SC

sruthik27/creating-claude-md

Developer tools
63 stars 품질 85 트렌드 85

Claude Code / Codex skill: generate a lean, high-signal CLAUDE.md from scratch via repo scan + focused user interview.

개요

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. Bootstraps project memory for a repo by combining: 1. — manifests, structure, linter configs, git history, existing docs, configured MCPs. 2. — 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. - 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. auditing or incrementally improving an existing CLAUDE.md — that's a separate concern. Then in any repo, ask Claude Code to "create a CLAUDE.

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

View this README on GitHub

추천 도구

다른 키워드를 입력하거나 필터를 제거해 보세요.

설치

npx skillfish add sruthik27/creating-claude-md