- Each forecast now extends to 2025-12 regardless of historical data length
- Step 1 (12 points): forecasts 36 months ahead to 2025-12
- Step 25 (36 points): forecasts 12 months ahead to 2025-12
- GIF shows full forecast horizon at every animation step
- X-axis fixed to 2022-01 to 2025-12 (full data range)
- Y-axis fixed to 0.72°C to 1.52°C (full value range)
- Background shows all observed data (faded gray) + final forecast reference (faded red dashed)
- Foreground shows current step data (bright blue) + current forecast (bright red)
- GIF size reduced from 918KB to 659KB
Create an all-out demonstration showing how TimesFM forecasts evolve
as more historical data is added:
- generate_animation_data.py: Runs 25 incremental forecasts (12→36 points)
- interactive_forecast.html: Single-file HTML with Chart.js slider
- Play/Pause animation control
- Shows historical data, forecast, 80%/90% CIs, and actual future data
- Live stats: forecast mean, max, min, CI width
- generate_gif.py: Creates animated GIF for embedding in markdown
- forecast_animation.gif: 25-frame animation (896 KB)
Interactive features:
- Slider to manually step through forecast evolution
- Auto-play with 500ms per frame
- Shows how each additional data point changes the forecast
- Confidence intervals narrow as more data is added
- Change title from 'Above 1951-1980 Baseline' to clearer example description
- New title: 'TimesFM Zero-Shot Forecast Example / 36-month Temperature Anomaly → 12-month Forecast'
- Makes it clear this is a demonstration with limited input data
This branch was originally created from feat/markdown-mermaid-writing-skill
for development purposes, but the timesfm-forecasting skill should be
independent of PR #50.
- Remove scientific-skills/markdown-mermaid-writing/ directory
- Remove reference to markdown-mermaid-writing from SKILL.md integration section
- This PR now stands alone and does not require PR #50 to be merged first
Model weights (~800 MB) download on-demand from HuggingFace when skill
is first used. Preflight checker ensures sufficient resources before
any download begins.
Add comprehensive TimesFM forecasting skill with mandatory system
preflight checks (RAM/GPU/disk), end-to-end CSV forecasting script,
full API reference, data preparation guide, and hardware requirements
documentation. Supports TimesFM 2.5 (200M), 2.0 (500M), and legacy
v1.0 with automatic batch size recommendations based on hardware.
Added '## ⚠️ Common pitfalls' section covering:
- Radar chart syntax (radar-beta vs radar, axis vs x-axis, curve syntax)
- XY Chart vs Radar syntax comparison table
- Accessibility notes for diagrams that don't support accTitle/accDescr
Prevents the x-axis → radar-beta confusion that occurred in the example
research report.
Changed from invalid 'radar' with 'x-axis' syntax to proper 'radar-beta'
syntax with axis/curve keywords as per references/diagrams/radar.md.
Also removed accTitle/accDescr (radar-beta doesn't support them) and
added italic description above the code block per accessibility requirements.
All instances of 'Boreal Bytes' updated to 'borealBytes' (as @borealBytes
in narrative context) across issue, PR, kanban, and SKILL.md.
Files: issue-00000050, pr-00000050, SKILL.md
All 40 references to borealBytes/opencode updated to the correct source:
https://github.com/SuperiorByteWorks-LLC/agent-project
Affected files: SKILL.md, all 24 diagram guides, 9 templates, issue and PR
docs, plus assets/examples/example-research-report.md (new file).
The example report demonstrates full skill usage: flowchart, sequence,
timeline, xychart, radar diagrams — all with accTitle/accDescr and
classDef colors, no %%{init}. Covers HEK293T CRISPR editing efficiency
as a realistic scientific context.
New skill establishing markdown + Mermaid diagrams as the default and
canonical documentation format for all scientific skill outputs.
Core principle (from K-Dense Discord, 2026-02-19): Mermaid in markdown
is the source of truth — text-based, version-controlled, token-efficient,
universally renderable. Python/AI images are downstream conversions only.
SKILL.md includes:
- Full 'source format' philosophy with three-phase workflow diagram
- 24-entry diagram type selection table with links to each guide
- 9-entry document template index
- Per-skill integration guides (scientific-schematics, scientific-writing,
literature-review, and any other output-producing skill)
- Quality checklist for finalizing documents from any skill
- Full attribution for ported Apache-2.0 content
Originated from conversation between Clayton Young (Boreal Bytes) and the
K-Dense team regarding documentation standards for shared scientific skills.
All content ported from borealBytes/opencode under Apache-2.0 license with
attribution headers prepended to each file.
- references/markdown_style_guide.md (~733 lines): full markdown formatting,
citation, collapsible sections, emoji, Mermaid integration, and template
selection guide
- references/mermaid_style_guide.md (~458 lines): full Mermaid standards —
emoji set, classDef color palette, accessibility (accTitle/accDescr),
theme neutrality (no %%{init}), and diagram type selection table
- references/diagrams/ (24 files): per-type exemplars, tips, and templates
for all Mermaid diagram types
- templates/ (9 files): PR, issue, kanban, ADR, presentation, how-to,
status report, research paper, project docs
Source: https://github.com/borealBytes/opencode
New skill for generating scientific infographics including:
- SKILL.md with comprehensive guidelines for infographic creation
- Design principles and color palette references
- Scripts for AI-powered infographic generation
- Support for various infographic types (statistical, process, comparison, etc.)
Co-authored-by: Cursor <cursoragent@cursor.com>
- Added criteria for identifying high-quality literature, emphasizing the importance of Tier-1 journals and citation counts.
- Updated guidelines for citation finding to prioritize influential papers and reputable authors.
- Revised abstract writing instructions to reflect the preference for flowing paragraphs over structured formats.
- Included best practices for generating AI schematics, specifically regarding figure numbering and content clarity.
- Replace direct calls to AllChem, Pairs, and Torsions with rdFingerprintGenerator in similarity_search.py
- Update example code in SKILL.md to reflect the new API usage
- Maintain existing functionality while adopting the modern fingerprint generation interface recommended by RDKit
- Updated SKILL.md in citation management to include best practices for identifying seminal and high-impact papers, emphasizing citation count thresholds, venue quality tiers, and author reputation indicators.
- Expanded literature review SKILL.md to prioritize high-impact papers, detailing citation metrics, journal tiers, and author reputation assessment.
- Added comprehensive evaluation strategies for paper impact and quality in literature_search_strategies.md, including citation count significance and journal impact factor guidance.
- Improved research lookup scripts to prioritize results based on citation count, venue prestige, and author reputation, enhancing the quality of research outputs.
- Add new nstc_guidelines.md with official requirements and practical insights
- Include CM03 format specifications and page limits by field
- Integrate LaTeX templates (CTAN package, Overleaf templates)
- Add practical writing strategies from three expert reviewers:
* Prof. Huang You-Ping (NPU): Scoring thresholds and section strategies
* Prof. Guo Yao-Huang: Closed-loop logic and KPI formulation
* President Wei Yao-Hui (Mackay): SMART principles and review dimensions
- Include budget preparation guidance and common pitfalls
- Update SKILL.md to reference NSTC in overview and agency list
This comprehensive guide provides 700+ lines of actionable guidance for
Taiwan NSTC (formerly MOST/NSC) research proposal writing.
