Claude Md Improver

by anthropicsb78ac49cdc6bNo license37K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

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".

FeaturedInstructions onlyAI & Agents
AI-generated overview

Audits CLAUDE.md files in a repository, scores their quality, and applies approved targeted improvements.

What it does
The skill discovers CLAUDE.md files across a repository, including project root, local override, global, package-specific and nested locations. It evaluates each file against weighted criteria such as documented commands, architecture clarity, non-obvious patterns, conciseness, currency and actionability, and assigns a score and letter grade. It then outputs a file-by-file quality report with issues and recommended additions, and after user approval applies targeted edits, showing diffs and explaining each change.
When to use it
Use it when asked to check, audit, update, improve or fix CLAUDE.md files, or when the user mentions CLAUDE.md maintenance or project memory optimization. It fits repositories where Claude Code project context may be stale, incomplete or missing key commands and gotchas.
Requirements
Runs as instructions only, with no bundled scripts. It relies on the agent's Read, Glob, Grep, Bash and Edit tools, and it writes to CLAUDE.md files after user approval.

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:

TypeLocationPurpose
Project root./CLAUDE.mdPrimary project context (checked into git, shared with team)
Local overrides./.claude.local.mdPersonal/local settings (gitignored, not shared)
Global defaults~/.claude/CLAUDE.mdUser-wide defaults across all projects
Package-specific./packages/*/CLAUDE.mdModule-level context in monorepos
SubdirectoryAny nested locationFeature/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 [blocked] for detailed rubrics.

Quick Assessment Checklist:

CriterionWeightCheck
Commands/workflows documentedHighAre build/test/deploy commands present?
Architecture clarityHighCan Claude understand the codebase structure?
Non-obvious patternsMediumAre gotchas and quirks documented?
ConcisenessMediumNo verbose explanations or obvious info?
CurrencyHighDoes it reflect current codebase state?
ActionabilityHighAre 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 work2. **Missing dependencies**: Required tools not mentioned3. **Outdated architecture**: File structure that's changed4. **Missing environment setup**: Required env vars or config5. **Broken test commands**: Test scripts that have changed6. **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)

Source and attribution

Source:anthropics/claude-plugins-officialinplugins/claude-md-management/skills/claude-md-improverat commitb78ac49

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

More from anthropics/claude-plugins-official

Skill Development

anthropics

Featured

Guides creation of Claude Code plugin skills, covering structure, descriptions, progressive disclosure and validation.

AI & Agents37Kupdated today

Plugin Structure

anthropics

Featured

Guides the structure, manifest, and component layout of Claude Code plugins.

AI & Agents37Kupdated today

Project Artifact

anthropics

Featured

Generate and publish a project status artifact — an opinionated, tabbed status page for a project too big for one update (overview & success criteria, the workstream sequence, next steps, plus background, plan, risks & open questions, and decisions/FAQ when they earn a tab) — published with the built-in Artifact tool to a default-private claude.ai page the user can share with teammates. Use when a piece of work spans several workstreams and you want a shareable overview kept current. Each artifact is backed by a small per-project config in the plugin data dir, so refreshing it re-gathers live state, redeploys the same URL, and reports only the delta. For software projects whose workstreams are PRs, also read swe.md (the X.Y PR-numbering convention; pulling PR state with gh/git; a per-PR detail block). Needs the built-in Artifact tool (claude.ai login). Not for single-PR changes or public docs.

Awaiting classification37Kupdated today

Command Development

anthropics

Featured

Guides creation of Claude Code slash commands, covering structure, YAML frontmatter, arguments and plugin features.

AI & Agents37Kupdated today

Playground

anthropics

Featured

Builds self-contained interactive HTML playgrounds with controls, live preview, and copyable prompt output.

Design & Creative37Kupdated today

M5 Onboard

anthropics

Featured

Provisions M5Stack ESP32 boards by detecting them on USB, flashing UIFlow 2.0 firmware, and installing a MicroPython app bundle.

DevOps & Cloud37Kupdated today