Agent skill · AI & Agents

claude-md-generator

Use when the user asks to generate or update a project's CLAUDE or AGENTS context file from a codebase scan. Writes a focused file under 100 lines containing only the non-obvious build commands, conventions, and gotchas Claude Code needs.

Varnan-Techgithub.com/Varnan-TechGitHub ↗
claude-codecopilotMIT
Install
npx skills add Varnan-Tech/opendirectory --skill claude-md-generator --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 5
SKILL.md size: 8 KB
Bundled scripts: none
Version: 1.0.0
Declared author: OpenDirectory
Requires: [claude-code, gemini-cli, github-copilot]
Path: skills/claude-md-generator/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 571
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# CLAUDE.md Generator Read the codebase. Write a CLAUDE.md that tells Claude exactly what it needs: no more, no less. --- **Critical rule:** A good CLAUDE.md is under 100 lines. It contains only information Claude cannot derive from reading the code itself. Do not auto-write the file: always show the draft and wait for user approval first. **Code snippet rule:** Never include inline code examples in CLAUDE.md. Instead use `file.ts:42` references. Code in CLAUDE.md wastes tokens and goes stale. --- ## Step 1: Detect Mode Determine which of three modes to run: **create**: No CLAUDE.md exists. Write one from scratch. **update**: A CLAUDE.md exists. Improve it without discarding custom content. **audit**: Score all CLAUDE.md files in the project A-F and output a quality report. If the user says "audit", "check", "review", or "grade" my CLAUDE.md, run audit mode. ```bash # Discover ALL CLAUDE.md locations find . -name "CLAUDE.md" -not -path "*/node_modules/*" -not -path "*/.git/*" 2>/dev/null ls ~/.claude/CLAUDE.md 2>/dev/null && echo "Global CLAUDE.md found" ls .claude.local.md 2>/dev/null && echo ".claude.local.md found" ``` If multiple CLAUDE.md files are found: list them. Ask: "Foun

What's inside
Steps it walks through
  1. Step 1: Detect Mode
  2. Step 2: Audit Mode (skip to Step 3 if create/update)
  3. Step 3: Scan Project Structure
  4. Step 4: Extract Build and Test Commands
  5. Step 5: Find Code Style and Gotchas
  6. Step 6: Generate CLAUDE.md Draft with Gemini
  7. Step 7: Self-QA
  8. Step 8: Present Draft and Wait for Approval
  9. What NOT to Include
Ships with 4 files
  • .env.example
  • README.md
  • evals/evals.json
  • references/section-guide.md
Commands it runs
Discover ALL CLAUDE.md locations
find . -name "CLAUDE.md" -not -path "*/node_modules/*" -not -path "*/.git/*" 2>/dev/null
ls ~/.claude/CLAUDE.md 2>/dev/null && echo "Global CLAUDE.md found"
ls .claude.local.md 2>/dev/null && echo ".claude.local.md found"
Project type and package manager
ls package.json yarn.lock pnpm-lock.yaml bun.lockb requirements.txt pyproject.toml Cargo.toml go.mod 2>/dev/null
Top-level directory structure
find . -maxdepth 2 -type d \
npm/yarn/pnpm/bun scripts
cat package.json 2>/dev/null \
More from opendirectory
All skills →
About this skill
What does the claude-md-generator skill do?

Use when the user asks to generate or update a project's CLAUDE or AGENTS context file from a codebase scan. Writes a focused file under 100 lines containing only the non-obvious build commands, conventions, and gotchas Claude Code needs.

How do I install it?

Run `npx skills add Varnan-Tech/opendirectory --skill claude-md-generator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From Varnan-Tech/opendirectory, a repository with 571 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going