跳到正文
cccskills
免费在 GitHub 公开

claude-md-improver

Review CLAUDE.md files, which provide project instructions to Claude Code. Receive a scored quality report covering commands, structure, and outdated guidance, then approve focused edits that keep the instructions concise and useful.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

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".

查看安装方法

适用场景

  • Auditing project instructions for Claude Code
  • Updating outdated build and test commands
  • Reviewing instructions across multiple packages
  • Adding recurring pitfalls to project guidance

包含的文件(4)

  • SKILL.md5.9 KB
  • references/quality-criteria.md2.6 KB
  • references/templates.md3.6 KB
  • references/update-guidelines.md3.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

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)

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

access

免费

Manage access to a Telegram channel integration by approving pairing codes, updating allowed users, and setting direct-message and group policies. Check pending requests and adjust reply behavior through configuration files read by the channel server.

中文简介正在准备中。当前显示英语简介。

  • Approve or deny a Telegram pairing request
  • Review and update allowed users
  • Change direct-message access policies
anthropics/claude-plugins-official4.3万2026年10月18日 更新

access

免费

Manage access to a Discord channel integration by approving pairing codes, updating allowed users, and setting direct-message and channel policies. Check pending requests and adjust reply behavior through configuration files read by the channel server.

中文简介正在准备中。当前显示英语简介。

  • Approve or deny a Discord pairing request
  • Review and update allowed users
  • Change direct-message access policies
anthropics/claude-plugins-official4.3万2026年10月18日 更新

access

免费

Manage who can contact an assistant through the iMessage channel. Update approved senders, approve pairing codes, and configure direct message and group access rules by editing the channel’s local settings.

中文简介正在准备中。当前显示英语简介。

  • Add or remove approved iMessage senders
  • Approve or reject a pending pairing code
  • Set group access and mention requirements
anthropics/claude-plugins-official4.3万2026年10月18日 更新

Design autonomous agents for Claude Code plugins, including when they should run, what they should do, and which tools they may use. Provides file templates and guidance for validating configuration and testing behavior.

中文简介正在准备中。当前显示英语简介。

  • Create a code review agent
  • Clarify when an agent should run
  • Limit the tools an agent can access
anthropics/claude-plugins-official4.3万2026年10月18日 更新

Add interactive panels to an MCP server so users can select records, view charts, or follow progress inside a conversation. The skill guides tool connections, interface implementation, sandbox restrictions, and testing in hosts that support these panels.

中文简介正在准备中。当前显示英语简介。

  • Build a searchable contact or file picker
  • Display charts and previews inside a conversation
  • Show live progress for a long-running job
anthropics/claude-plugins-official4.3万2026年10月18日 更新

Plan and build an MCP server, a connection that lets Claude use external tools. Choose hosting, tool structure, authentication, and a framework, then scaffold a server or hand off to specialized packaging and interface skills.

中文简介正在准备中。当前显示英语简介。

  • Connect a cloud API to Claude
  • Choose how to run and distribute an MCP server
  • Organize tools for an API with many actions
anthropics/claude-plugins-official4.3万2026年10月18日 更新

查看 anthropics 的全部技能

报告此技能的问题