Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
anthropics avatar

Claude Md Improver

  • 8.4k installs
  • 32.9k repo stars
  • Updated July 31, 2026
  • anthropics/claude-plugins-official

Audit, score, and update CLAUDE.md files to optimize project context for Claude Code sessions

About

This skill systematically discovers, evaluates, and updates CLAUDE.md files throughout a repository. It scans for all CLAUDE.md variants (root, local, package-specific), scores each file against quality criteria (commands, architecture clarity, currency, actionability), generates detailed quality reports with grades and specific gaps, and proposes targeted updates after user approval. Developers invoke it when maintaining project memory files, onboarding new team members to Claude-assisted workflows, or ensuring build/test commands stay current. The skill handles monorepo structures, distinguishes between shared project files and local overrides, and teaches users the `#` shortcut for auto-incorporating session learnings into CLAUDE.md.

  • Discovers all CLAUDE.md variants: project root, .claude.local.md, package-specific, and global configs
  • Scores files A-F across six criteria: commands, architecture, patterns, conciseness, currency, actionability
  • Outputs quality reports before any modifications, showing specific gaps and recommended additions
  • Proposes minimal targeted updates grounded in discovered commands, gotchas, and non-obvious patterns
  • Handles monorepo setups and teaches users Claude's `#` shortcut for auto-documenting session learnings

Claude Md Improver by the numbers

  • 8,386 all-time installs (skills.sh)
  • +605 installs in the week ending Jul 29, 2026 (Skillselion tracking)
  • Ranked #56 of 1,881 Documentation skills by installs in the Skillselion catalog
  • Security screen: MEDIUM risk (skills.sh audit)
  • Data as of Jul 31, 2026 (Skillselion catalog sync)
At a glance

claude-md-improver capabilities & compatibility

included-with-claude

Capabilities
discovers claude md files · evaluates documentation quality · scores against criteria · generates quality reports · proposes targeted updates · applies approved changes · handles monorepo structures · distinguishes file types
Works with
github · gitlab · bitbucket
Use cases
documentation · code review · project management · refactoring
Platforms
macOS · Windows · Linux · WSL
Runs
Runs locally
Pricing
Free
npx skills add https://github.com/anthropics/claude-plugins-official --skill claude-md-improver

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs8.4k
repo stars32.9k
Security audit3 / 3 scanners passed
Last updatedJuly 31, 2026
Repositoryanthropics/claude-plugins-official

What it does

Audit and improve CLAUDE.md files across codebases to ensure Claude has optimal project context and current commands.

Who is it for?

Maintaining project memory files in active codebases, onboarding teams to Claude workflows, ensuring build/test documentation stays current

Skip if: Creating initial CLAUDE.md from scratch (use templates), general code documentation (use standard docs), API reference generation

When should I use this skill?

User asks to check/audit/update/improve/fix CLAUDE.md, mentions CLAUDE.md maintenance, or wants project memory optimization

What you get

Current, concise CLAUDE.md files with actionable commands and project-specific gotchas that optimize Claude's project understanding

  • Quality report with file-by-file scores and grades
  • Specific issue list per CLAUDE.md file
  • Targeted update proposals with diffs

By the numbers

  • Evaluates 6 quality criteria with weighted scoring out of 100 points
  • Discovers up to 50 CLAUDE.md files per scan (head -50 in find command)
  • Proposes 3-5 file location types: project root, local overrides, global defaults, package-specific, subdirectory

Files

SKILL.mdMarkdownGitHub ↗

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:

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 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:

### Update: ./CLAUDE.md

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

+ ## 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 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)

Related skills

Forks & variants (2)

Claude Md Improver has 2 known copies in the catalog totaling 157 installs. They canonicalize to this original listing.

How it compares

Pick claude-md-improver over manual edits when multiple CLAUDE.md files need template-based quality scoring across a monorepo.

FAQ

What's the difference between CLAUDE.md and .claude.local.md?

CLAUDE.md is the shared project file checked into git. .claude.local.md contains personal preferences, is gitignored, and overrides project settings locally.

How does the quality scoring work?

Files are scored 0-100 across six weighted criteria: commands/workflows (20 pts), architecture clarity (20 pts), non-obvious patterns (15 pts), conciseness (15 pts), currency (15 pts), actionability (15 pts). A=90-100, B=70-89, C=50-69, D=30-49, F=0-29.

What updates does the skill propose?

Only targeted additions discovered during analysis: missing build/test commands, undocumented gotchas, architecture gaps, or configuration quirks. It avoids generic advice or restating obvious code patterns.

Is Claude Md Improver safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Documentationdocsintegrationsdevops

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.