Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Agent skill for color science expertise. Many references covering color spaces, accessibility (APCA, WCAG), palette generation, pigment mixing, and historical color theory. Works with Claude Code, Codex, Cursor, Copilot & others.
| Date | Stars |
|---|---|
| 2026-07-31 | 531 |
| 2026-08-02 | 535 |
| 2026-08-06 | 535 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# color-expert
An [agent skill](https://agentskills.io) that turns your coding agent into a color science expert. Built from resources I keep looking up, returning to, and sharing with others.
## What this is
This started as a simple skill file with some color theory notes. Over time it grew into a comprehensive knowledge base as I kept pasting videos, articles, tools, and papers that I find myself referencing again and again — both for my own work building color tools and for explaining color concepts to others.
The skill has three layers:
1. **`SKILL.md`** (~200 lines) — The "greatest hits" that your agent loads immediately. Key facts, corrections, tool recommendations, and guidelines that answer most color questions without needing to dig deeper.
2. **`references/INDEX.md`** (~220 lines) — A structured lookup table your agent can scan to find the right reference file for a specific topic.
3. **`references/`** (144 markdown files, ~286K words) — Deep reference material: full video transcripts, article summaries, library documentation, scraped websites, and research notes.
There is also a lightweight **`evals/`** folder for realistic trigger and task prompts so the skill can be reviewed against actual usage instead of only edited by intuition.
## How it was built
The collection process is simple: when I come across a color resource worth keeping — a YouTube video, a GitHub repo, a research paper, an article — I paste the URL and the skill's workflow captures it:
- **Videos** get transcribed via [`yt-dlp`](https://github.com/yt-dlp/yt-dlp), summarized, and key concepts extracted
- **PDFs and documents** get converted to markdown via [`markitdown`](https://github.com/microsoft/markitdown) by Microsoft
- **GitHub repos** get their README/docs fetched and documented
- **Articles** get their content extracted and saved
- **Books mentioned in videos** get searched on Archive.org; freely available PDFs get downloaded
- **Websites** (like huevaluechroma.com) get fully scraped chapter by chapter
- **Tools and links** mentioned in any resource get collected into the Online Tools table
Everything goes into one of three folders and gets indexed.
## Structure
```text
SKILL.md # The skill definition (loaded on activation)
CLAUDE.md # Claude Code repo instructions
references/
INDEX.md # Master lookup table
historical/ # Pre-digital color science
*.md # Ostwald, Helmholtz, Bezold, Ridgway, ISCC-NBS,
# Moses Harris, Amy Sawyer, Lewis/Ladd-Franklin,
# Caravaggio's pigments, Itten critique...
pdfs/ # Source books from Archive.org (gitignored, ~236MB)
contemporary/ # Modern color science & theory
*.md # OKLAB articles, Briggs lectures, CSA webinars,
# Pixar Color Science, bird tetrachromacy, OLO,
# Acerola, Juxtopposed, Computerphile, GenColor paper...
huevaluechroma/ # Full scrape of David Briggs's site (11 chapters)
colorandcontrast/ # colorandcontrast.com extracted content
pdfs/ # Research papers (gitignored)
techniques/ # Tools, libraries, methods, practical application
*.md # Spectral.js, Culori, Color.js, RampenSau, Poline,
# RYBitten, PickyPalette, Color Buddy lint rules,
# APCA/Myndex, IQ cosine formula, Cubehelix,
# Tyler Hobbs generative color, Fontana approach,
# pixel art palettes, Book of Shaders, LYGIA,
# paint mixing lectExcerpt of 11,398 characters
Read on GitHub
95
Mizu · Japan
2
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:68af19e9288b8462, topic:copilot
matched fp:68af19e9288b8462, topic:chatgpt