convez.ai
SkillAutomaçãoIntermediário
xiaobei930

CC-Best

xiaobei930/cc-best

Time de dev autônomo: PM→Lead→Dev→QA em um plugin

Ver no GitHub
BomPluginScore · de 0 a 100

Transforma Claude Code em um time de desenvolvimento autônomo com papéis definidos (PM, Lead, Dev, QA). Oferece 44 comandos, 19 skills, 8 agents e fluxo de trabalho pré-configurado que simula colaboração real entre membros de equipe com guardrails de segurança integrados.

Instalação

$npx convez-ai xiaobei930/cc-best

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
50
Forks
3
Acompanhando
0
Saúde
71%
Último commit
há 5 meses
Versão
v0.11.0
Issues abertas
0
Contribuidores
1

Casos de uso

  • Automatizar fluxo completo de desenvolvimento (requisitos → código → review)
  • Aplicar padrões de codificação e regras de segurança consistentemente
  • Simular colaboração em equipe para projetos solo

Veredito

Ferramenta robusta para quem busca automatizar workflows de desenvolvimento com múltiplos agentes. Exige configuração inicial mas entrega produtividade real em projetos complexos que demandam múltiplos papéis.

README

A tradução para o português deste README ainda está na fila.

CC-Best


Transform Claude into a complete development team. From product requirements to code review — one plugin, full workflow.

Why CC-Best?

🎯 The Problem: Claude Code is powerful, but configuring workflows, coding standards, and safety rules from scratch takes hours.

✨ The Solution: Pre-configured roles (PM → Lead → Designer → Dev → QA) that mirror real team collaboration, with safety guardrails built-in.

⚡ Quick Start

# Add marketplace and install
/plugin marketplace add xiaobei930/cc-best
/plugin install cc-best@xiaobei930

# Verify installation (30 seconds)
/cc-best:status

# Start using
/cc-best:iterate "implement user authentication"

💡 Enable Hooks: After installation, run /cc-best:setup --hooks to activate safety guards and automation hooks. See Hooks Configuration for details.

Plugin vs Clone: Command Format

InstallationCommand formatExample
Plugin ⭐/cc-best:command/cc-best:iterate "add feature"
Clone/command/iterate "add feature"

💡 Recommended: Install via plugin for automatic updates and easier management. All documentation uses plugin format (/cc-best:xxx). Clone users: run convert-to-local.js.

git clone https://github.com/xiaobei930/cc-best.git .claude
cd .claude && bash scripts/shell/init.sh

# Convert command format from /cc-best:xxx to /xxx
node scripts/node/convert-to-local.js

Use clone when you need to customize all files in your repo.

⚠️ Important: All documentation uses plugin format (/cc-best:xxx). Run the conversion script to update to local format (/xxx).

# Remove the plugin
/plugin uninstall cc-best@xiaobei930

# Remove marketplace (optional)
/plugin marketplace remove xiaobei930/cc-best

No files are left behind.

What Happens Next?

After running /cc-best:iterate "implement user authentication", Claude will:

1. 📋 /cc-best:pm     → Analyze requirements, create task breakdown
2. 🏗️ /cc-best:lead   → Design technical solution
3. 💻 /cc-best:dev    → Write code, create tests
4. 🧪 /cc-best:qa     → Run tests, verify quality
5. ✅ /cc-best:commit → Commit changes with proper message

You just watch. Intervene only when needed.

Common Workflows

I want to...CommandWhat Claude does
Build a feature/cc-best:iterate "add dark mode toggle"Full cycle: plan → code → test → commit
Fix a bug/cc-best:iterate "fix login timeout issue"Investigate → fix → verify → commit
Review code/cc-best:pm "review recent changes"Analyze code, suggest improvements
Learn the codebase/cc-best:pairStep-by-step exploration with explanations

Who Is This For?

You are...Recommended modeWhy
Team with multiple rolesFull workflowPM → Lead → Dev → QA mirrors your process
Solo developer/cc-best:iterateLet Claude handle the boring parts
Learning Claude Code/cc-best:pairUnderstand each step before proceeding
Need quick fixesDirect commands/cc-best:dev "fix the typo" for simple tasks

✨ Core Features

FeatureWhat it does
🎭 Role-Based WorkflowPM → Lead → Designer → Dev → QA — complete development cycle
🔄 Autonomous Mode/cc-best:iterate runs tasks without intervention until completion
🛡️ Safety HooksBlocks rm -rf /, git push --force, and other risky commands
📐 Multi-Language Standards8-dir layered structure: common + Python/frontend/Java/C#/C++/embedded/UI rules
🧠 Memory BankPersists progress and decisions across sessions
👥 Pair Programming/cc-best:pair — step-by-step collaboration with 5 confirmation checkpoints
🔗 Knowledge Pipelineobserve → analyze → learn → evolve — self-improving knowledge loop
🌐 Cross-PlatformWindows, macOS, Linux — auto-detects package manager

While CC-Best is built for Claude Code, the methodology (Dao-Fa-Shu-Qi) and role-driven patterns are framework-agnostic and can be adapted for other AI coding assistants.

What Makes CC-Best Different

Not just a prompt template collection — CC-Best simulates real team collaboration:

  • 7 roles with clear boundaries: PM → Lead → Designer → Dev → QA → Verify → Commit
  • Each role has explicit MUST/SHOULD/NEVER rules, output templates, and handoff protocols
  • Automatic flow: PM creates REQ → Lead reviews & creates DES/TSK → Dev implements → QA validates
  • Downstream correction (A3): Lead can adjust PM decisions; QA distinguishes implementation bugs from requirement assumption errors
  • Document traceability: REQ-XXX → DES-XXX → TSK-XXX numbered chain

/cc-best:iterate enables fully autonomous development:

Read progress.md → Select role → Execute → Verify → Commit → Next task (no waiting)
  • Smart role selection: 8 state conditions determine which role activates
  • A1-A5 decision principles: Context inference (A1), decision recording (A2), downstream correction (A3), MVP fallback (A4), issue classification (A5)
  • 4 strict stop conditions: All tasks done, user interrupt, fatal error, external dependency
  • Cross-session continuity: memory-bank + progress.md rolling window

CC-Best learns from your development patterns:

observe → analyze → learn → evolve
  • observe: observe-patterns.js hook automatically tracks tool usage patterns
  • analyze: /cc-best:analyze mines git history and usage data
  • learn: /cc-best:learn extracts reusable knowledge
  • evolve: /cc-best:evolve generates new commands, skills, or agents from learned patterns

📁 Directory Structure

your-project/
├── CLAUDE.md          # Project constitution
├── commands/          # 44 slash commands
├── skills/            # 19 development skills
├── agents/            # 8 specialized agents
├── rules/             # 43 coding standards (10 dirs)
├── hooks/             # Safety hooks
├── scripts/           # Automation (node/python/shell)
├── memory-bank/       # Progress & architecture docs
└── .claude/           # Claude Code config
DirectoryContents
commands/Role commands (pm, lead, dev, qa), Mode commands (iterate, pair), Tool commands (build, test, commit)
skills/Backend, Frontend, Testing, Security, DevOps, Architecture, Git
agents/architect, build-error-resolver, code-reviewer, code-simplifier, planner, requirement-validator, security-reviewer, tdd-guide
rules/43 rules in 10 dirs: common/ + python/, frontend/, java/, csharp/, cpp/, embedded/, ui/, rust/, go/
scripts/Cross-platform hooks in Node.js (default), with Python/Bash alternatives
memory-bank/progress.md (rolling window), architecture.md, tech-stack.md

🔄 Workflow

Standard Development Cycle

flowchart LR
    PM["/pm<br/>Requirements"] --> Clarify["/clarify<br/>Clarify"]
    Clarify --> Lead["/lead<br/>Design"]
    Lead --> Designer["/designer<br/>UI Design"]
    Designer --> Dev["/dev<br/>Implement"]
    Dev --> QA["/qa<br/>Test"]
    QA --> Verify["/verify<br/>Verify"]
    Verify --> Commit["/commit<br/>Commit"]
    Commit --> Clear["/clear<br/>Clear Context"]
    Clear -.->|Loop| PM

Three Development Modes

ModeCommandUse CaseCharacteristics
Autonomous Iteration/cc-best:iterateClear task listFully autonomous, no intervention needed
Pair Programming/cc-best:pairLearning, sensitive operationsConfirm each step, human-machine collaboration
Long-Running Loop/cc-best:cc-ralphHour-level batch tasksRequires ralph-loop plugin (/plugin install ralph-loop@claude-plugins-official)
Current StateRole SelectedAction
No requirements doc/cc-best:pmRequirement analysis
REQ has low-confidence items/cc-best:clarifyRequirement clarification
Has REQ, no design/cc-best:leadTechnical design
Has design, frontend tasks/cc-best:designerUI design guidance
Has tasks to implement/cc-best:devCoding implementation
Code ready for verification/cc-best:verifyBuild + type + lint + test + security
Verification passed/cc-best:qaFunctional acceptance

Core behavior: Task complete → Update progress.md → Read next task → Execute immediately (no waiting).

Stop conditions: All tasks done | User interrupt (Ctrl+C) | Fatal error | External dependency needed.

5 mandatory confirmation checkpoints:

CheckpointExample
Understanding"I understand you need X. Correct?"
Design choice"Option A or B? I recommend A because..."
Destructive action"About to delete X. Confirm?"
External call"Will call production API. Proceed?"
Commit"Commit message: '...'. OK?"

Learning mode: /cc-best:pair --learn "teach me unit testing" — Claude explains every step in detail.

Safe autonomy: Even in pair mode, Claude can freely read files, search code, run tests, and format code.

📖 Detailed usage guide: See MODES.md for comprehensive documentation on each mode, including when to use, how to control, and best practices.


📋 Command Reference

44 commands organized into categories:

CategoryCommandsPurpose
Role/cc-best:pm, /cc-best:lead, /cc-best:dev, /cc-best:qa, /cc-best:designer, /cc-best:clarify, /cc-best:verifyDevelopment workflow roles
Mode/cc-best:iterate, /cc-best:pair, /cc-best:cc-ralph, /cc-best:mode, /cc-best:modelAutonomous/pair modes & model strategy
Build/cc-best:build, /cc-best:test, /cc-best:run, /cc-best:fixBuild and test automation
Git/cc-best:commit, /cc-best:pr, /cc-best:git-guideVersion control
Context/cc-best:compact-context, /cc-best:checkpoint, /cc-best:catchup, /cc-best:context, /cc-best:memorySession management
Quality/cc-best:cleanup, /cc-best:docs, /cc-best:learn, /cc-best:analyze, /cc-best:evolveCode quality & knowledge
Ops/cc-best:fix-issue, /cc-best:release, /cc-best:service, /cc-best:hotfixIssue fix, release, hotfix, services
Setup/cc-best:setup, /cc-best:setup-pm, /cc-best:status, /cc-best:self-check, /cc-best:confidence-check, /cc-best:security-auditConfiguration & diagnostics

📖 Full reference: See COMMANDS.md for all parameters and usage examples.


🛠️ Skills

19 development skills organized by domain:

DomainSkillsCoverage
Backendbackend, api, databasePython, TS, Java, Go, C#
Frontendfrontend, nativeWeb + iOS/macOS/Tauri
Qualityquality, testing, security, debugTDD, OWASP, profiling
Architecturearchitecture, devops, gitADR, CI/CD, branching
RoutingmodelTask→model recommendation
Sessionsession, learning, compact, explorationLifecycle + knowledge management
Researchsearch-first, second-opinionSearch strategy, cross-validation

📖 Full reference: See skills/README for detailed skill documentation.


🏗️ Architecture Overview

CC-Best uses a four-tier architecture:

flowchart TB
    subgraph User["👤 You"]
        CMD["/cc-best:iterate 'add feature'"]
    end

    subgraph Commands["📋 Commands (44)"]
        PM["/pm"] --> Lead["/lead"] --> Dev["/dev"] --> QA["/qa"]
    end

    subgraph Skills["🛠️ Skills (19)"]
        S1["backend · frontend · testing · security"]
        S2["architecture · devops · git"]
        S3["learning · compact · exploration"]
    end

    subgraph Agents["🤖 Agents (8)"]
        A1["architect · planner · code-reviewer"]
        A2["code-simplifier · security-reviewer"]
        A3["tdd-guide · build-error-resolver · requirement-validator"]
    end

    subgraph Safety["🛡️ Safety Hooks (30)"]
        H1["PreToolUse: validate, secrets, protect"]
        H2["PostToolUse: format, typecheck, observe"]
    end

    CMD --> Commands
    Commands -.->|"auto-inject"| Skills
    Commands -.->|"delegate"| Agents
    Commands -.->|"guard"| Safety
LayerTriggerPurpose
CommandsUser types /xxxRole workflow, user-initiated actions
SkillsAuto-injectedBest practices, coding standards
AgentsTask tool delegationSpecialized sub-tasks (review, planning)
HooksLifecycle eventsSafety guards, auto-format, pattern learning

8 specialized agents: architect, build-error-resolver, code-reviewer, code-simplifier, planner, requirement-validator, security-reviewer, tdd-guide

📐 Full documentation: See ARCHITECTURE.md for component relationships and call chains.

🤖 Agent details: See agents/README for agent capabilities and invocation.


🔌 Plugin Compatibility

CC-Best is designed to work seamlessly with official Claude Code plugins. Our built-in agents and skills complement (not replace) official plugins.

Relationship with Official Plugins

CC-Best ContentOfficial PluginRelationship
code-reviewer agentcode-review pluginBuilt-in: lightweight local version; Official: more powerful with auto-trigger
security-reviewer agentsecurity-guidanceBuilt-in: OWASP checklist; Official: automatic security analysis
code-simplifier agentcode-simplifierSimilar function; official plugin has more context
/cc-best:cc-ralph commandralph-loop pluginCC-Best wrapper; requires plugin for cross-session persistence
hookify exampleshookify pluginBuilt-in: examples; Official: full hook management

Recommended Plugin Configuration

{
  "enabledPlugins": {
    "code-review@claude-plugins-official": true,
    "hookify@claude-plugins-official": true,
    "security-guidance@claude-plugins-official": true
  }
}

When to Use Which

  • No plugins installed: Built-in agents/skills work standalone
  • With plugins: Use official plugins for advanced features, CC-Best for quick local checks
  • Best practice: Install official plugins, use built-in agents for immediate feedback, official plugins for deep analysis

⚙️ Customization Guide

Adding New Rules

Create a file in rules/:

---
paths:
  - "**/*.your-ext"
---

# Rule Title

## Rule Content

...

Adding New Commands

Create a file in commands/:

---
allowed_tools:
  - Read
  - Edit
  - Write
  - Bash
---

# /your-command - Command Name

## Responsibilities

...

## Execution Steps

1. ...
2. ...

Configuring Hooks

Edit .claude/settings.local.json:

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "python scripts/your-script.py",
            "timeout": 5
          }
        ]
      }
    ]
  }
}

Pre-configured Hooks

⚠️ Important: Hooks Require Manual Setup

Due to a known Claude Code issue, plugin hooks are disabled by default. To enable the safety guards and automation hooks, run:

/cc-best:setup --hooks

This command configures hooks with absolute paths. See the FAQ for more details.

All hooks default to Node.js for cross-platform compatibility. Python/Bash alternatives available in scripts/.

TriggerFunctionScript (Node.js)
PreToolUseValidate dangerous commandsvalidate-command.js
PreToolUseConfirm before git pushpause-before-push.js
PreToolUseProtect sensitive filesprotect-files.js
PreToolUseBlock random .md creationblock-random-md.js
PreToolUseLong-running task warninglong-running-warning.js
PostToolUseAuto-format codeformat-file.js
PostToolUseCheck console.logcheck-console-log.js
PostToolUseTypeScript type checktypescript-check.js
SessionStartSession health checksession-check.js
PreCompactSave state before compactpre-compact.js

💡 Best Practices

1. Keep CLAUDE.md Concise

  • Keep it under 100 lines
  • Put detailed specifications in rules/

2. Use the Memory Bank

  • Update progress.md after each task completion
  • Record important decisions in architecture.md

3. Context Management

  • Normal mode: Use /clear frequently to avoid context overflow
  • /cc-best:iterate mode: Don't clear manually, maintain loop continuity

4. Don't Overload MCP

  • Enable no more than 10 MCP servers per project
  • Use disabledMcpServers to disable unused ones

5. Regular Cleanup

  • Delete unused language rules
  • Remove unused commands

6. MCP Temporary Directory Management

MCP tools auto-create temporary directories in your project:

DirectorySourcePurpose
.playwright-mcp/MCP auto-createdPlaywright MCP temporary files
.claude/mcp-data/MCP auto-createdMCP shared data
*-mcp/MCP auto-createdOther MCP tool directories
.claude/screenshots/Template-definedManually saved screenshots (meaningful)

Cleanup Script: Use cleanup.sh for regular maintenance:

# Preview files to delete (dry run)
bash scripts/shell/cleanup.sh --dry-run

# Clean files older than 7 days (default)
bash scripts/shell/cleanup.sh

# Clean files older than 3 days
bash scripts/shell/cleanup.sh --days 3

# Clean all MCP temporary files
bash scripts/shell/cleanup.sh --all

❓ FAQ

📖 Full FAQ: See FAQ.md for comprehensive troubleshooting guides.

Quick Answers

Run /cc-best:setup --verify to diagnose. Common fixes:

  • Clone users: cp .claude/settings.local.json.example .claude/settings.local.json
  • Plugin users: Run /cc-best:setup --hooks to configure absolute paths
  • Windows: See FAQ.md for ${CLAUDE_PLUGIN_ROOT} workarounds
ModeControlUse Case
/cc-best:iterateFully autonomousClear task list
/cc-best:pairConfirm each stepLearning, sensitive ops
  • Interrupt: Press Ctrl+C (or Esc in some terminals)
  • Pause: Type anything — Claude will wait for your input
  • Resume: Just continue the conversation

Claude saves progress to memory-bank/progress.md, so you can always resume later.

Claude will:

  1. Analyze the failure
  2. Return to /cc-best:dev to fix the issue
  3. Re-run /cc-best:qa to verify

If stuck after 3 attempts, Claude will ask for your input. You can:

  • Provide hints: "Try checking the database connection"
  • Skip the test: "Skip this test for now"
  • Take over: "I'll fix this manually"

Edit .claude/settings.local.json:

{ "enabledMcpjsonServers": ["memory", "sequential-thinking"] }

Best practice: Enable ≤10 MCP servers per project.

Both are excellent. Choose based on your needs:

ScenarioRecommendedWhy
Team collaborationCC-BestRole workflow (PM→Lead→Dev→QA)
Multi-language stackCC-Best7 language coding standard dirs
Chinese teamCC-BestBilingual docs
Solo developerSuperpowersLighter, git worktree automation
Need git worktreeSuperpowersAuto-creates isolated branches

💡 They can coexist! Use CC-Best for workflows, Superpowers for git automation.


🔧 Requirements

DependencyVersionNotes
Claude CodeLatest recommendedHooks require recent versions
Node.js16+For cross-platform hooks (default)
Python3.8+For some hook scripts
Bash/Git BashAny versionOptional for bash hooks

Optional MCP Servers

Some commands use MCP (Model Context Protocol) tools for enhanced functionality:

MCP ServerUsed ByPurpose
Playwright/cc-best:designer, /cc-best:dev, /cc-best:pmBrowser automation for UI testing and screenshots
Firecrawl/cc-best:pm, /cc-best:leadWeb scraping for requirement research

Note: These are optional. Commands work without MCP servers but with reduced functionality. Install via Claude Code settings: Settings > MCP Servers

Supported Languages

LanguageRule FileFormatterTest Framework
Pythonpython-style.mdBlack + isortpytest
Vue/TS/JSfrontend-style.mdPrettierVitest
C++cpp-style.mdclang-formatGoogle Test
Javajava-style.mdgoogle-java-formatJUnit
C#csharp-style.mddotnet formatxUnit/NUnit
Gobackend/go.mdgofmttesting
Swiftnative/ios.mdswift-formatXCTest

📚 References

Official Resources

Plugin Documentation


🌐 Note on Internal Files

CC-Best's internal files (commands/, rules/, skills/) are written in Chinese. This is intentional:

  • Claude understands Chinese - All Claude models can read and follow Chinese instructions perfectly
  • No translation burden - Maintaining dual-language internal files would be impractical
  • Focus on users - The README (this file) is fully English for international users

If you prefer English internal files, community contributions for English translations are welcome!


🤝 Contributing

Contributions are welcome! See CONTRIBUTING.md for details.

Contribution TypeDescription
⭐ StarShow your support
🐛 Bug ReportReport issues
💡 Feature RequestSuggest features
📝 DocumentationImprove docs
🔧 CodeAdd commands, rules, skills

📄 License

MIT License - Free to use and modify


Star History

Ver o original no GitHub

Bom para

Relacionados