meodai/skill.color-expert

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.

What it solves

Coding agents often give superficial or incorrect answers about color — from picking palettes to explaining color spaces. This skill gives them a deep, curated knowledge base of color science, so they can answer like an expert. It solves the problem of agents lacking reliable color knowledge by providing a structured, indexed collection of references, tools, and guidelines.

How it works

The skill has three layers:

  1. SKILL.md — the core facts and recommendations loaded immediately by the agent.
  2. references/INDEX.md — a compact map to 185 markdown reference files, covering historical and contemporary color science, techniques, and tools.
  3. references/ — deep material: video transcripts, article summaries, scraped websites, and research notes.

The knowledge base is built by capturing color resources (videos, PDFs, repos, articles) and converting them into markdown via tools like yt-dlp and markitdown. Everything is indexed and organized into historical, contemporary, and techniques sections. There's also an evals/ folder with realistic trigger prompts and task prompts to test and refine when the skill activates and how well it answers.

Who it's for

For developers and teams using coding agents (Claude Code, Codex, Cursor, etc.) who need accurate color guidance in their work — whether building design tools, generating palettes, explaining color theory, or ensuring accessibility. Also for anyone curating color knowledge, as it includes a maintenance guide and roadmap.

Highlights

  • Three-layer structure: SKILL.md for quick answers, INDEX.md for navigation, deep references for depth.
  • 185 markdown reference files (~370,000 words) covering historical color science, contemporary theory, and practical techniques.
  • Catalogs 74 online tools and 109 distinct video sources.
  • Includes scripts to refresh stats and a clear maintenance guide.
  • Evals folder with trigger and task prompts to verify the skill's performance.
  • Key opinions backed by research: use OKLCH/OKLAB over HSL, avoid coolors.co, integrated mixing, etc.

Related

  • Project
    InternScience/Awesome-Scientific-Skills

    A curated, open collection of Agent Skills for scientific research, covering bioinformatics, chemistry, data analysis, literature search, and more. It gathers high-quality, science-relevant skills from official and community sources into a clone-ready repository that works across multiple AI coding agents.

  • Project
    Leonxlnx/taste-skill

    Taste Skill is an agent plugin that upgrades AI coding assistants to produce high-quality, art-directed website designs and dashboards instead of generic layouts.

  • Project
    Astro-Han/karpathy-llm-wiki

    A reusable agent skill that enables LLMs to build and maintain a structured wiki of synthesized knowledge, moving beyond simple RAG by compiling sources into durable, cross-linked markdown pages.

  • Project
    Appllama/appllama-skills

    A set of agent skills that enable AI agents to research top-grossing mobile apps and build high-fidelity, simulator-verified Expo and React Native screens.

  • Project
    kangarooking/kangarooking-skills

    A collection of structured, open-source Agent Skills compatible with the Agent Skills standard, providing reusable workflows for content creation, image generation, and AI project engineering.