Skip to content
Agentmart
Submit a tool

CLAUDE.md · meodai/skill.color-expert

CLAUDE.md from meodai/skill.color-expert: 31 lines covering Project Overview, Architecture, No Build/Test/Lint, Editing Guidelines.

Template by meodai

IndexedCC-BY-4.0★ 621
Write a review

Chalk Labs

Need help deploying CLAUDE.md · meodai/skill.color-expert?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code. Read the repository before you give any tool access to your data.

curl -fsSL https://raw.githubusercontent.com/meodai/skill.color-expert/main/CLAUDE.md -o CLAUDE.md

Read it and adapt it to your project before use.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The CLAUDE.md file that meodai/skill.color-expert (621 stars) keeps for coding agents. It has 31 lines in 4 sections: Project Overview; Architecture; No Build/Test/Lint; Editing Guidelines. Use it as a model for your own project's instructions.

Use cases: documentation

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

What's in it

A CLAUDE.md file: project memory Claude Code loads at the start of every session.

For
Claude Code
Length
31 lines
File
CLAUDE.md

Sections

  1. Project Overview
  2. Architecture
  3. No Build/Test/Lint
  4. Editing Guidelines

First lines (shown under the repo's CC-BY-4.0 license)

# CLAUDE.md

This file provides guidance when working with code in this repository.

## Project Overview

This is an **agent skill** (compatible with Claude Code, Codex, Cursor, Copilot, OpenCode, and others via [agentskills.io](https://agentskills.io)). It contains a `SKILL.md` file that serves as a color expertise knowledge base, automatically loaded when the agent handles color-related tasks (naming, theory, spaces, accessibility, perception).

## Architecture

- `SKILL.md` — The skill definition with YAML frontmatter (`name`, `description`) and structured color knowledge. Loaded when color work is detected.
- `references/INDEX.md` — Compact map: one line per reference file, meant to be read whole.
- `references/<dir>/INDEX.md` — Full summaries and source links per directory; opened only when the one-liner is too terse.
- `references/techniques/ONLINE-TOOLS.md`, `references/PDFS.md` — Online tool catalogue and primary-source PDF list.
- `references/historical/` — Pre-digital color science (Ostwald, Helmholtz, ISCC-NBS, etc.)
- `references/contemporary/` — Modern color science (OKLAB, Briggs, CSA webinars, etc.)
- `references/techniques/` — Tools, libraries, methods (Spectral.js, Culori, APCA, palette generation, etc.)

## No Build/Test/Lint

There are no commands to run. This project is purely declarative content consumed by agent skill systems.

## Editing Guidelines

- Keep SKILL.md frontmatter `description` field accurate — it controls when the skill triggers.
- The skill is referenced by name (`color-expert`).
- SKILL.md should be concise "greatest hits" (~200 lines) — the agent already has broad color knowledge; the skill should correct misconceptions, highlight non-obvious facts, and point to the right tools.
- Deep content goes in `references/` files, not in SKILL.md.
- PDFs are gitignored; archive.org source links are preserved in every reference file and listed in `references/PDFS.md`.
- Counts quoted in `README.md` come from `scripts/stats.sh` — refresh with that, don't hand-edit them.

Signals

Stars
621
Forks
39
Open issues
0
Last commit (this folder)
Oct 7, 2026 (23 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
CC-BY-4.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from meodai

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get CLAUDE.md · meodai/skill.color-expert running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying CLAUDE.md · meodai/skill.color-expert?

CallGet help
Cite this page

CLAUDE.md · meodai/skill.color-expert. Agent Mart. https://agentmart.dev/templates/meodai-skill-color-expert-claude-md (last updated 2026-10-24)