Skip to main content
skill Claude Code official · Anthropic

claude-md-improver — Claude Code skill: audit CLAUDE.md

This skill audits CLAUDE.md files, produces a quality report, and suggests focused edits. Use it when project instructions need a careful review.

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin install claude-md-management@claude-plugins-official
Open on GitHub

What claude-md-improver does

claude-md-improver searches a repository for CLAUDE.md, .claude.md, and .claude.local.md files. It reviews each file for documented commands, architecture context, project-specific quirks, currentness, concision, and actionable guidance, then builds a scored report with issues and recommendations.

The skill waits for approval after the report and applies only the agreed edits. Its workflow uses Read, Glob, Grep, Bash, and Edit to inspect files, check the repository, and update CLAUDE.md. It fits monorepos and projects where instructions have drifted over time. Skip it when CLAUDE.md is maintained manually and must remain unchanged.

What it helps with

  • audit every CLAUDE.md in a repository
  • spot stale build and test commands
  • score the quality of project instructions
  • add project-specific gotchas to CLAUDE.md

Example prompts for the agent

  • Audit every CLAUDE.md in this repository and produce a quality report.
  • Find stale commands and suggest focused updates for CLAUDE.md.
  • Review CLAUDE.md, show the report, and wait for my approval before editing.

How to install claude-md-improver

1Plugin marketplace

/plugin install claude-md-management@claude-plugins-official

This installs the whole claude-md-management plugin with all its skills

2Skills CLI (Vercel)

npx skills add anthropics/claude-plugins-official --skill claude-md-improver -a claude-code

3Manually: put the files in place

~/.claude/skills/claude-md-improver/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/claude-md-improver/

From the same set37

The whole set →
code-reviewer official Anthropic Reviews code changes against CLAUDE.md project rules and flags material defects. Run it before a commit or pull request. Claude Code 31,050installs code-reviewer official Anthropic This subagent checks code changes for bugs, security issues, and project-rule violations. Use it when a review should focus on findings that matter. Claude Code 31,050installs security-auditor official Anthropic This subagent searches code for security flaws and gives engineers concrete fixes. Use it to review a project before hardening or modernization work. Claude Code 10,718installs test-engineer official Anthropic This subagent captures legacy behavior in tests and compares it with a rewritten implementation. Use it before changing existing modules. Claude Code 9,715installs claude-automation-recommender official Anthropic Analyzes a codebase and recommends Claude Code hooks, subagents, skills, plugins, and MCP servers. Useful when setting up a project or refining an existing workflow. Claude Code 9,057installs playground official Anthropic Builds interactive HTML playgrounds with controls, a live preview, and a generated prompt. Use it when a topic is easier to explore visually than through plain text. Claude Code 7,967installs agent-development official Anthropic This skill guides you through creating agents for Claude Code plugins, from trigger conditions to system prompts and tool access. Use it when adding a subagent to a plugin. Claude Code 7,353installs skill-development official Anthropic Guides the design of skills for Claude Code plugins, from gathering use cases to organizing files and metadata. Useful when building a new skill or revising an existing one. Claude Code 7,219installs

Similar

nature-polishing Yuan1z0825 A skill that polishes, translates and tightens existing academic prose. Facts, terminology and evidence boundaries stay intact. Claude Code CX Codex Cursor +1 17,400installs baoyu-article-illustrator JimLiu Inspects article structure, picks key spots for graphics, and generates consistent raster illustrations. Use it when an article needs visuals planned directly inside your coding agent. Claude Code CX Codex Cursor +1 31,900installs baoyu-slide-deck JimLiu Turns content into slide images: an outline with style rules first, then individual PNGs. Built for reading and sharing, not live presenting. Claude Code CX Codex Cursor +1 31,200installs baoyu-comic JimLiu A skill that builds original knowledge comics with panel layouts and batch image generation. Useful when you need a comic about a topic, a biography or a tutorial. Claude Code CX Codex Cursor +1 29,900installs nature-paper2ppt Yuan1z0825 Builds a Chinese academic .pptx from a scientific paper or reading notes, with figures from the source and speaker notes. Claude Code CX Codex Cursor +1 16,000installs context7-mcp upstash This skill fetches current library and framework documentation before the agent answers. Use it for setup questions, API references, and code generation. Claude Code CX Codex Cursor +1 6,200installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs

Questions about claude-md-improver

How do I install claude-md-improver in Claude Code?

Run /plugin install claude-md-management@claude-plugins-official, or use npx skills add anthropics/claude-plugins-official --skill claude-md-improver -a claude-code.

What does claude-md-improver do?

It finds CLAUDE.md files, checks them against quality criteria, and creates a scored report. After approval, it applies targeted updates.

Does claude-md-improver edit files without approval?

No. It presents the quality report first, asks for confirmation, and edits CLAUDE.md only after approval.

Source text

SKILL.md · Apache-2.0
---
name: claude-md-improver
description: 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".
tools: Read, Glob, Grep, Bash, Edit
---

# 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

For each CLAUDE.md file, evaluate against quality criteria. See [references/quality-criteria.md](references/quality-criteria.md) for detailed rubrics.

**Quick Assessment Checklist:**

| Criterion | Weight | Check |
|-----------|--------|-------|
| Commands/workflows documented | High | Are build/test/deploy commands present? |
| Architecture clarity | High | Can Claude understand the codebase structure? |
| Non-obvious patterns | Medium | Are gotchas and quirks documented? |
| Conciseness | Medium | No verbose explanations or obvious info? |
| Currency | High | Does it reflect current codebase state? |
| Actionability | High | Are instructions executable, not vague? |

**Quality Scores:**
- **A (90-100)**: Comprehensive, current, actionable
- **B (70-89)**: Good coverage, minor gaps
- **C (50-69)**: Basic info, missing key sections
- **D (30-49)**: Sparse or outdated
- **F (0-29)**: Missing or severely outdated

### Phase 3: Quality Report Output

**ALWAYS output the quality report BEFORE making any updates.**

Format:

```
## CLAUDE.md Quality Report

### Summary
- Files found: X
- Average score: X/100
- Files needing update: X

### File-by-File Assessment

#### 1. ./CLAUDE.md (Project Root)
**Score: XX/100 (Grade: X)**

| Criterion | Score | Notes |
|-----------|-------|-------|
| Commands/workflows | X/20 | ... |
| Architecture clarity | X/20 | ... |
| Non-obvious patterns | X/15 | ... |
| Conciseness | X/15 | ... |
| Currency | X/15 | ... |
| Actionability | X/15 | ... |

**Issues:**
- [List specific problems]

**Recommended additions:**
- [List what should be added]

#### 2. ./packages/api/CLAUDE.md (Package-specific)
...
```

### Phase 4: Targeted Updates

After outputting the quality report, ask user for confirmation before updating.

**Update Guidelines (Critical):**

1. **Propose targeted additions only** - Focus on genuinely useful info:
   - Commands or workflows discovered during analysis
   - Gotchas or non-obvious patterns found in code
   - Package relationships that weren't clear
   - Testing approaches that work
   - Configuration quirks

2. **Keep it minimal** - Avoid:
   - Restating what's obvious from the code
   - Generic best practices already covered
   - One-off fixes unlikely to recur
   - Verbose explanations when a one-liner suffices

3. **Show diffs** - For each change, show:
   - Which CLAUDE.md file to update
   - The specific addition (as a diff or quoted block)
   - Brief explanation of why this helps future sessions

**Diff Format:**

```markdown
### Update: ./CLAUDE.md

**Why:** Build command was missing, causing confusion about how to run the project.

```diff
+ ## Quick Start
+
+ ```bash
+ npm install
+ npm run dev  # Start development server on port 3000
+ ```
```
```

### Phase 5: Apply Updates

After user approval, apply changes using the Edit tool. Preserve existing content structure.

## Templates

See [references/templates.md](references/templates.md) for CLAUDE.md templates by project type.

## Common Issues to Flag

1. **Stale commands**: Build commands that no longer work
2. **Missing dependencies**: Required tools not mentioned
3. **Outdated architecture**: File structure that's changed
4. **Missing environment setup**: Required env vars or config
5. **Broken test commands**: Test scripts that have changed
6. **Undocumented gotchas**: Non-obvious patterns not captured

## User Tips to Share

When presenting recommendations, remind users:

- **`#` key shortcut**: During a Claude session, press `#` to have Claude auto-incorporate learnings into CLAUDE.md
- **Keep it concise**: CLAUDE.md should be human-readable; dense is better than verbose
- **Actionable commands**: All documented commands should be copy-paste ready
- **Use `.claude.local.md`**: For personal preferences not shared with team (add to `.gitignore`)
- **Global defaults**: Put user-wide preferences in `~/.claude/CLAUDE.md`

## What Makes a Great CLAUDE.md

**Key principles:**
- Concise and human-readable
- Actionable commands that can be copy-pasted
- Project-specific patterns, not generic advice
- Non-obvious gotchas and warnings

**Recommended sections** (use only what's relevant):
- Commands (build, test, dev, lint)
- Architecture (directory structure)
- Key Files (entry points, config)
- Code Style (project conventions)
- Environment (required vars, setup)
- Testing (commands, patterns)
- Gotchas (quirks, common mistakes)
- Workflow (when to do what)

© Anthropic · Apache-2.0 · anthropics/claude-plugins-official

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor