🇺🇸English

CLAUDE.md Management

Provides comprehensive CLAUDE.md file management capabilities including auditing, quality assessment, and targeted improvements. This skill ensures Claude Code has optimal project context by maintaining high-quality documentation files.

Overview

CLAUDE.md files are the primary mechanism for providing project-specific context to Claude Code sessions. This skill manages the complete lifecycle of CLAUDE.md files: discovery, quality assessment, reporting, and improvement. It follows a 5-phase workflow that ensures documentation is current, actionable, and concise.

The skill evaluates CLAUDE.md files against standardized quality criteria across 6 dimensions: Commands/Workflows, Architecture Clarity, Non-Obvious Patterns, Conciseness, Currency, and Actionability. Each file receives a score (0-100) and letter grade (A-F) with specific improvement recommendations.

When to Use

Use this skill when:

• User explicitly asks to "check", "audit", "update", "improve", "fix", or "maintain" CLAUDE.md
• User mentions "CLAUDE.md quality", "documentation review", or "project memory optimization"
• CLAUDE.md needs to be created from scratch for a new project
• User asks about improving Claude's understanding of the codebase
• Documentation has become stale or outdated
• Starting work on a new codebase and need to understand existing documentation
• User presses # during a session to incorporate learnings into CLAUDE.md

Trigger phrases: "audit CLAUDE.md", "check documentation quality", "improve project context", "review CLAUDE.md", "validate documentation"

Instructions

Phase 1: Discovery

Find all CLAUDE.md files in the repository:

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

File Types & Locations:

Phase 2: Quality Assessment

For each CLAUDE.md file, read references/quality-criteria.md and evaluate against these criteria:

Quality Scores: A (90-100), B (70-89), C (50-69), D (30-49), F (0-29)

Phase 3: Quality Report Output

CRITICAL: 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]

Phase 4: Targeted Updates

After report output, ask user for confirmation before updating.

Readreferences/update-guidelines.md for detailed update principles.

Key principles:

1. Propose targeted additions only - commands, gotchas, patterns, configs
2. Keep it minimal - avoid obvious info, generic advice, one-off fixes
3. Show diffs - file, change (diff format), explanation

Diff format:

### Update: ./CLAUDE.md
**Why:** [Brief explanation of why this helps]

```diff
+ ## Quick Start
+
+ ```bash
+ npm install
+ npm run dev
+ ```



### Phase 5: Apply Updates

After user approval, use Edit tool to apply changes. Preserve existing content structure.

## Examples

### Example 1: Quality Assessment

**User request:** "Check if my CLAUDE.md is good"

**Response:**
~~~markdown
## CLAUDE.md Quality Report

### Summary
- Files found: 1
- Average score: 65/100
- Files needing update: 1

### File-by-File Assessment

#### 1. ./CLAUDE.md
**Score: 65/100 (Grade: C)**

| Criterion | Score | Notes |
|-----------|-------|-------|
| Commands/workflows | 10/20 | Only npm install documented |
| Architecture clarity | 15/20 | Basic tree, missing module relationships |
| Non-obvious patterns | 5/15 | No gotchas documented |
| Conciseness | 15/15 | Concise and dense |
| Currency | 10/15 | Some outdated paths |
| Actionability | 10/15 | Some vague instructions |

**Issues:**
- Missing test command
- Missing build command
- No documentation of auth flow complexity
- References to old src/structure

**Recommended additions:**
- Add Commands section with test/build
- Document auth module gotcha
- Update architecture paths

Example 2: Creating from Scratch

User request: "Create a CLAUDE.md for this React project"

Response:

I'll create a CLAUDE.md for your React project. Let me first analyze the codebase structure.

[Scans package.json, src/, and key config files]

## CLAUDE.md Quality Report

### Summary
- Files found: 0
- Creating new CLAUDE.md at project root

### Proposed CLAUDE.md Content:

# Project Name

## Commands

| Command | Description |
|---------|-------------|
| `npm install` | Install dependencies |
| `npm run dev` | Start dev server (Vite on port 5173) |
| `npm run build` | Production build |
| `npm run test` | Run Vitest tests |
| `npm run lint` | ESLint check |

## Architecture

src/ ├── components/ # Reusable UI components ├── pages/ # Route pages ├── hooks/ # Custom React hooks ├── lib/ # Utilities and API clients └── main.tsx # Entry point

## Gotchas

- Vite requires files in `public/` for static assets
- State updates in `useEffect` need proper dependency arrays

Shall I create this file?

### Example 3: Update Proposal

**User request:** "Update my CLAUDE.md with what you learned"

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

**Why:** Discovered that tests require database setup which wasn't documented.

```diff
## Testing

+ **Prerequisites:** Start test database first with `docker-compose up -d test-db`
+ `npm run test` - Run all tests
+ `npm run test:unit` - Unit tests only (no DB required)

Also found issue with API_BASE_URL:

## Environment

- `API_BASE_URL` - API endpoint (default: localhost:3000)
+ `API_BASE_URL` - API endpoint (required for production, defaults to http://localhost:3000 in dev)

Apply these changes?

## Best Practices

1. **Always read references before acting**: Quality criteria, templates, and update guidelines contain essential details
2. **Report before editing**: Never modify CLAUDE.md without first presenting a quality report
3. **Preserve existing structure**: When updating, maintain the existing organization and style
4. **Be project-specific**: Only add information specific to this codebase, not generic advice
5. **Verify commands work**: Before suggesting commands, mentally or actually verify they execute correctly
6. **Use progressive disclosure**: Keep SKILL.md lean, reference detailed rubrics in separate files
7. **Score consistently**: Apply the same scoring standards across all files for fair comparison

## Constraints and Warnings

1. **Never modify without approval**: Always get user confirmation before editing CLAUDE.md files
2. **Don't remove content without asking**: If suggesting deletions, explicitly mark them and get approval
3. **Respect `.claude.local.md`**: These are personal settings; never suggest modifying them in shared docs
4. **Avoid generic advice**: Do not add "write good code" type content - focus on project-specific patterns
5. **Keep diffs concise**: Show only the actual changes, not entire file contents
6. **Verify file paths**: Ensure all referenced files exist before documenting them
7. **Score objectively**: Use the rubric consistently; don't inflate scores for incomplete documentation

Weekly Installs

301

Repository

giuseppe-trisci…oper-kit

GitHub Stars

173

First Seen

Feb 14, 2026

Security Audits

Gen Agent Trust HubPassSocketPassSnykPass

Installed on

opencode263

codex263

gemini-cli261

claude-code257

github-copilot254

cursor248