{"id":41691141,"url":"https://github.com/xiaobei930/claude-code-best-practices","last_synced_at":"2026-02-08T19:04:47.976Z","repository":{"id":334057007,"uuid":"1139859857","full_name":"xiaobei930/claude-code-best-practices","owner":"xiaobei930","description":"🎭 Transform Claude into a dev team: PM → Lead → Dev → QA workflow. 35 commands, 17 skills, safety hooks. | 让 Claude 变成开发团队","archived":false,"fork":false,"pushed_at":"2026-01-29T11:01:48.000Z","size":7046,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-01-30T01:08:40.530Z","etag":null,"topics":["ai-agent","ai-coding","anthropic","best-practices","claude","claude-code","code-assistant","cursor-alternative","developer-tools","productivity","prompt-engineering","python","template","vibe-coding","vibe-coding-assistant","workflow-automation"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/xiaobei930.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-22T14:10:15.000Z","updated_at":"2026-01-29T11:01:51.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/xiaobei930/claude-code-best-practices","commit_stats":null,"previous_names":["xiaobei930/claude-code-best-practices"],"tags_count":15,"template":true,"template_full_name":null,"purl":"pkg:github/xiaobei930/claude-code-best-practices","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaobei930%2Fclaude-code-best-practices","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaobei930%2Fclaude-code-best-practices/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaobei930%2Fclaude-code-best-practices/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaobei930%2Fclaude-code-best-practices/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xiaobei930","download_url":"https://codeload.github.com/xiaobei930/claude-code-best-practices/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiaobei930%2Fclaude-code-best-practices/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29006081,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-02T04:25:24.522Z","status":"ssl_error","status_checked_at":"2026-02-02T04:24:51.069Z","response_time":58,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agent","ai-coding","anthropic","best-practices","claude","claude-code","code-assistant","cursor-alternative","developer-tools","productivity","prompt-engineering","python","template","vibe-coding","vibe-coding-assistant","workflow-automation"],"created_at":"2026-01-24T20:16:13.075Z","updated_at":"2026-02-02T05:06:27.304Z","avatar_url":"https://github.com/xiaobei930.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CC-Best\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eRole-Driven Development Workflow for Claude Code\u003c/strong\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://opensource.org/licenses/MIT\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT-yellow.svg\" alt=\"License: MIT\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/xiaobei930/claude-code-best-practices/releases\"\u003e\u003cimg src=\"https://img.shields.io/github/v/release/xiaobei930/claude-code-best-practices?include_prereleases\" alt=\"Release\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/xiaobei930/claude-code-best-practices/actions/workflows/validate-template.yml\"\u003e\u003cimg src=\"https://github.com/xiaobei930/claude-code-best-practices/actions/workflows/validate-template.yml/badge.svg\" alt=\"Validate Plugin\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/xiaobei930/claude-code-best-practices/stargazers\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/xiaobei930/claude-code-best-practices?style=social\" alt=\"GitHub stars\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eEnglish\u003c/strong\u003e | \u003ca href=\"README.zh-CN.md\"\u003e中文\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n\u003e **Transform Claude into a complete development team.**\n\u003e From product requirements to code review — one plugin, full workflow.\n\n\u003cp align=\"center\"\u003e\n  \u003ccode\u003e35 commands\u003c/code\u003e · \u003ccode\u003e17 skills\u003c/code\u003e · \u003ccode\u003e8 agents\u003c/code\u003e · \u003ccode\u003e7 language standards\u003c/code\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"#-quick-start\"\u003eQuick Start\u003c/a\u003e •\n  \u003ca href=\"#-core-features\"\u003eFeatures\u003c/a\u003e •\n  \u003ca href=\"#-workflow\"\u003eWorkflow\u003c/a\u003e •\n  \u003ca href=\"#-command-reference\"\u003eCommands\u003c/a\u003e •\n  \u003ca href=\"#-faq\"\u003eFAQ\u003c/a\u003e\n\u003c/p\u003e\n\n### Why CC-Best?\n\n🎯 **The Problem**: Claude Code is powerful, but configuring workflows, coding standards, and safety rules from scratch takes hours.\n\n✨ **The Solution**: Pre-configured roles (PM → Lead → Designer → Dev → QA) that mirror real team collaboration, with safety guardrails built-in.\n\n## ⚡ Quick Start\n\n```bash\n# Add marketplace and install\n/plugin marketplace add xiaobei930/claude-code-best-practices\n/plugin install cc-best@xiaobei930\n\n# Verify installation (30 seconds)\n/cc-best:status\n\n# Start using\n/cc-best:iterate \"implement user authentication\"\n```\n\n\u003cdetails\u003e\n\u003csummary\u003e📹 See it in action\u003c/summary\u003e\n\u003cbr\u003e\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/setup.gif\" alt=\"Setup Demo\" width=\"80%\"\u003e\n\u003c/p\u003e\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e📦 Alternative: Clone for full customization\u003c/summary\u003e\n\n```bash\ngit clone https://github.com/xiaobei930/claude-code-best-practices.git .claude\ncd .claude \u0026\u0026 bash scripts/shell/init.sh\n\n# Convert command format from /cc-best:xxx to /xxx\nnode scripts/node/convert-to-local.js\n```\n\nUse clone when you need to customize all files in your repo.\n\n\u003e ⚠️ **Important**: All documentation uses plugin format (`/cc-best:xxx`).\n\u003e Run the conversion script to update to local format (`/xxx`).\n\n\u003c/details\u003e\n\n### Plugin vs Clone: Command Format\n\n| Installation  | Command format     | Example                          |\n| ------------- | ------------------ | -------------------------------- |\n| **Plugin** ⭐ | `/cc-best:command` | `/cc-best:iterate \"add feature\"` |\n| **Clone**     | `/command`         | `/cc-best:iterate \"add feature\"`         |\n\n\u003e 💡 **Recommended**: Install via plugin for automatic updates and easier management.\n\u003e All documentation uses plugin format (`/cc-best:xxx`). Clone users: run `convert-to-local.js`.\n\n\u003cdetails\u003e\n\u003csummary\u003e🗑️ Uninstall\u003c/summary\u003e\n\n```bash\n# Remove the plugin\n/plugin uninstall cc-best@xiaobei930\n\n# Remove marketplace (optional)\n/plugin marketplace remove xiaobei930/claude-code-best-practices\n```\n\nNo files are left behind.\n\n\u003c/details\u003e\n\n### What Happens Next?\n\nAfter running `/cc-best:iterate \"implement user authentication\"`, Claude will:\n\n```\n1. 📋 /cc-best:pm     → Analyze requirements, create task breakdown\n2. 🏗️ /cc-best:lead   → Design technical solution\n3. 💻 /cc-best:dev    → Write code, create tests\n4. 🧪 /cc-best:qa     → Run tests, verify quality\n5. ✅ /cc-best:commit → Commit changes with proper message\n```\n\nYou just watch. Intervene only when needed.\n\n### Common Workflows\n\n| I want to...       | Command                              | What Claude does                           |\n| ------------------ | ------------------------------------ | ------------------------------------------ |\n| Build a feature    | `/cc-best:iterate \"add dark mode toggle\"`    | Full cycle: plan → code → test → commit    |\n| Fix a bug          | `/cc-best:iterate \"fix login timeout issue\"` | Investigate → fix → verify → commit        |\n| Review code        | `/cc-best:pm \"review recent changes\"`        | Analyze code, suggest improvements         |\n| Learn the codebase | `/cc-best:pair`                              | Step-by-step exploration with explanations |\n\n### Who Is This For?\n\n| You are...                   | Recommended mode | Why                                       |\n| ---------------------------- | ---------------- | ----------------------------------------- |\n| **Team with multiple roles** | Full workflow    | PM → Lead → Dev → QA mirrors your process |\n| **Solo developer**           | `/cc-best:iterate`       | Let Claude handle the boring parts        |\n| **Learning Claude Code**     | `/cc-best:pair`          | Understand each step before proceeding    |\n| **Need quick fixes**         | Direct commands  | `/cc-best:dev \"fix the typo\"` for simple tasks    |\n\n---\n\n## ✨ Core Features\n\n| Feature                         | What it does                                                    |\n| ------------------------------- | --------------------------------------------------------------- |\n| 🎭 **Role-Based Workflow**      | PM → Lead → Designer → Dev → QA — complete development cycle    |\n| 🔄 **Autonomous Mode**          | `/cc-best:iterate` runs tasks without intervention until completion     |\n| 🛡️ **Safety Hooks**             | Blocks `rm -rf /`, `git push --force`, and other risky commands |\n| 📐 **Multi-Language Standards** | Coding conventions for Python, Vue/TS, C++, Java, C#, Go, Swift |\n| 🧠 **Memory Bank**              | Persists progress and decisions across sessions                 |\n| 🌐 **Cross-Platform**           | Windows, macOS, Linux — auto-detects package manager            |\n\n\u003cdetails\u003e\n\u003csummary\u003e📹 See /cc-best:iterate in action\u003c/summary\u003e\n\u003cbr\u003e\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/iterate.gif\" alt=\"Iterate Demo\" width=\"80%\"\u003e\n\u003c/p\u003e\n\u003c/details\u003e\n\n---\n\n## 📁 Directory Structure\n\n```\nyour-project/\n├── CLAUDE.md          # Project constitution\n├── commands/          # 35 slash commands\n├── skills/            # 17 development skills\n├── agents/            # 8 specialized agents\n├── rules/             # Coding standards\n├── hooks/             # Safety hooks\n├── scripts/           # Automation (node/python/shell)\n├── memory-bank/       # Progress \u0026 architecture docs\n└── .claude/           # Claude Code config\n```\n\n\u003cdetails\u003e\n\u003csummary\u003e📂 Detailed structure\u003c/summary\u003e\n\n| Directory      | Contents                                                                                                                |\n| -------------- | ----------------------------------------------------------------------------------------------------------------------- |\n| `commands/`    | Role commands (`pm`, `lead`, `dev`, `qa`), Mode commands (`iterate`, `pair`), Tool commands (`build`, `test`, `commit`) |\n| `skills/`      | Backend, Frontend, Testing, Security, DevOps, Architecture, Git                                                         |\n| `agents/`      | `code-reviewer`, `code-simplifier`, `planner`, `security-reviewer`, `tdd-guide`, `requirement-validator`                |\n| `rules/`       | Language-specific coding standards (Python, Vue/TS, C++, Java, C#, Go)                                                  |\n| `scripts/`     | Cross-platform hooks in Node.js (default), with Python/Bash alternatives                                                |\n| `memory-bank/` | `progress.md` (rolling window), `architecture.md`, `tech-stack.md`                                                      |\n\n\u003c/details\u003e\n\n---\n\n## 🔄 Workflow\n\n### Standard Development Cycle\n\n```mermaid\nflowchart LR\n    PM[\"/pm\u003cbr/\u003eRequirements\"] --\u003e Clarify[\"/clarify\u003cbr/\u003eClarify\"]\n    Clarify --\u003e Lead[\"/lead\u003cbr/\u003eDesign\"]\n    Lead --\u003e Designer[\"/designer\u003cbr/\u003eUI Design\"]\n    Designer --\u003e Dev[\"/dev\u003cbr/\u003eImplement\"]\n    Dev --\u003e QA[\"/qa\u003cbr/\u003eTest\"]\n    QA --\u003e Verify[\"/verify\u003cbr/\u003eVerify\"]\n    Verify --\u003e Commit[\"/commit\u003cbr/\u003eCommit\"]\n    Commit --\u003e Clear[\"/clear\u003cbr/\u003eClear Context\"]\n    Clear -.-\u003e|Loop| PM\n```\n\n### Three Development Modes\n\n| Mode                     | Command     | Use Case                       | Characteristics                                |\n| ------------------------ | ----------- | ------------------------------ | ---------------------------------------------- |\n| **Autonomous Iteration** | `/cc-best:iterate`  | Clear task list                | Fully autonomous, no intervention needed       |\n| **Pair Programming**     | `/cc-best:pair`     | Learning, sensitive operations | Confirm each step, human-machine collaboration |\n| **Long-Running Loop**    | `/cc-best:cc-ralph` | Hour-level batch tasks         | Requires ralph-loop plugin                     |\n\n\u003e 📖 **Detailed usage guide**: See [MODES.md](.claude-plugin/MODES.md) for comprehensive documentation on each mode, including when to use, how to control, and best practices.\n\n---\n\n## 📋 Command Reference\n\n**35 commands** organized into categories:\n\n| Category    | Commands                                                          | Purpose                           |\n| ----------- | ----------------------------------------------------------------- | --------------------------------- |\n| **Role**    | `/cc-best:pm`, `/cc-best:lead`, `/cc-best:dev`, `/cc-best:qa`, `/cc-best:designer`, `/cc-best:clarify`, `/cc-best:verify` | Development workflow roles        |\n| **Mode**    | `/cc-best:iterate`, `/cc-best:pair`, `/cc-best:cc-ralph`, `/cc-best:mode`                         | Autonomous/cc-best:pair programming modes |\n| **Build**   | `/cc-best:build`, `/cc-best:test`, `/cc-best:run`, `/cc-best:fix`                                 | Build and test automation         |\n| **Git**     | `/cc-best:commit`, `/cc-best:pr`, `/cc-best:git`                                          | Version control                   |\n| **Context** | `/cc-best:compact`, `/cc-best:checkpoint`, `/cc-best:catchup`, `/cc-best:context`, `/cc-best:memory`      | Session management                |\n| **Quality** | `/cc-best:cleanup`, `/cc-best:docs`, `/cc-best:learn`, `/cc-best:analyze`, `/cc-best:evolve`              | Code quality \u0026 knowledge          |\n| **Setup**   | `/cc-best:setup`, `/cc-best:setup-pm`, `/cc-best:status`, `/cc-best:self-check`                   | Configuration                     |\n\n\u003e 📖 **Full reference**: See [COMMANDS.md](.claude-plugin/COMMANDS.md) for all parameters and usage examples.\n\n---\n\n## 🛠️ Skills\n\n**17 development skills** organized by domain:\n\n| Domain           | Skills                               | Coverage                    |\n| ---------------- | ------------------------------------ | --------------------------- |\n| **Backend**      | `backend`, `api`, `database`         | Python, TS, Java, Go, C#    |\n| **Frontend**     | `frontend`                           | Vue, React, Svelte, Angular |\n| **Quality**      | `testing`, `security`, `debug`       | TDD, OWASP, profiling       |\n| **Architecture** | `architecture`, `devops`, `git`      | ADR, CI/CD, branching       |\n| **Session**      | `learning`, `compact`, `exploration` | Knowledge management        |\n\n\u003e 📖 **Full reference**: See [skills/README](skills/README) for detailed skill documentation.\n\n---\n\n## 🏗️ Architecture Overview\n\nThis template uses a **three-tier architecture**:\n\n```mermaid\nflowchart TB\n    subgraph User[\"👤 You\"]\n        CMD[\"/cc-best:iterate 'add feature'\"]\n    end\n\n    subgraph Commands[\"📋 Commands (35)\"]\n        PM[\"/cc-best:pm\"] --\u003e Lead[\"/cc-best:lead\"] --\u003e Dev[\"/cc-best:dev\"] --\u003e QA[\"/cc-best:qa\"]\n    end\n\n    subgraph Skills[\"🛠️ Skills (17)\"]\n        S1[\"backend\"]\n        S2[\"frontend\"]\n        S3[\"testing\"]\n        S4[\"security\"]\n    end\n\n    subgraph Agents[\"🤖 Agents (6)\"]\n        A1[\"code-reviewer\"]\n        A2[\"planner\"]\n        A3[\"security-reviewer\"]\n    end\n\n    CMD --\u003e Commands\n    Commands -.-\u003e|\"auto-inject\"| Skills\n    Commands -.-\u003e|\"delegate\"| Agents\n```\n\n| Layer        | Trigger              | Purpose                                  |\n| ------------ | -------------------- | ---------------------------------------- |\n| **Commands** | User types `/xxx`    | Role workflow, user-initiated actions    |\n| **Skills**   | Auto-injected        | Best practices, coding standards         |\n| **Agents**   | Task tool delegation | Specialized sub-tasks (review, planning) |\n\n**8 specialized agents**: `architect`, `build-error-resolver`, `code-reviewer`, `code-simplifier`, `planner`, `requirement-validator`, `security-reviewer`, `tdd-guide`\n\n\u003e 📐 **Full documentation**: See [ARCHITECTURE.md](.claude-plugin/ARCHITECTURE.md) for component relationships and call chains.\n\u003e\n\u003e 🤖 **Agent details**: See [agents/README](agents/README) for agent capabilities and invocation.\n\n---\n\n## 🔌 Plugin Compatibility\n\nThis template is designed to work seamlessly with official Claude Code plugins. Our built-in agents and skills complement (not replace) official plugins.\n\n### Relationship with Official Plugins\n\n| Template Content          | Official Plugin      | Relationship                                                                 |\n| ------------------------- | -------------------- | ---------------------------------------------------------------------------- |\n| `code-reviewer` agent     | `code-review` plugin | Template: lightweight local version; Plugin: more powerful with auto-trigger |\n| `security-reviewer` agent | `security-guidance`  | Template: OWASP checklist; Plugin: automatic security analysis               |\n| `code-simplifier` agent   | `code-simplifier`    | Similar function; plugin has more context                                    |\n| `/cc-best:cc-ralph` command       | `ralph-loop` plugin  | CC-Best wrapper; requires plugin for cross-session persistence               |\n| `hookify` examples        | `hookify` plugin     | Template: examples; Plugin: full hook management                             |\n\n### Recommended Plugin Configuration\n\n```json\n{\n  \"enabledPlugins\": {\n    \"code-review@claude-plugins-official\": true,\n    \"hookify@claude-plugins-official\": true,\n    \"security-guidance@claude-plugins-official\": true\n  }\n}\n```\n\n### When to Use Which\n\n- **No plugins installed**: Template agents/skills work standalone\n- **With plugins**: Use plugins for advanced features, template for quick local checks\n- **Best practice**: Install plugins, use template agents for immediate feedback, plugins for deep analysis\n\n---\n\n## ⚙️ Customization Guide\n\n### Adding New Rules\n\nCreate a file in `rules/`:\n\n```markdown\n---\npaths:\n  - \"**/*.your-ext\"\n---\n\n# Rule Title\n\n## Rule Content\n\n...\n```\n\n### Adding New Commands\n\nCreate a file in `commands/`:\n\n```markdown\n---\nallowed_tools:\n  - Read\n  - Edit\n  - Write\n  - Bash\n---\n\n# /your-command - Command Name\n\n## Responsibilities\n\n...\n\n## Execution Steps\n\n1. ...\n2. ...\n```\n\n### Configuring Hooks\n\nEdit `.claude/settings.local.json`:\n\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Bash\",\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"python scripts/your-script.py\",\n            \"timeout\": 5\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n### Pre-configured Hooks\n\n\u003e ⚠️ **Important: Hooks Require Manual Setup**\n\u003e\n\u003e Due to a [known Claude Code issue](https://github.com/anthropics/claude-code/issues/9354), plugin hooks are **disabled by default**. To enable the safety guards and automation hooks, run:\n\u003e\n\u003e ```bash\n\u003e /cc-best:setup --hooks\n\u003e ```\n\u003e\n\u003e This command configures hooks with absolute paths. See the [FAQ](#hook-issues) for more details.\n\nAll hooks default to Node.js for cross-platform compatibility. Python/Bash alternatives available.\n\n| Trigger      | Function                    | Script (Node.js)       |\n| ------------ | --------------------------- | ---------------------- |\n| PreToolUse   | Validate dangerous commands | `validate-command.js`  |\n| PreToolUse   | Confirm before git push     | `pause-before-push.js` |\n| PreToolUse   | Protect sensitive files     | `protect-files.js`     |\n| PreToolUse   | Block random .md creation   | `block-random-md.js`   |\n| PostToolUse  | Auto-format code            | `format-file.js`       |\n| PostToolUse  | Check console.log           | `check-console-log.js` |\n| PostToolUse  | TypeScript type check       | `typescript-check.js`  |\n| SessionStart | Session health check        | `session-check.js`     |\n| SessionStart | Load previous context       | `session-start.js`     |\n| PreCompact   | Save state before compact   | `pre-compact.js`       |\n| SessionEnd   | Session end persistence     | `session-end.js`       |\n\n---\n\n## 💡 Best Practices\n\n### 1. Keep CLAUDE.md Concise\n\n- Keep it under 100 lines\n- Put detailed specifications in `rules/`\n\n### 2. Use the Memory Bank\n\n- Update `progress.md` after each task completion\n- Record important decisions in `architecture.md`\n\n### 3. Context Management\n\n- Normal mode: Use `/clear` frequently to avoid context overflow\n- `/cc-best:iterate` mode: Don't clear manually, maintain loop continuity\n\n### 4. Don't Overload MCP\n\n- Enable no more than 10 MCP servers per project\n- Use `disabledMcpServers` to disable unused ones\n\n### 5. Regular Cleanup\n\n- Delete unused language rules\n- Remove unused commands\n\n### 6. MCP Temporary Directory Management\n\nMCP tools auto-create temporary directories in your project:\n\n| Directory              | Source           | Purpose                                 |\n| ---------------------- | ---------------- | --------------------------------------- |\n| `.playwright-mcp/`     | MCP auto-created | Playwright MCP temporary files          |\n| `.claude/mcp-data/`    | MCP auto-created | MCP shared data                         |\n| `*-mcp/`               | MCP auto-created | Other MCP tool directories              |\n| `.claude/screenshots/` | Template-defined | Manually saved screenshots (meaningful) |\n\n**Cleanup Script**: Use `cleanup.sh` for regular maintenance:\n\n```bash\n# Preview files to delete (dry run)\nbash scripts/shell/cleanup.sh --dry-run\n\n# Clean files older than 7 days (default)\nbash scripts/shell/cleanup.sh\n\n# Clean files older than 3 days\nbash scripts/shell/cleanup.sh --days 3\n\n# Clean all MCP temporary files\nbash scripts/shell/cleanup.sh --all\n```\n\n---\n\n## ❓ FAQ\n\n\u003e 📖 **Full FAQ**: See [FAQ.md](FAQ.md) for comprehensive troubleshooting guides.\n\n### Quick Answers\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eHooks not working?\u003c/strong\u003e\u003c/summary\u003e\n\nRun `/cc-best:setup --verify` to diagnose. Common fixes:\n\n- Clone users: `cp .claude/settings.local.json.example .claude/settings.local.json`\n- Plugin users: Run `/cc-best:setup --hooks` to configure absolute paths\n- Windows: See [FAQ.md](FAQ.md#hook-issues) for `${CLAUDE_PLUGIN_ROOT}` workarounds\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003e/cc-best:iterate vs /pair?\u003c/strong\u003e\u003c/summary\u003e\n\n| Mode       | Control           | Use Case                |\n| ---------- | ----------------- | ----------------------- |\n| `/cc-best:iterate` | Fully autonomous  | Clear task list         |\n| `/cc-best:pair`    | Confirm each step | Learning, sensitive ops |\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eHow to stop /iterate?\u003c/strong\u003e\u003c/summary\u003e\n\n- **Interrupt**: Press `Ctrl+C` (or `Esc` in some terminals)\n- **Pause**: Type anything — Claude will wait for your input\n- **Resume**: Just continue the conversation\n\nClaude saves progress to `memory-bank/progress.md`, so you can always resume later.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eWhat if /cc-best:qa fails?\u003c/strong\u003e\u003c/summary\u003e\n\nClaude will:\n\n1. Analyze the failure\n2. Return to `/cc-best:dev` to fix the issue\n3. Re-run `/cc-best:qa` to verify\n\nIf stuck after 3 attempts, Claude will ask for your input. You can:\n\n- Provide hints: \"Try checking the database connection\"\n- Skip the test: \"Skip this test for now\"\n- Take over: \"I'll fix this manually\"\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eMCP configuration?\u003c/strong\u003e\u003c/summary\u003e\n\nEdit `.claude/settings.local.json`:\n\n```json\n{ \"enabledMcpjsonServers\": [\"memory\", \"sequential-thinking\"] }\n```\n\nBest practice: Enable ≤10 MCP servers per project.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eCC-Best vs Superpowers?\u003c/strong\u003e\u003c/summary\u003e\n\nBoth are excellent. Choose based on your needs:\n\n| Scenario             | Recommended | Why                              |\n| -------------------- | ----------- | -------------------------------- |\n| Team collaboration   | CC-Best     | Role workflow (PM→Lead→Dev→QA)   |\n| Multi-language stack | CC-Best     | 7 language coding standards      |\n| Chinese team         | CC-Best     | Bilingual docs                   |\n| Solo developer       | Superpowers | Lighter, git worktree automation |\n| Need git worktree    | Superpowers | Auto-creates isolated branches   |\n\n\u003e 💡 They can coexist! Use CC-Best for workflows, Superpowers for git automation.\n\n\u003c/details\u003e\n\n---\n\n## 🔧 Requirements\n\n| Dependency    | Version            | Notes                              |\n| ------------- | ------------------ | ---------------------------------- |\n| Claude Code   | Latest recommended | Hooks require recent versions      |\n| Node.js       | 16+                | For cross-platform hooks (default) |\n| Python        | 3.8+               | For some hook scripts              |\n| Bash/Git Bash | Any version        | Optional for bash hooks            |\n\n### Optional MCP Servers\n\nSome commands use MCP (Model Context Protocol) tools for enhanced functionality:\n\n| MCP Server | Used By                    | Purpose                                           |\n| ---------- | -------------------------- | ------------------------------------------------- |\n| Playwright | `/cc-best:designer`, `/cc-best:dev`, `/cc-best:pm` | Browser automation for UI testing and screenshots |\n| Firecrawl  | `/cc-best:pm`, `/cc-best:lead`             | Web scraping for requirement research             |\n\n\u003e **Note**: These are optional. Commands work without MCP servers but with reduced functionality.\n\u003e Install via Claude Code settings: `Settings \u003e MCP Servers`\n\n### Supported Languages\n\n| Language  | Rule File           | Formatter          | Test Framework |\n| --------- | ------------------- | ------------------ | -------------- |\n| Python    | `code-style.md`     | Black + isort      | pytest         |\n| Vue/TS/JS | `frontend-style.md` | Prettier           | Vitest         |\n| C++       | `cpp-style.md`      | clang-format       | Google Test    |\n| Java      | `java-style.md`     | google-java-format | JUnit          |\n| C#        | `csharp-style.md`   | dotnet format      | xUnit/NUnit    |\n| Go        | `backend/go.md`     | gofmt              | testing        |\n| Swift     | `native/ios.md`     | swift-format       | XCTest         |\n\n---\n\n## 📚 References\n\n### Official Resources\n\n- [Anthropic Official Best Practices](https://www.anthropic.com/engineering/claude-code-best-practices)\n- [CLAUDE.md Complete Guide](https://www.builder.io/blog/claude-md-guide)\n\n### Community Projects\n\n- [everything-claude-code](https://github.com/affaan-m/everything-claude-code) - Claude Code resource collection\n- [vibe-coding-cn](https://github.com/2025Emma/vibe-coding-cn) - Chinese Vibe Coding guide\n\n---\n\n## 🌐 Note on Internal Files\n\nThis template's internal files (`commands/`, `rules/`, `skills/`) are written in **Chinese**. This is intentional:\n\n- **Claude understands Chinese** - All Claude models can read and follow Chinese instructions perfectly\n- **No translation burden** - Maintaining dual-language internal files would be impractical\n- **Focus on users** - The README (this file) is fully English for international users\n\nIf you prefer English internal files, community contributions for English translations are welcome!\n\n---\n\n## 🤝 Contributing\n\nContributions are welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) for details.\n\n| Contribution Type  | Description                                                      |\n| ------------------ | ---------------------------------------------------------------- |\n| ⭐ Star            | Show your support                                                |\n| 🐛 Bug Report      | [Report issues](../../issues/new?template=bug_report.md)         |\n| 💡 Feature Request | [Suggest features](../../issues/new?template=feature_request.md) |\n| 📝 Documentation   | Improve docs                                                     |\n| 🔧 Code            | Add commands, rules, skills                                      |\n\n---\n\n## 📄 License\n\n[MIT License](LICENSE) - Free to use and modify\n\n---\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eIf this template helps you, please give it a ⭐ Star!\u003c/strong\u003e\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxiaobei930%2Fclaude-code-best-practices","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxiaobei930%2Fclaude-code-best-practices","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxiaobei930%2Fclaude-code-best-practices/lists"}