claude-md-improver SKILL.md skillA

The newest version of a file that held these bytes earlier

claude-md-improver in skateddu/claude-code-python-setup is at git:20261015.42513a8 (Oct 15, 2026), graded A.

mdr add skateddu/claude-code-python-setup/claude-md-improver@git:20261015.42513a8

This copy is 2 versions behind it. See what changed · install this older copy instead

This line moves to the next version by itself within about an hour of that file saving one. A copy already installed stays as it is until you update it.

claude-md-improver from socialgouv/iterion is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
socialgouv/iterion
Path
pkg/claw/internal/tools/bundled_skills/claude-md-management/skills/claude-md-improver/SKILL.md
Versions recorded
1
Latest version
git:20261113.77ee4ea, committed Nov 13, 2026
Size
6,028 bytes
Repository stars
19
License
MIT

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".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# CLAUDE.md Improver

Audit, evaluate, and improve CLAUDE.md files across a codebase to ensure Claude Code has optimal project context.

**This skill can write to CLAUDE.md files.** After presenting a quality report and getting user approval, it updates CLAUDE.md files with targeted improvements.

## Workflow

### Phase 1: Discovery

Find all CLAUDE.md files in the repository:

```bash
find . -name "CLAUDE.md" -o -name ".claude.md" -o -name ".claude.local.md" 2>/dev/null | head -50
```

**File Types & Locations:**

| Type | Location | Purpose |
|------|----------|---------|
| Project root | `./CLAUDE.md` | Primary project context (checked into git, shared with team) |
| Local overrides | `./.claude.local.md` | Personal/local settings (gitignored, not shared) |
| Global defaults | `~/.claude/CLAUDE.md` | User-wide defaults across all projects |
| Package-specific | `./packages/*/CLAUDE.md` | Module-level context in monorepos |
| Subdirectory | Any nested location | Feature/domain-specific context |

**Note:** Claude auto-discovers CLAUDE.md files in parent directories, making monorepo setups work automatically.

### Phase 2: Quality Assessment
…

Read the whole file at its exact version.

How to install

This older copy, pinned
mdr add socialgouv/iterion/claude-md-improver@git:20261113.77ee4ea

Pins git:20261113.77ee4ea in mdr.lock, 2 versions behind the newest at the top of this page.

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_glsv3aoffl6dugc3/b06c7420be08ca1c7f6d75f7f4709fdb787624a2d363e2f8052216d8c780f85b.json

Then /plugin install mdr-claude-md-improver@markdownregistry-glsv3aoffl6dugc3 in Claude Code. It installs git:20261113.77ee4ea, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add socialgouv/iterion/claude-md-improver@sha256:b06c7420be08ca1c

The older copy line above pins the label git:20261113.77ee4ea, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_glsv3aoffl6dugc3.svg)](https://markdownregistry.com/a/art_glsv3aoffl6dugc3)

3 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: get me the newest skateddu/claude-code-python-setup/claude-md-improver, and what changed since b06c742? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of claude-md-improver from somewhere else? Ask it: where did my claude-md-improver come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Nov 13, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261113.77ee4ea latest2026-11-13 77ee4ea 6,028 BA view

Copies

The newest version, then this copy

Newest: git:20261015.42513a8 of claude-md-improver in skateddu/claude-code-python-setup (.claude/skills/claude-md-improver/SKILL.md), graded A.

This copy: byte for byte that file's version git:20260320.cd1dca0, which it committed on Mar 20, 2026, before this repository did; graded A, 2 versions behind.

See what changed since these bytes · ask your agent

Matched on the exact bytes and the commit dates, nothing else. It does not say who wrote the file or where this repository got it.

Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6028 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

socialgouv/iterion · 19 stars · license MIT · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_glsv3aoffl6dugc3
GET https://markdownregistry.com/api/v1/resolve?ref=socialgouv/iterion/claude-md-improver
GET https://markdownregistry.com/api/v1/blob/b06c7420be08ca1c7f6d75f7f4709fdb787624a2d363e2f8052216d8c780f85b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from socialgouv/iterion

AGENTS.md AGENTS.md file
socialgouv/iterion · AGENTS.md
git:20261115.3d04064 · audit A · 19 stars
CLAUDE.md CLAUDE.md file
socialgouv/iterion · CLAUDE.md
git:20261115.3d04064 · audit A · 19 stars
iterion-dsl SKILL.md skill
socialgouv/iterion · SKILL.md · Author, review, or debug Iterion .bot workflows and .botz bundles using the current indentation-sensitive DSL. Use for…
git:20261116.dc5b6c3 · audit A · 19 stars
claude-automation-recommender SKILL.md skill
socialgouv/iterion · pkg/claw/internal/tools/bundled_skills/claude-code-setup/skills/claude-automation-recommender/SKILL.md · Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when…
git:20261113.77ee4ea · audit A · 19 stars
frontend-design SKILL.md skill
socialgouv/iterion · pkg/claw/internal/tools/bundled_skills/frontend-design/skills/frontend-design/SKILL.md · Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to…
git:20261113.77ee4ea · audit A · 19 stars
writing-hookify-rules SKILL.md skill
socialgouv/iterion · pkg/claw/internal/tools/bundled_skills/hookify/skills/writing-rules/SKILL.md · This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add…
v0.1.0 · audit A · 19 stars
math-olympiad SKILL.md skill
socialgouv/iterion · pkg/claw/internal/tools/bundled_skills/math-olympiad/skills/math-olympiad/SKILL.md
v0.1.0 · audit B · 19 stars
build-mcp-app SKILL.md skill
socialgouv/iterion · pkg/claw/internal/tools/bundled_skills/mcp-server-dev/skills/build-mcp-app/SKILL.md · This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP…
v0.1.0 · audit B · 19 stars
build-mcp-server SKILL.md skill
socialgouv/iterion · pkg/claw/internal/tools/bundled_skills/mcp-server-dev/skills/build-mcp-server/SKILL.md · This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration"…
v0.1.0 · audit A · 19 stars
build-mcpb SKILL.md skill
socialgouv/iterion · pkg/claw/internal/tools/bundled_skills/mcp-server-dev/skills/build-mcpb/SKILL.md · This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a…
v0.1.0 · audit A · 19 stars
playground SKILL.md skill
socialgouv/iterion · pkg/claw/internal/tools/bundled_skills/playground/skills/playground/SKILL.md · Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually…
git:20261113.77ee4ea · audit A · 19 stars
agent-development SKILL.md skill
socialgouv/iterion · pkg/claw/internal/tools/bundled_skills/plugin-dev/skills/agent-development/SKILL.md · This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent…
v0.1.0 · audit A · 19 stars

Every file in socialgouv/iterion

Other files named claude-md-improver

claude-md-improver SKILL.md skill
anthropics/claude-plugins-official · plugins/claude-md-management/skills/claude-md-improver/SKILL.md · Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix…
git:20260116.a86e346 · audit A · 47,468 stars
claude-md-improver SKILL.md skill
sandbaseai/sandbase-skills · marketing/claude-md-improver/SKILL.md · Plan, implement, or review claude.md improver work in an existing codebase with compatibility, security, and…
git:20260908.a887321 · audit A · 212 stars
claude-md-improver SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_claude-md-management/for-forgecat/skills/claude-md-improver/SKILL.md · Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix…
git:20260610.c645100 · audit A · 93 stars
claude-md-improver SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_claude-md-management/for-codex/.agents/skills/claude-md-improver/SKILL.md · Audit and improve CLAUDE.md files in repositories. Use when user
git:20260610.c645100 · audit A · 93 stars
claude-md-improver SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_claude-md-management/for-cursor/.cursor/skills/claude-md-improver/SKILL.md · Audit and improve CLAUDE.md files in repositories. Use when user
git:20260610.c645100 · audit A · 93 stars
claude-md-improver SKILL.md skill
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_claude-md-management/for-claude/.claude/skills/claude-md-improver/SKILL.md · Audit and improve CLAUDE.md files in repositories. Use when user
git:20260610.c645100 · audit A · 93 stars
claude-md-improver SKILL.md skill
skateddu/claude-code-python-setup · .claude/skills/claude-md-improver/SKILL.md · Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix…
git:20261015.42513a8 · audit A · 29 stars

Browse by kind, by grade A, or by owner.