claude-md-improver

tarafından anthropic

CLAUDE.md dosyalarını denetleyip iyileştirerek Claude Code'un proje bağlamını optimize eder. Tüm CLAUDE.md varyantlarını (proje kökü, yerel geçersiz kılmalar, pakete özgü, genel varsayılanlar) keşfeder ve her birini komutlar, mimari netliği, desenler, özlülük, güncellik ve eyleme dönüştürülebilirlik kapsayan bir kalite çerçevesine göre değerlendirir. Herhangi bir değişiklik yapmadan önce dosya bazında puanlar ve belirli iyileştirme önerileri içeren ayrıntılı bir kalite raporu çıkarır. Yalnızca kullanıcıdan sonra hedeflenmiş, minimum güncellemeler uyg

npx skills add https://github.com/anthropics/claude-plugins-official --skill claude-md-improver

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  • D (30-49): Sparse or outdated
  • F (0-29): Missing or severely outdated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.

```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 tarafından daha fazla skill

analyzing-financial-statements
anthropic
Bu beceri, yatırım analizi için finansal tablo verilerinden temel finansal oranları ve metrikleri hesaplar.
applying-brand-guidelines
anthropic
Bu beceri, oluşturulan tüm belgelere renkler, yazı tipleri, düzenler ve mesajlaşma dahil olmak üzere tutarlı kurumsal markalama ve stil uygular.
creating-financial-models
anthropic
Bu beceri, DCF analizi, duyarlılık testi, Monte Carlo simülasyonları ve yatırım için senaryo planlaması ile gelişmiş bir finansal modelleme paketi sunar…
board-minutes
anthropic
Kurul veya komite toplantı tutanaklarını ev formatınızda taslak haline getirir. Takviminizden yaklaşan kurul ve komite toplantılarını otomatik olarak algılar, gündemi sorar ve…
crm-cleanup
anthropic
HubSpot'u bayat fırsatlar, yinelenen kişiler ve eksik alanlar için tarar, ardından sahibinin onayladıklarını düzeltir. Fırsatlar, kişiler için isteğe bağlı kapsam argümanını kabul eder,…
redshift-api
anthropic
Amazon Redshift üzerinde SQL çalıştırın — ifadeler gönderin, durumu sorgulayın, sonuçlar arasında gezinin ve veritabanları/şemalar/tablolar arasında göz atın. Kullanıcı istediğinde bunu kullanın…
ticket-deflector
anthropic
Yönlendirilen bir müşteri e-postasını veya talebini okur, PayPal'dan sipariş/iade durumunu ve HubSpot'tan hesap geçmişini çeker, sahibinin üslubuna uygun bir yanıt taslağı oluşturur…
reg-feed-watcher
anthropic
Düzenleyici beslemeleri şimdi kontrol et ve son kontrolden bu yana yeni olanları, maddilik eşiğine göre filtreleyerek raporla. Kullanıcı "beslemeleri kontrol et" dediğinde kullanılır,…