[skills](https://carteblanche.com/index.md) / [code](https://carteblanche.com/index.md?category=code)

# claude-md-improver

what it does

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".

by anthropics · version 1 · license Apache-2.0

We imported this skill from its author’s repository. Is this yours? [Claim this listing](https://carteblanche.com/claim/claude-md-improver)

Verified · Before and after: 2 models · 1 try per case · [View source](https://github.com/anthropics/claude-plugins-official/tree/0412be76f50ab4f4f8abff3753efa9269fbbca5b/plugins/claude-md-management/skills/claude-md-improver) · [Install from your agent](https://carteblanche.com/connect.md) · [Download .zip](https://carteblanche.com/skills/claude-md-improver/download)

## Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the skill and once without. Read both and judge for yourself.

[Compare the answers](https://carteblanche.com/skills/claude-md-improver/compare)

## The models

2 models

Claude Sonnet 5.5

made by Anthropic

claude-sonnet-5-5 · revision not reported by the provider

1 try per case · tested 7 Nov 2026

GPT-6.1 Sol

made by OpenAI

gpt-6.1-sol · revision not reported by the provider

1 try per case · tested 7 Nov 2026

## The tasks

written by Carte Blanche

**example-1**

“Can you audit all the CLAUDE.md files in my monorepo? We've got one at the root plus a few in packages/api and packages/web. I think they're bloated and out of date, since we switched from npm to pnpm last month. Give me a quality report first, then make targeted fixes.”

**example-2**

“I want to do some CLAUDE.md maintenance on this repo. The current file is just a long dump of style rules and has no build or test commands, and Claude keeps guessing wrong how to run things. Please check it, tell me what's weak, and improve it. The stack is Django with pytest, and we run migrations with a make target.”

## Install

Download the .zip and unzip it. Put its files, in a folder named `claude-md-improver`, here:

Claude Code · `~/.claude/skills/` · Every project. For one project only, use .claude/skills/ inside it.

Codex · `~/.agents/skills/` · Every project. For one repository only, use .agents/skills/ inside it.

Cursor · `~/.cursor/skills/` · Cursor also reads the Claude Code and Codex folders above.

Then start a new session and ask for what the skill does. Other agents that read SKILL.md have their own skills folder; check their docs.

Or [install from your agent](https://carteblanche.com/connect.md): ask it to install `claude-md-improver` from Carte Blanche.

## Badge for your README

Carte Blanche: Verified

Paste this into the skill’s README. It links to this page, and shows how the listing stands whenever it’s loaded.

```
[![Carte Blanche](https://carteblanche.com/badge/claude-md-improver.svg)](https://carteblanche.com/skills/claude-md-improver)
```

## About this test

- **tested**: 7 Nov 2026
- **version tested**: v1
- **cases**: 2
- **tries per case**: 1 try per case
- **run without the skill**: yes
- **cases written by**: Carte Blanche
- **size**: 15293 characters

What this shows, and what it doesn’t

How 2 models answered these 2 requests, with and without the skill. It says nothing about other models, and it doesn’t limit what your own agent can do.

[How we test](https://carteblanche.com/how-it-works.md)