Claude Md Writer

What it does

When your agent uses it

• Clean up the CLAUDE.md (or AGENTS.md) file that tells a coding agent how to work in a repo — commands
• Onboarding an agent to a codebase
• The agent keeps making the same repo-specific mistake
• The user asks for project instructions

Example prompts

• “/claude-md-writer”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Read the README, package.json scripts, CI config, and any existing contributor docs.
2. 2Skim the top-level directories and the two or three files that everything imports.
3. 3Check git log for what changes most — that is where the conventions matter.
4. 4Ask the user for the traps. This is the section they cannot skip and you cannot infer: "What has bitten you or a teammate in this repo?"
5. 5Write it. Then cut it by a third.

What it can do on your machine

Read from SKILL.md and the folder at commit fc5b785. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npm
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npm and git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Claude Md Writer loads about 1k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 507 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~92

When it runs · the whole SKILL.md, loaded when a task matches

~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:22

  npm run dev          # port 3000, needs .env.local

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OneWave-AI/claude-skills at commit fc5b785, republished under its MIT licence (© OneWave-AI). 507 words, ~1,002 tokens.

name

claude-md-writer

description

Use to create or clean up the CLAUDE.md (or AGENTS.md) file that tells a coding agent how to work in a repo — commands, conventions, architecture, and the traps. Trigger when onboarding an agent to a codebase, when the agent keeps making the same repo-specific mistake, or when the user asks for project instructions, agent rules, or a context file.

tools

Read, Write, Edit, Glob, Grep, Bash

npm run dev          # port 3000, needs .env.local
npm test -- <file>   # single file; the bare `npm test` runs the whole suite (6 min)

# <Project>

<One sentence: what this is and who uses it.>

## Commands
<the handful that matter, with the gotcha flags>

## Architecture
<five lines, entry point first>

## Conventions
- <repo-specific rule> — see `path/to/exemplar.ts`

## Traps
- <the thing that wastes an hour>

## Rules
- Never <x>.
- Always <y>.

© OneWave-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in claude-md-writer of OneWave-AI/claude-skills.

Open the folder on GitHubat commit fc5b785