Sandbox
Sign in
@sruthik27/creating-claude-md
Skills#Claude Code#Codex#Any agent#Coding#Docs

Agent skill for creating CLAUDE.md from a repo scan

This skill helps an agent build a clean `CLAUDE.md` or `AGENTS.md` for a repository from scratch. It scans the repo for existing signals, then asks six focused questions for the decisions only the user can supply, and trims the result to a short, useful file.

63 stars•4 forks•Updated 4mo ago
Who it's for

Builders who want their agent to set up repo memory for a new project or replace a bad one.

What it delivers

You can get a concise project memory file that helps your agent avoid repeat mistakes and follow repo-specific rules.

What it does

Repo scan

Looks at manifests, folder structure, linter configs, git history, docs, and configured MCPs before writing anything.

Six-question interview

Asks for the missing judgment calls: why the repo exists, gotchas, out-of-scope work, approval gates, testing philosophy, and external docs.

Short output cap

Keeps the generated `CLAUDE.md` under 80 lines, with 120 lines as a hard maximum.

Rewrite-first approach

Targets brand-new memory files or complete rewrites, not incremental cleanup of an existing `CLAUDE.md`.

Skill format support

Ships as plain Markdown with YAML frontmatter in `SKILL.md`, so it can work with Claude Code, Codex, and other skill-aware agents.

How to get it

  1. 1Clone into the skills directory
    git clone https://github.com/sruthik27/creating-claude-md.git ~/.claude/skills/creating-claude-md

README

creating-claude-md

An Agent Skill for generating a lean, high-signal CLAUDE.md (or AGENTS.md) for a repository from scratch.

Works with Claude Code, Codex, and any other coding agent that supports the SKILL.md format.

What it does

Bootstraps project memory for a repo by combining:

  1. An autonomous repo scan — manifests, structure, linter configs, git history, existing docs, configured MCPs.
  2. A focused 6-question interview — the judgment content only the user can supply (WHY, gotchas, out-of-scope, approval gates, testing philosophy, external docs like Confluence pages).

The output is a CLAUDE.md under 80 lines (120 hard cap) where every line earns its place. If a line wouldn't prevent a specific mistake, the skill deletes it.

When to use

  • Repo has no CLAUDE.md and you want one.
  • Existing CLAUDE.md is unsalvageable and you want a clean rewrite.
  • You're setting up a repo for an agent for the first time.

Not for auditing or incrementally improving an existing CLAUDE.md — that's a separate concern.

Install

Claude Code

Clone into the skills directory:

git clone https://github.com/sruthik27/creating-claude-md.git ~/.claude/skills/creating-claude-md

Then in any repo, ask Claude Code to "create a CLAUDE.md" or "bootstrap project memory" and the skill will trigger.

Codex / other agents

Point your agent at the SKILL.md file. The format is plain Markdown with YAML frontmatter — most agent runtimes that support skills accept it as-is.

Key design choices

  • 80-line target, 120 hard cap. Bloat causes harnesses to down-weight every instruction in the file, not just the tail. The cap is a forcing function.
  • Imperative rules, paired with positive alternatives. "Never force-push; rebase locally then push normally" beats "Never force-push" alone.
  • No content that linters already enforce. Indentation, quotes, import order, etc. go in .eslintrc / biome.json / ruff.toml, not CLAUDE.md.
  • External docs by reference, never by paste. Confluence/Notion URLs + purpose + read/update policy. CLAUDE.md is not a cache.
  • Aux files only when the root exceeds 80 lines. No speculative scaffolding.

License

MIT

Files in the repo

Repository payload•4 top-level entries
  • .gitignore
  • LICENSE
  • README.md
  • SKILL.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More skills

obra/
superpowers
obra/superpowersSkills

An agentic skills framework & software development methodology that works.

285k
1 add
Graphify-Labs/graphifySkills

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

117k
1 add
Vincentwei1021/
anything2explainer
Vincentwei1021/anything2explainerSkills

Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.

666
career-ops-hq/career-opsSkills

Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)

71k