mirror of
https://github.com/K-Dense-AI/claude-scientific-skills.git
synced 2026-01-26 16:58:56 +08:00
Update SKILL.md files to add double quotation marks for all skills, ensuring clarity and consistency across all entries.
This commit is contained in:
Haoxuan "Orion" Li
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: pdf
|
||||
description: Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
|
||||
description: "Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale."
|
||||
license: Proprietary. LICENSE.txt has complete terms
|
||||
---
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: exploratory-data-analysis
|
||||
description: Comprehensive exploratory data analysis (EDA) toolkit for analyzing datasets and generating actionable insights. Use this skill when users provide data files and request analysis, exploration, insights, or understanding of their data. Handles CSV, Excel (.xlsx/.xls), JSON, Parquet, TSV, Feather, HDF5, and Pickle files. Automatically performs statistical analysis including distributions, correlations, outlier detection, missing data patterns, and data quality assessment. Generates professional visualizations (histograms, box plots, correlation heatmaps, scatter matrices) and comprehensive markdown reports with automated insights. Key triggers: "analyze this data", "explore this dataset", "what's in this file", "data insights", "statistical summary", "data visualization", "EDA", "exploratory analysis", "data profiling", "understand my data", "find patterns", "data quality", "missing data", "outliers", "correlations", "distributions". Always outputs structured markdown reports with embedded visualizations and actionable recommendations.
|
||||
description: "Comprehensive exploratory data analysis (EDA) toolkit for analyzing datasets and generating actionable insights. Use this skill when users provide data files and request analysis, exploration, insights, or understanding of their data. Handles CSV, Excel (.xlsx/.xls), JSON, Parquet, TSV, Feather, HDF5, and Pickle files. Automatically performs statistical analysis including distributions, correlations, outlier detection, missing data patterns, and data quality assessment. Generates professional visualizations (histograms, box plots, correlation heatmaps, scatter matrices) and comprehensive markdown reports with automated insights. Key triggers: \"analyze this data\", \"explore this dataset\", \"what's in this file\", \"data insights\", \"statistical summary\", \"data visualization\", \"EDA\", \"exploratory analysis\", \"data profiling\", \"understand my data\", \"find patterns\", \"data quality\", \"missing data\", \"outliers\", \"correlations\", \"distributions\". Always outputs structured markdown reports with embedded visualizations and actionable recommendations."
|
||||
---
|
||||
|
||||
# Exploratory Data Analysis
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: hypothesis-generation
|
||||
description: Generate robust, testable scientific hypotheses grounded in existing literature. Use this skill when users need to formulate hypotheses from observations, design experiments to test hypotheses, explore competing explanations for phenomena, develop testable predictions, or create mechanistic explanations across any scientific domain. This skill is essential for hypothesis formation, experimental design, developing testable predictions, proposing mechanistic explanations, generating alternative theories, designing studies to distinguish between competing hypotheses, creating falsifiable predictions, and systematically evaluating hypothesis quality. Apply when users ask about "why" something happens, need to explain observations, want to test theories, design experiments, propose mechanisms, generate predictions, or explore alternative explanations in biology, chemistry, physics, medicine, psychology, or any scientific field.
|
||||
description: "Generate robust, testable scientific hypotheses grounded in existing literature. Use this skill when users need to formulate hypotheses from observations, design experiments to test hypotheses, explore competing explanations for phenomena, develop testable predictions, or create mechanistic explanations across any scientific domain. This skill is essential for hypothesis formation, experimental design, developing testable predictions, proposing mechanistic explanations, generating alternative theories, designing studies to distinguish between competing hypotheses, creating falsifiable predictions, and systematically evaluating hypothesis quality. Apply when users ask about \"why\" something happens, need to explain observations, want to test theories, design experiments, propose mechanisms, generate predictions, or explore alternative explanations in biology, chemistry, physics, medicine, psychology, or any scientific field."
|
||||
---
|
||||
|
||||
# Scientific Hypothesis Generation
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: peer-review
|
||||
description: Comprehensive scientific peer review toolkit for evaluating manuscripts, papers, preprints, and research documents across all disciplines. Use this skill to conduct systematic peer review following established scientific standards, providing constructive feedback on methodology, statistical analysis, experimental design, data interpretation, reproducibility, ethical considerations, and scientific rigor. Includes structured evaluation workflows, reporting standards compliance checks, figure/data integrity assessment, and guidance for writing professional review reports. Applicable to original research articles, reviews, meta-analyses, methods papers, short reports, and preprints in biology, chemistry, physics, medicine, computational sciences, and interdisciplinary research. Essential for manuscript evaluation, grant review, conference paper assessment, and maintaining scientific quality standards.
|
||||
description: "Comprehensive scientific peer review toolkit for evaluating manuscripts, papers, preprints, and research documents across all disciplines. Use this skill to conduct systematic peer review following established scientific standards, providing constructive feedback on methodology, statistical analysis, experimental design, data interpretation, reproducibility, ethical considerations, and scientific rigor. Includes structured evaluation workflows, reporting standards compliance checks, figure/data integrity assessment, and guidance for writing professional review reports. Applicable to original research articles, reviews, meta-analyses, methods papers, short reports, and preprints in biology, chemistry, physics, medicine, computational sciences, and interdisciplinary research. Essential for manuscript evaluation, grant review, conference paper assessment, and maintaining scientific quality standards."
|
||||
---
|
||||
|
||||
# Scientific Critical Evaluation and Peer Review
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: scientific-brainstorming
|
||||
description: Structured conversational brainstorming partner for scientific research ideation and creative problem-solving. Activates when scientists need to: generate novel research ideas and hypotheses; explore interdisciplinary connections and cross-domain analogies; challenge research assumptions and conventional thinking; overcome creative blocks and mental barriers; develop innovative methodologies and experimental approaches; synthesize disparate concepts into coherent research directions; identify unexpected research opportunities and unexplored angles; brainstorm solutions to complex scientific problems; expand research scope beyond obvious approaches; connect findings across different scientific fields; develop collaborative research proposals; explore "what if" scenarios and alternative hypotheses; identify gaps in current scientific understanding; generate research questions from preliminary observations; develop creative approaches to experimental design; brainstorm applications of emerging technologies; explore unconventional data analysis methods; identify novel research collaborations; develop scientific communication strategies; and think through research problems from multiple fresh perspectives. This skill provides structured brainstorming workflows including divergent exploration, connection-making, critical evaluation, and synthesis phases, while maintaining conversational collaboration and domain-aware guidance across scientific disciplines.
|
||||
description: "Structured conversational brainstorming partner for scientific research ideation and creative problem-solving. Activates when scientists need to: generate novel research ideas and hypotheses; explore interdisciplinary connections and cross-domain analogies; challenge research assumptions and conventional thinking; overcome creative blocks and mental barriers; develop innovative methodologies and experimental approaches; synthesize disparate concepts into coherent research directions; identify unexpected research opportunities and unexplored angles; brainstorm solutions to complex scientific problems; expand research scope beyond obvious approaches; connect findings across different scientific fields; develop collaborative research proposals; explore \"what if\" scenarios and alternative hypotheses; identify gaps in current scientific understanding; generate research questions from preliminary observations; develop creative approaches to experimental design; brainstorm applications of emerging technologies; explore unconventional data analysis methods; identify novel research collaborations; develop scientific communication strategies; and think through research problems from multiple fresh perspectives. This skill provides structured brainstorming workflows including divergent exploration, connection-making, critical evaluation, and synthesis phases, while maintaining conversational collaboration and domain-aware guidance across scientific disciplines."
|
||||
---
|
||||
|
||||
# Scientific Brainstorming
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: scientific-critical-thinking
|
||||
description: Apply systematic scientific critical thinking to rigorously evaluate research methodology, statistical analyses, evidence quality, and scientific claims. Use this skill when: analyzing research papers for methodological flaws and biases; evaluating experimental designs for validity threats; assessing statistical methods, power, multiple comparisons, and effect sizes; identifying logical fallacies and cognitive biases in scientific arguments; reviewing evidence hierarchies and GRADE criteria; critiquing causal claims vs correlational findings; evaluating study quality using established frameworks (Cochrane ROB, Newcastle-Ottawa); detecting publication bias, p-hacking, and selective reporting; assessing confounding, selection bias, and measurement validity; reviewing research proposals and study protocols; evaluating media reports of scientific findings; conducting systematic literature reviews; determining confidence levels in scientific conclusions; distinguishing between exploratory and confirmatory findings; and providing constructive methodological feedback for improving research rigor.
|
||||
description: "Apply systematic scientific critical thinking to rigorously evaluate research methodology, statistical analyses, evidence quality, and scientific claims. Use this skill when: analyzing research papers for methodological flaws and biases; evaluating experimental designs for validity threats; assessing statistical methods, power, multiple comparisons, and effect sizes; identifying logical fallacies and cognitive biases in scientific arguments; reviewing evidence hierarchies and GRADE criteria; critiquing causal claims vs correlational findings; evaluating study quality using established frameworks (Cochrane ROB, Newcastle-Ottawa); detecting publication bias, p-hacking, and selective reporting; assessing confounding, selection bias, and measurement validity; reviewing research proposals and study protocols; evaluating media reports of scientific findings; conducting systematic literature reviews; determining confidence levels in scientific conclusions; distinguishing between exploratory and confirmatory findings; and providing constructive methodological feedback for improving research rigor."
|
||||
---
|
||||
|
||||
# Scientific Critical Thinking
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: scientific-visualization
|
||||
description: Create publication-ready scientific figures, plots, charts, and visualizations using matplotlib, seaborn, and plotly. Use this skill for any scientific data visualization task including: creating figures for research papers and manuscripts; preparing plots for journal submission (Nature, Science, Cell, PLOS, PNAS, etc.); making publication-quality figures with proper resolution, fonts, and formatting; ensuring colorblind accessibility and accessibility compliance; creating multi-panel figures with consistent styling; visualizing statistical data with error bars, significance markers, and proper statistical representation; exporting figures in correct formats (PDF, EPS, TIFF, PNG) with appropriate DPI; following journal-specific requirements and style guidelines; improving existing figures to meet publication standards; creating figures that work in both color and grayscale; visualizing experimental results, data analysis outputs, statistical comparisons, time series, distributions, correlations, heatmaps, scatter plots, bar charts, line plots, box plots, violin plots, and other scientific plot types; ensuring figures are clear, accurate, accessible, and professional; applying proper typography, color palettes, and layout principles; creating figures for presentations, posters, and scientific communication; visualizing genomics data, microscopy images, experimental measurements, and research findings.
|
||||
description: "Create publication-ready scientific figures, plots, charts, and visualizations using matplotlib, seaborn, and plotly. Use this skill for any scientific data visualization task including: creating figures for research papers and manuscripts; preparing plots for journal submission (Nature, Science, Cell, PLOS, PNAS, etc.); making publication-quality figures with proper resolution, fonts, and formatting; ensuring colorblind accessibility and accessibility compliance; creating multi-panel figures with consistent styling; visualizing statistical data with error bars, significance markers, and proper statistical representation; exporting figures in correct formats (PDF, EPS, TIFF, PNG) with appropriate DPI; following journal-specific requirements and style guidelines; improving existing figures to meet publication standards; creating figures that work in both color and grayscale; visualizing experimental results, data analysis outputs, statistical comparisons, time series, distributions, correlations, heatmaps, scatter plots, bar charts, line plots, box plots, violin plots, and other scientific plot types; ensuring figures are clear, accurate, accessible, and professional; applying proper typography, color palettes, and layout principles; creating figures for presentations, posters, and scientific communication; visualizing genomics data, microscopy images, experimental measurements, and research findings."
|
||||
---
|
||||
|
||||
# Scientific Visualization
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: statistical-analysis
|
||||
description: Comprehensive statistical analysis toolkit for rigorous academic research using Python. This skill handles hypothesis testing (t-tests, ANOVA, chi-square, non-parametric tests), regression analysis (linear, multiple, logistic), correlation analysis, Bayesian statistics, and power analysis. It provides systematic workflows for test selection, assumption checking, effect size calculation, diagnostic visualization, and APA-style reporting. Use this skill when you need to: analyze data statistically, choose appropriate statistical tests, check assumptions before analysis, calculate effect sizes and confidence intervals, conduct power analysis for study planning, perform hypothesis testing or regression analysis, interpret statistical results, create publication-ready statistical reports, handle assumption violations, conduct Bayesian analysis, or generate diagnostic plots and statistical visualizations. Essential for research data analysis, experimental design validation, statistical modeling, and academic reporting.
|
||||
description: "Comprehensive statistical analysis toolkit for rigorous academic research using Python. This skill handles hypothesis testing (t-tests, ANOVA, chi-square, non-parametric tests), regression analysis (linear, multiple, logistic), correlation analysis, Bayesian statistics, and power analysis. It provides systematic workflows for test selection, assumption checking, effect size calculation, diagnostic visualization, and APA-style reporting. Use this skill when you need to: analyze data statistically, choose appropriate statistical tests, check assumptions before analysis, calculate effect sizes and confidence intervals, conduct power analysis for study planning, perform hypothesis testing or regression analysis, interpret statistical results, create publication-ready statistical reports, handle assumption violations, conduct Bayesian analysis, or generate diagnostic plots and statistical visualizations. Essential for research data analysis, experimental design validation, statistical modeling, and academic reporting."
|
||||
---
|
||||
|
||||
# Statistical Analysis
|
||||
|
||||
Reference in New Issue
Block a user