b/scientific-skills/transformers/SKILL.md index e0fb5ce..60d3380 100644 --- a/scientific-skills/transformers/SKILL.md +++ b/scientific-skills/transformers/SKILL.md @@ -1,6 +1,8 @@ --- name: transformers description: This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets. +metadata: + skill-author: K-Dense Inc. --- # Transformers diff --git a/scientific-skills/treatment-plans/README.md b/scientific-skills/treatment-plans/README.md deleted file mode 100644 index 9cf0ff5..0000000 --- a/scientific-skills/treatment-plans/README.md +++ /dev/null @@ -1,488 +0,0 @@ -# Treatment Plans Skill - -## Overview - -Skill for generating **concise, clinician-focused** medical treatment plans across all clinical specialties. Provides LaTeX/PDF templates with SMART goal frameworks, evidence-based interventions, regulatory compliance, and validation tools for patient-centered care planning. - -**Default to 1-page format** for most cases - think "quick reference card" not "comprehensive textbook". - -## What's Included - -### ๐Ÿ“‹ Seven Treatment Plan Types - -1. **One-Page Treatment Plan** (PREFERRED) - Concise, quick-reference format for most clinical scenarios -2. **General Medical Treatment Plans** - Primary care, chronic diseases (diabetes, hypertension, heart failure) -3. **Rehabilitation Treatment Plans** - Physical therapy, occupational therapy, cardiac/pulmonary rehab -4. **Mental Health Treatment Plans** - Psychiatric care, depression, anxiety, PTSD, substance use -5. **Chronic Disease Management Plans** - Complex multimorbidity, long-term care coordination -6. **Perioperative Care Plans** - Preoperative optimization, ERAS protocols, postoperative recovery -7. **Pain Management Plans** - Acute and chronic pain, multimodal analgesia, opioid-sparing strategies - -### ๐Ÿ“š Reference Files (5 comprehensive guides) - -- `treatment_plan_standards.md` - Professional standards, documentation requirements, legal considerations -- `goal_setting_frameworks.md` - SMART goals, patient-centered outcomes, shared decision-making -- `intervention_guidelines.md` - Evidence-based treatments, pharmacological and non-pharmacological -- `regulatory_compliance.md` - HIPAA compliance, billing documentation, quality measures -- `specialty_specific_guidelines.md` - Detailed guidelines for each treatment plan type - -### ๐Ÿ“„ LaTeX Templates (7 professional templates) - -- `one_page_treatment_plan.tex` - **FIRST CHOICE** - Dense, scannable 1-page format (like precision oncology reports) -- `general_medical_treatment_plan.tex` - Comprehensive medical care planning -- `rehabilitation_treatment_plan.tex` - Functional restoration and therapy -- `mental_health_treatment_plan.tex` - Psychiatric and behavioral health -- `chronic_disease_management_plan.tex` - Long-term disease management -- `perioperative_care_plan.tex` - Surgical and procedural care -- `pain_management_plan.tex` - Multimodal pain treatment - -### ๐Ÿ”ง Validation Scripts (4 automation tools) - -- `generate_template.py` - Interactive template selection and generation -- `validate_treatment_plan.py` - Comprehensive quality and compliance checking -- `check_completeness.py` - Verify all required sections present -- `timeline_generator.py` - Create visual treatment timelines and schedules - -## Quick Start - -### Generate a Treatment Plan Template - -```bash -cd .claude/skills/treatment-plans/scripts -python generate_template.py - -# Or specify type directly -python generate_template.py --type general_medical --output diabetes_plan.tex -``` - -Available template types: -- `one_page` (PREFERRED - use for most cases) -- `general_medical` -- `rehabilitation` -- `mental_health` -- `chronic_disease` -- `perioperative` -- `pain_management` - -### Compile to PDF - -```bash -cd /path/to/your/treatment/plan -pdflatex my_treatment_plan.tex -``` - -### Validate Your Treatment Plan - -```bash -# Check for completeness -python check_completeness.py my_treatment_plan.tex - -# Comprehensive validation -python validate_treatment_plan.py my_treatment_plan.tex -``` - -### Generate Treatment Timeline - -```bash -python timeline_generator.py --plan my_treatment_plan.tex --output timeline.pdf -``` - -## Standard Treatment Plan Components - -All templates include these essential sections: - -### 1. Patient Information (De-identified) -- Demographics and relevant medical background -- Active conditions and comorbidities -- Current medications and allergies -- Functional status baseline -- HIPAA-compliant de-identification - -### 2. Diagnosis and Assessment Summary -- Primary diagnosis (ICD-10 coded) -- Secondary diagnoses -- Severity classification -- Functional limitations -- Risk stratification - -### 3. Treatment Goals (SMART Format) - -**Short-term goals** (1-3 months): -- Specific, measurable outcomes -- Realistic targets with defined timeframes -- Patient-centered priorities - -**Long-term goals** (6-12 months): -- Disease control targets -- Functional improvement objectives -- Quality of life enhancement -- Complication prevention - -### 4. Interventions - -- **Pharmacological**: Medications with dosages, frequencies, monitoring -- **Non-pharmacological**: Lifestyle modifications, behavioral interventions, education -- **Procedural**: Planned procedures, specialist referrals, diagnostic testing - -### 5. Timeline and Schedule -- Treatment phases with timeframes -- Appointment frequency -- Milestone assessments -- Expected treatment duration - -### 6. Monitoring Parameters -- Clinical outcomes to track -- Assessment tools and scales -- Monitoring frequency -- Intervention thresholds - -### 7. Expected Outcomes -- Primary outcome measures -- Success criteria -- Timeline for improvement -- Long-term prognosis - -### 8. Follow-up Plan -- Scheduled appointments -- Communication protocols -- Emergency procedures -- Transition planning - -### 9. Patient Education -- Condition understanding -- Self-management skills -- Warning signs -- Resources and support - -### 10. Risk Mitigation -- Adverse effect management -- Safety monitoring -- Emergency action plans -- Fall/infection prevention - -## Common Use Cases - -### 1. Type 2 Diabetes Management - -``` -Goal: Create comprehensive treatment plan for newly diagnosed diabetes - -Template: general_medical_treatment_plan.tex - -Key Components: -- SMART goals: HbA1c <7% in 3 months, weight loss 10 lbs in 6 months -- Medications: Metformin titration schedule -- Lifestyle: Diet, exercise, glucose monitoring -- Monitoring: HbA1c every 3 months, quarterly visits -- Education: Diabetes self-management education -``` - -### 2. Post-Stroke Rehabilitation - -``` -Goal: Develop rehab plan for stroke patient with hemiparesis - -Template: rehabilitation_treatment_plan.tex - -Key Components: -- Functional assessment: FIM scores, ROM, strength testing -- PT goals: Ambulation 150 feet with cane in 12 weeks -- OT goals: Independent ADLs, upper extremity function -- Treatment schedule: PT/OT/SLP 3x week each -- Home exercise program -``` - -### 3. Major Depressive Disorder - -``` -Goal: Create integrated treatment plan for depression - -Template: mental_health_treatment_plan.tex - -Key Components: -- Assessment: PHQ-9 score 16 (moderate depression) -- Goals: Reduce PHQ-9 to <5, return to work in 12 weeks -- Psychotherapy: CBT weekly sessions -- Medication: SSRI with titration schedule -- Safety planning: Crisis contacts, warning signs -``` - -### 4. Total Knee Replacement - -``` -Goal: Perioperative care plan for elective TKA - -Template: perioperative_care_plan.tex - -Key Components: -- Preop optimization: Medical clearance, medication management -- ERAS protocol implementation -- Postop milestones: Ambulation POD 1, discharge POD 2-3 -- Pain management: Multimodal analgesia -- Rehab plan: PT starting POD 0 -``` - -### 5. Chronic Low Back Pain - -``` -Goal: Multimodal pain management plan - -Template: pain_management_plan.tex - -Key Components: -- Pain assessment: Location, intensity, functional impact -- Goals: Reduce pain 7/10 to 3/10, return to work -- Medications: Non-opioid analgesics, adjuvants -- PT: Core strengthening, McKenzie exercises -- Behavioral: CBT for pain, mindfulness -- Interventional: Consider ESI if inadequate response -``` - -## SMART Goals Framework - -All treatment plans use SMART criteria for goal-setting: - -- **Specific**: Clear, well-defined outcome (not vague) -- **Measurable**: Quantifiable metrics or observable behaviors -- **Achievable**: Realistic given patient capabilities and resources -- **Relevant**: Aligned with patient priorities and values -- **Time-bound**: Specific timeframe for achievement - -### Examples - -**Good SMART Goals**: -- Reduce HbA1c from 8.5% to <7% within 3 months -- Walk independently 150 feet with assistive device by 8 weeks -- Decrease PHQ-9 depression score from 18 to <10 in 8 weeks -- Achieve knee flexion >90 degrees by postoperative day 14 -- Reduce pain from 7/10 to โ‰ค4/10 within 6 weeks - -**Poor Goals** (not SMART): -- "Feel better" (not specific or measurable) -- "Improve diabetes" (not specific or time-bound) -- "Get stronger" (not measurable) -- "Return to normal" (vague, not specific) - -## Workflow Examples - -### Standard Treatment Plan Workflow - -1. **Assess patient** - Complete history, physical, diagnostic testing -2. **Select template** - Choose appropriate template for clinical context -3. **Generate template** - `python generate_template.py --type [type]` -4. **Customize plan** - Fill in patient-specific information (de-identified) -5. **Set SMART goals** - Define measurable short and long-term goals -6. **Specify interventions** - Evidence-based pharmacological and non-pharmacological -7. **Create timeline** - Schedule appointments, milestones, reassessments -8. **Define monitoring** - Outcome measures, assessment frequency -9. **Validate completeness** - `python check_completeness.py plan.tex` -10. **Quality check** - `python validate_treatment_plan.py plan.tex` -11. **Review quality checklist** - Compare to `quality_checklist.md` -12. **Generate PDF** - `pdflatex plan.tex` -13. **Review with patient** - Shared decision-making, confirm understanding -14. **Implement and document** - Execute plan, track progress in clinical notes -15. **Reassess and modify** - Adjust plan based on outcomes - -### Multidisciplinary Care Plan Workflow - -1. **Identify team members** - PCP, specialists, therapists, case manager -2. **Create base plan** - Generate template for primary condition -3. **Add specialty sections** - Integrate consultant recommendations -4. **Coordinate goals** - Ensure alignment across disciplines -5. **Define communication** - Team meeting schedule, documentation sharing -6. **Assign responsibilities** - Clarify who manages each intervention -7. **Create care timeline** - Coordinate appointments across providers -8. **Share plan** - Distribute to all team members and patient -9. **Track collectively** - Shared monitoring and outcome tracking -10. **Regular team review** - Adjust plan collaboratively - -## Best Practices - -### Patient-Centered Care -โœ“ Involve patients in goal-setting and decision-making -โœ“ Respect cultural beliefs and language preferences -โœ“ Address health literacy with appropriate language -โœ“ Align plan with patient values and life circumstances -โœ“ Support patient activation and self-management - -### Evidence-Based Practice -โœ“ Follow current clinical practice guidelines -โœ“ Use interventions with proven efficacy -โœ“ Incorporate quality measures (HEDIS, CMS) -โœ“ Avoid low-value or ineffective interventions -โœ“ Update plans based on emerging evidence - -### Regulatory Compliance -โœ“ De-identify per HIPAA Safe Harbor method (18 identifiers) -โœ“ Document medical necessity for billing support -โœ“ Include informed consent documentation -โœ“ Sign and date all treatment plans -โœ“ Maintain professional documentation standards - -### Quality Documentation -โœ“ Complete all required sections -โœ“ Use clear, professional medical language -โœ“ Include specific, measurable goals -โœ“ Specify exact medications (dose, route, frequency) -โœ“ Define monitoring parameters and frequency -โœ“ Address safety and risk mitigation - -### Care Coordination -โœ“ Communicate plan to entire care team -โœ“ Define roles and responsibilities -โœ“ Coordinate across care settings -โœ“ Integrate specialist recommendations -โœ“ Plan for care transitions - -## Integration with Other Skills - -### Clinical Reports -- **SOAP Notes**: Document treatment plan implementation and progress -- **H&P Documents**: Initial assessment informs treatment planning -- **Discharge Summaries**: Summarize treatment plan execution -- **Progress Notes**: Track goal achievement and plan modifications - -### Scientific Writing -- **Citation Management**: Reference clinical practice guidelines -- **Literature Review**: Understand evidence base for interventions -- **Research Lookup**: Find current treatment recommendations - -### Research -- **Research Grants**: Treatment protocols for clinical trials -- **Clinical Trial Reports**: Document trial interventions - -## Clinical Practice Guidelines - -Treatment plans should align with evidence-based guidelines: - -### General Medicine -- American Diabetes Association (ADA) Standards of Care -- ACC/AHA Cardiovascular Guidelines -- GOLD COPD Guidelines -- JNC-8 Hypertension Guidelines -- KDIGO Chronic Kidney Disease Guidelines - -### Rehabilitation -- APTA Physical Therapy Clinical Practice Guidelines -- AOTA Occupational Therapy Practice Guidelines -- AHA/AACVPR Cardiac Rehabilitation Guidelines -- Stroke Rehabilitation Best Practices - -### Mental Health -- APA (American Psychiatric Association) Practice Guidelines -- VA/DoD Clinical Practice Guidelines for Mental Health -- NICE Guidelines (UK) -- Evidence-based psychotherapy protocols (CBT, DBT, ACT) - -### Pain Management -- CDC Opioid Prescribing Guidelines -- AAPM (American Academy of Pain Medicine) Guidelines -- WHO Analgesic Ladder -- Multimodal Analgesia Best Practices - -### Perioperative Care -- ERAS (Enhanced Recovery After Surgery) Society Guidelines -- ASA Perioperative Guidelines -- SCIP (Surgical Care Improvement Project) Measures - -## Professional Standards - -### Documentation Requirements -- Complete and accurate patient information -- Clear diagnosis with appropriate ICD-10 coding -- Evidence-based interventions -- Measurable goals and outcomes -- Defined monitoring and follow-up -- Provider signature, credentials, and date - -### Medical Necessity -Treatment plans must demonstrate: -- Medical appropriateness of interventions -- Alignment with diagnosis and severity -- Evidence supporting treatment choices -- Expected outcomes and benefit -- Frequency and duration justification - -### Legal Considerations -- Informed consent documentation -- Patient understanding and agreement -- Risk disclosure and mitigation -- Professional liability protection -- Compliance with state/federal regulations - -## Support and Resources - -### Getting Help - -1. **Check reference files** - Comprehensive guidance in `references/` directory -2. **Review templates** - See example structures in `assets/` directory -3. **Run validation scripts** - Identify issues with automated tools -4. **Consult SKILL.md** - Detailed documentation and best practices -5. **Review quality checklist** - Ensure all quality criteria met - -### External Resources - -- Clinical practice guidelines from specialty societies -- UpToDate and DynaMed for treatment recommendations -- AHRQ Effective Health Care Program -- Cochrane Library for intervention evidence -- CMS Quality Measures and HEDIS specifications -- HEDIS (Healthcare Effectiveness Data and Information Set) - -### Professional Organizations - -- American Medical Association (AMA) -- American Academy of Family Physicians (AAFP) -- Specialty society guidelines (ADA, ACC, AHA, APA, etc.) -- Joint Commission standards -- Centers for Medicare & Medicaid Services (CMS) - -## Frequently Asked Questions - -### How do I choose the right template? - -Match the template to your primary clinical focus: -- **Chronic medical conditions** โ†’ general_medical or chronic_disease -- **Post-surgery or injury** โ†’ rehabilitation or perioperative -- **Psychiatric conditions** โ†’ mental_health -- **Pain as primary issue** โ†’ pain_management - -### What if my patient has multiple conditions? - -Use the `chronic_disease_management_plan.tex` template for complex multimorbidity, or choose the template for the primary condition and add sections for comorbidities. - -### How often should treatment plans be updated? - -- **Initial creation**: At diagnosis or treatment initiation -- **Regular updates**: Every 3-6 months for chronic conditions -- **Significant changes**: When goals are met or treatment is modified -- **Annual review**: Minimum for all chronic disease plans - -### Can I modify the LaTeX templates? - -Yes! Templates are designed to be customized. Modify sections, add specialty-specific content, or adjust formatting to meet your needs. - -### How do I ensure HIPAA compliance? - -- Remove all 18 HIPAA identifiers (see Safe Harbor method) -- Use age ranges instead of exact ages (e.g., "60-65" not "63") -- Remove specific dates, use relative timelines -- Omit geographic identifiers smaller than state -- Use `check_deidentification.py` script from clinical-reports skill - -### What if validation scripts find issues? - -Review the specific issues identified, consult reference files for guidance, and revise the plan accordingly. Common issues include: -- Missing required sections -- Goals not meeting SMART criteria -- Insufficient monitoring parameters -- Incomplete medication information - -## License - -Part of the Claude Scientific Writer project. See main LICENSE file. - ---- - -For detailed documentation, see `SKILL.md`. For issues or questions, consult the comprehensive reference files in the `references/` directory. - diff --git a/scientific-skills/treatment-plans/SKILL.md b/scientific-skills/treatment-plans/SKILL.md index 24b4f49..ff82689 100644 --- a/scientific-skills/treatment-plans/SKILL.md +++ b/scientific-skills/treatment-plans/SKILL.md @@ -2,6 +2,8 @@ name: treatment-plans description: "Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability." allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Treatment Plan Writing diff --git a/scientific-skills/umap-learn/SKILL.md b/scientific-skills/umap-learn/SKILL.md index 411e2f5..0151579 100644 --- a/scientific-skills/umap-learn/SKILL.md +++ b/scientific-skills/umap-learn/SKILL.md @@ -1,6 +1,8 @@ --- name: umap-learn description: "UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data." +metadata: + skill-author: K-Dense Inc. --- # UMAP-Learn diff --git a/scientific-skills/uniprot-database/SKILL.md b/scientific-skills/uniprot-database/SKILL.md index bf389f6..92d2b41 100644 --- a/scientific-skills/uniprot-database/SKILL.md +++ b/scientific-skills/uniprot-database/SKILL.md @@ -1,6 +1,8 @@ --- name: uniprot-database description: "Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control." +metadata: + skill-author: K-Dense Inc. --- # UniProt Database diff --git a/scientific-skills/uspto-database/SKILL.md b/scientific-skills/uspto-database/SKILL.md index 9e036d5..123fdce 100644 --- a/scientific-skills/uspto-database/SKILL.md +++ b/scientific-skills/uspto-database/SKILL.md @@ -1,6 +1,8 @@ --- name: uspto-database description: "Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches." +metadata: + skill-author: K-Dense Inc. --- # USPTO Database diff --git a/scientific-skills/vaex/SKILL.md b/scientific-skills/vaex/SKILL.md index 9174485..ace1caa 100644 --- a/scientific-skills/vaex/SKILL.md +++ b/scientific-skills/vaex/SKILL.md @@ -1,6 +1,8 @@ --- name: vaex description: Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that don't fit in memory. +metadata: + skill-author: K-Dense Inc. --- # Vaex diff --git a/scientific-skills/venue-templates/SKILL.md b/scientific-skills/venue-templates/SKILL.md index e636e6c..bdbc2f1 100644 --- a/scientific-skills/venue-templates/SKILL.md +++ b/scientific-skills/venue-templates/SKILL.md @@ -2,6 +2,8 @@ name: venue-templates description: Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates. allowed-tools: [Read, Write, Edit, Bash] +metadata: + skill-author: K-Dense Inc. --- # Venue Templates diff --git a/scientific-skills/zarr-python/SKILL.md b/scientific-skills/zarr-python/SKILL.md index acefa67..61a7af0 100644 --- a/scientific-skills/zarr-python/SKILL.md +++ b/scientific-skills/zarr-python/SKILL.md @@ -1,6 +1,8 @@ --- name: zarr-python description: "Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines." +metadata: + skill-author: K-Dense Inc. --- # Zarr Python diff --git a/scientific-skills/zinc-database/SKILL.md b/scientific-skills/zinc-database/SKILL.md index 6f85f9d..c6abc1f 100644 --- a/scientific-skills/zinc-database/SKILL.md +++ b/scientific-skills/zinc-database/SKILL.md @@ -1,6 +1,8 @@ --- name: zinc-database description: "Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery." +metadata: + skill-author: K-Dense Inc. --- # ZINC Database