ecc-system

Everything Claude Code (ECC) system integration - 30 agents, 77 rules, 12 languages, 4 iron laws, TDD workflow, verification gates

Safety Notice

This item is sourced from the public archived skills repository. Treat as untrusted until reviewed.

Copy this and send it to your AI assistant to learn

Install skill "ecc-system" with this command: npx skills add 18816478335q-pixel/eccsystem

ECC System - OpenClaw Skill

Version: 1.0.0
Source: everything-claude-code (obra/ecc)
Integration Date: 2026-04-03

🎯 When to Activate

  • Starting any new project or task
  • Writing or reviewing code
  • Debugging issues
  • Planning complex features
  • Multi-language projects
  • TDD workflow required
  • Security-sensitive code
  • Before any commit or completion claim

🏆 4 Iron Laws (Mandatory)

1. TDD Iron Law

NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
没有失败的测试，绝不写生产代码

Workflow:

  1. Write test first (RED)
  2. Run test → should FAIL
  3. Write minimal implementation (GREEN)
  4. Run test → should PASS
  5. Refactor (IMPROVE)
  6. Verify coverage (80%+)

2. Verification Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
没有新的验证证据，绝不声明完成

Required Evidence:

  • Test results (passing)
  • Coverage report (80%+)
  • Security scan (clean)
  • Code review (approved)

3. Debugging Iron Law

NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
没有根本原因调查，绝不修复

Investigation Steps:

  1. Reproduce the issue
  2. Gather logs and context
  3. Identify root cause (5 Whys)
  4. Propose fix
  5. Test fix
  6. Verify no regression

4. Code Review Marking

🔴 Blocker - Must fix before merge
🟡 Suggestion - Recommended improvement
💭 Nit - Optional polish

Review Checklist:

  • No hardcoded secrets
  • All inputs validated
  • SQL injection prevention
  • XSS prevention
  • CSRF protection
  • Auth/authorization verified
  • Rate limiting enabled
  • Error messages safe

📋 Core Principles (6 Mandatory)

1. Immutability (CRITICAL)

ALWAYS create new objects, NEVER mutate existing ones

WRONG:  modify(original, field, value) → changes in-place
CORRECT: update(original, field, value) → returns new copy

2. 80% Test Coverage

Minimum 80% coverage required for all code

Test Types (ALL required):
1. Unit tests - individual functions/components
2. Integration tests - API endpoints/database operations
3. E2E tests - critical user flows

3. Security First

Before ANY commit, verify:
- No hardcoded secrets (API keys, passwords, tokens)
- All user inputs validated
- SQL injection prevention (parameterized queries)
- XSS prevention (sanitized HTML)
- CSRF protection enabled
- Authentication/authorization verified
- Rate limiting on all endpoints
- Error messages don't leak sensitive data

4. TDD Workflow

RED → GREEN → REFACTOR → VERIFY

1. Write failing test
2. Write minimal implementation
3. Refactor for quality
4. Verify coverage and security

5. File Organization

MANY SMALL FILES > FEW LARGE FILES

- High cohesion, low coupling
- 200-400 lines typical, 800 max
- Extract utilities from large modules
- Organize by feature/domain, not by type

6. Agent Orchestration

Parallel execution, multi-perspective review

- Launch independent agents in parallel
- Use multiple agents for different perspectives
- Aggregate results for comprehensive analysis

🛠️ Tools & Scripts

Language Detector

python tools/language-detector.py --project .
python tools/language-detector.py --file file.ts

Language Switcher

python tools/language-switcher.py --list
python tools/language-switcher.py --set python
python tools/language-switcher.py --current

Hooks Adapter

# ecc-hooks-adapter.py
# PreToolUse/PostToolUse automation
# Automatically logs tool calls and analyzes results

Observer Manager

# ecc-observer-manager.py
# Manages observer lifecycle
# start/stop/status checks

📚 12 Language Supports

LanguageRulesSkills
TypeScriptcoding-style, hooks, patterns, security, testingtypescript-reviewer
JavaScriptcoding-style, hooks, patterns, security, testing-
Pythoncoding-style, hooks, patterns, security, testingpython-reviewer
Javacoding-style, hooks, patterns, security, testingjava-reviewer
Kotlincoding-style, hooks, patterns, security, testingkotlin-reviewer
Gocoding-style, hooks, patterns, security, testinggo-reviewer
Rustcoding-style, hooks, patterns, security, testingrust-reviewer
C++coding-style, hooks, patterns, security, testingcpp-reviewer
C#coding-style, hooks, patterns, security, testing-
PHPcoding-style, hooks, patterns, security, testing-
Perlcoding-style, hooks, patterns, security, testingperl-reviewer
Swiftcoding-style, hooks, patterns, security, testing-

🤝 30 ECC Agents

Engineering (22 agents)

  • architect - System architecture design
  • build-error-resolver - Build error resolution
  • code-reviewer - Code quality review
  • cpp-build-resolver / cpp-reviewer - C++ support
  • go-build-resolver / go-reviewer - Go support
  • java-build-resolver / java-reviewer - Java support
  • kotlin-build-resolver / kotlin-reviewer - Kotlin support
  • python-reviewer - Python code review
  • rust-build-resolver / rust-reviewer - Rust support
  • typescript-reviewer - TypeScript review
  • flutter-reviewer - Flutter review
  • database-reviewer - Database review
  • doc-updater / docs-lookup - Documentation
  • performance-optimizer - Performance optimization
  • refactor-cleaner - Code cleanup
  • pytorch-build-resolver - PyTorch support
  • harness-optimizer - Harness optimization
  • healthcare-reviewer - Healthcare domain review

Testing (2 agents)

  • e2e-runner - E2E test execution
  • tdd-guide - TDD workflow guidance

Project Management (2 agents)

  • chief-of-staff - Communication triage
  • loop-operator - Autonomous loop execution

Specialized (1 agent)

  • planner - Implementation planning

📖 Documentation

Design Documents

  • docs/superpowers/specs/2026-04-03-neural-network-system-design.md
  • ECC-FINAL-REPORT.md
  • ECC-USER-GUIDE.md

Integration Reports

  • ECC-VERIFICATION-COMPLETE.md
  • ECC-TEST-REPORT.md
  • ECC-AGENTS-VERIFICATION-TODO.md

Rules Directory

  • ~/.agents/rules/ (77 rule files)
  • common/ (10 files)
  • typescript/python/java/kotlin/go/rust/cpp/csharp/php/perl/swift/ (5 files each)
  • zh/ (11 files - Chinese translation)

🚀 Quick Start

1. Check Available Agents

openclaw agents list

2. Check Available Skills

openclaw skills list

3. Detect Project Language

python tools/language-detector.py --project .

4. Set Language Mode

python tools/language-switcher.py --set python

5. Start TDD Workflow

1. Call tdd-guide agent
2. Write failing test
3. Call engineering-python-reviewer (or language-specific)
4. Write minimal implementation
5. Run tests
6. Refactor
7. Call verification-before-completion

✅ Quality Gates

Before Commit

  • Tests passing
  • Coverage 80%+
  • Security scan clean
  • Code review approved
  • No hardcoded secrets
  • All inputs validated

Before Completion Claim

  • Fresh verification evidence
  • Test results attached
  • Coverage report attached
  • Security scan attached
  • Code review approved

Before Bug Fix

  • Root cause identified
  • 5 Whys completed
  • Fix tested
  • No regression verified

📊 Metrics

MetricTargetStatus
Agents30 ECC + existing✅ 211 total
Skills77 rules + existing✅ 164 total
Languages12✅ Activated
Iron Laws4✅ Embedded
Core Principles6✅ Embedded
Test Coverage80%+⭐ Required
Security ScanClean⭐ Required

🔧 Installation

ECC system already integrated into OpenClaw v3.4 - ECC Edition.

Files Location:

  • Agents: ~/.agents/skills/agency-agents/ecc-agents/ (30 files)
  • Rules: ~/.agents/rules/ (77 files)
  • Tools: tools/ and workspace/
  • Docs: workspace/ and docs/superpowers/

No additional installation required!

📝 Usage Examples

Example 1: Code Review

User: Review this Python code

Flow:
1. Call engineering-python-reviewer
2. Apply python-coding-standards rules
3. Check 4 iron laws compliance
4. Mark issues with 🔴🟡💭
5. Provide fix suggestions

Example 2: New Project

User: Create a new project

Flow:
1. language-detector.py detects language
2. Call planner agent for project structure
3. Call architect agent for architecture
4. Call tdd-guide agent for test setup
5. Apply language-specific rules

Example 3: Bug Fix

User: This feature has a bug

Flow:
1. Follow debugging iron law (investigate first)
2. Call debugging agent for analysis
3. Call language-specific reviewer for fix
4. Call testing agent for verification
5. Check test coverage

Example 4: Multi-language Project

User: This is a multi-language project

Flow:
1. language-detector.py detects all languages
2. language-switcher.py switches current language
3. Apply language-specific rules
4. Call language-specific reviewer
5. Check cross-language interfaces

🎯 Success Criteria

  • 30 ECC agents available
  • 77 rule files available
  • 12 language supports activated
  • 4 iron laws embedded
  • 6 core principles embedded
  • Language tools working
  • Hooks system running
  • New session test passed
  • All verifications complete

Status: ✅ PRODUCTION READY

📞 Support

Documentation:

  • ECC-FINAL-REPORT.md - Final integration report
  • ECC-USER-GUIDE.md - User guide
  • ECC-VERIFICATION-COMPLETE.md - Verification report

Version: OpenClaw v3.4 - ECC Edition
Integration Date: 2026-04-03
Integration Time: 2 hours 21 minutes
Test Pass Rate: 100%

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open in GitHubOpen in ClawHub

Related Skills

Related by shared tags or category signals.

Coding

CodeBuddy Coding

# CodeBuddy Coding Skill **版本：** 1.0.0 **创建时间：** 2026-03-31 **作者：** OpenClaw Team --- ## 📋 Skill 概述 **CodeBuddy Coding Skill** 是一个通用的 AI 编程能力扩展，让任何 OpenClaw agent 都能调用 CodeBuddy CLI 的强大功能。 ### 核心能力 - ✅ **AI 编程** - 代码生成、重构、调试、优化 - ✅ **文件操作** - 创建、修改、删除文件 - ✅ **命令执行** - 运行构建、测试、部署命令 - ✅ **进度监控** - 实时报告任务进度和状态 - ✅ **结构化输出** - JSON 格式的可解析输出 ### 适用场景 - **Developer Agent** - 编写代码、修复 Bug - **Architect Agent** - 生成项目脚手架 - **Tester Agent** - 编写测试用例 - **任何需要编程能力的 Agent** - 通用编程支持 --- ## 🚀 快速开始 ### 基本用法 ```javascript // 1. 加载 Skill const codebuddy = require('./skill'); // 2. 执行编程任务 const result = await codebuddy.execute({ task: '创建一个用户登录页面', context: { projectPath: '/path/to/project', techStack: 'Vue 3 + TypeScript' }, options: { outputFormat: 'json', permissionMode: 'bypassPermissions' } }); // 3. 获取结果 console.log(result.status); // 'success' console.log(result.filesModified); // ['src/views/Login.vue'] console.log(result.toolCalls); // [{tool: 'write_to_file', ...}] ``` ### 监听进度 ```javascript // 订阅进度事件 codebuddy.onProgress((progress) => { console.log(`进度: ${progress.percentage}%`); console.log(`当前任务: ${progress.currentTask}`); console.log(`已用时间: ${progress.elapsedTime}s`); }); ``` --- ## 🔧 配置说明 ### 环境要求 - **CodeBuddy CLI** v2.68.0+ - **Node.js** v16.0.0+ - **OpenClaw** coding-agent skill 框架 ### Skill 配置 ```json { "name": "codebuddy-coding", "version": "1.0.0", "type": "coding", "capabilities": [ "code-generation", "file-operations", "command-execution", "progress-monitoring" ], "dependencies": { "codebuddy-cli": ">=2.68.0" } } ``` --- ## 📚 API 文档 ### `execute(options)` 执行编程任务。 **参数：** ```typescript interface ExecuteOptions { task: string; // 任务描述 context?: { // 任务上下文 projectPath?: string; // 项目路径 techStack?: string; // 技术栈 files?: string[]; // 相关文件 }; options?: { // 执行选项 outputFormat?: 'json' | 'text'; // 输出格式 permissionMode?: 'default' | 'bypassPermissions'; // 权限模式 timeout?: number; // 超时时间（秒） }; } ``` **返回：** ```typescript interface ExecuteResult { status: 'success' | 'failed' | 'timeout'; filesModified: string[]; // 修改的文件列表 toolCalls: ToolCall[]; // 工具调用记录 reasoning: string[]; // 推理过程 duration: number; // 执行时长（秒） error?: string; // 错误信息 } ``` ### `onProgress(callback)` 订阅进度更新事件。 **参数：** ```typescript type ProgressCallback = (progress: { percentage: number; // 完成百分比 currentTask: string; // 当前任务描述 elapsedTime: number; // 已用时间（秒） estimatedTime?: number; // 预计剩余时间（秒） filesModified: string[]; // 已修改文件 toolCalls: number; // 已调用工具次数 }) => void; ``` ### `getStatus()` 获取当前任务状态。 **返回：** ```typescript interface TaskStatus { state: 'idle' | 'running' | 'completed' | 'failed'; taskId?: string; startTime?: Date; progress?: Progress; } ``` --- ## 🎯 使用示例 ### 示例1：创建新组件 ```javascript const codebuddy = require('./skill'); // 创建登录组件 const result = await codebuddy.execute({ task: '创建一个用户登录组件，包含用户名、密码输入框和登录按钮', context: { projectPath: '/path/to/vue-project', techStack: 'Vue 3 Composition API + TypeScript' } }); if (result.status === 'success') { console.log('组件创建成功！'); console.log('创建的文件:', result.filesModified); } ``` ### 示例2：修复 Bug ```javascript const codebuddy = require('./skill'); // 修复登录验证 Bug const result = await codebuddy.execute({ task: '修复用户登录时的验证逻辑，密码应该至少8位且包含数字和字母', context: { projectPath: '/path/to/project', files: ['src/views/Login.vue', 'src/utils/validator.ts'] } }); console.log('修复完成:', result.filesModified); ``` ### 示例3：监听长时间任务进度 ```javascript const codebuddy = require('./skill'); // 订阅进度 codebuddy.onProgress((progress) => { console.log(`[${progress.percentage}%] ${progress.currentTask}`); console.log(` 已修改 ${progress.filesModified.length} 个文件`); console.log(` 已执行 ${progress.toolCalls} 次操作`); console.log(` 用时 ${progress.elapsedTime}s`); }); // 执行长时间任务 const result = await codebuddy.execute({ task: '重构整个用户管理模块，使用更清晰的架构', context: { projectPath: '/path/to/project' }, options: { timeout: 600 // 10分钟超时 } }); ``` --- ## 🔍 进度监控原理 ### JSON 输出解析 CodeBuddy CLI 支持 `--output-format json` 输出结构化数据： ```bash codebuddy -p "任务描述" --output-format json --permission-mode bypassPermissions ``` **输出格式：** ```json { "status": "running", "tool_calls": [ { "tool": "write_to_file", "parameters": { "filePath": "src/Login.vue", "content": "..." }, "result": "success" } ], "files_modified": ["src/Login.vue"], "reasoning": [ "分析任务需求", "设计组件结构", "编写代码" ], "progress": { "percentage": 45, "current_task": "编写登录表单" } } ``` ### 进度解析流程 ```mermaid graph LR A[CodeBuddy CLI] -->|JSON Stream| B[Progress Monitor] B -->|Parse JSON| C[Progress Data] C -->|Emit Event| D[Event Callbacks] D -->|Update| E[Agent UI] ``` --- ## ⚙️ 高级配置 ### 自定义输出解析器 ```javascript const codebuddy = require('./skill'); // 自定义解析器 codebuddy.setOutputParser((jsonLine) => { // 自定义解析逻辑 return { percentage: jsonLine.progress?.percentage || 0, task: jsonLine.progress?.current_task || '处理中' }; }); ``` ### 超时和重试 ```javascript const result = await codebuddy.execute({ task: '复杂重构任务', options: { timeout: 1200, // 20分钟超时 retryCount: 3, // 失败重试3次 retryDelay: 5000 // 重试间隔5秒 } }); ``` --- ## 🐛 调试和日志 ### 启用详细日志 ```javascript const codebuddy = require('./skill'); // 启用调试模式 codebuddy.setDebugMode(true); // 所有 CLI 输出会被记录到控制台 const result = await codebuddy.execute({ task: '创建测试文件' }); ``` ### 查看执行日志 ```javascript // 获取最近的执行日志 const logs = codebuddy.getExecutionLogs(); console.log(logs); // [ // { time: '11:30:01', event: 'CLI_START', command: '...' }, // { time: '11:30:02', event: 'TOOL_CALL', tool: 'write_to_file' }, // { time: '11:30:05', event: 'CLI_END', status: 'success' } // ] ``` --- ## 🚨 错误处理 ### 错误类型 ```typescript enum CodeBuddyErrorType { CLI_NOT_FOUND = 'CLI_NOT_FOUND', // CodeBuddy CLI 未安装 INVALID_TASK = 'INVALID_TASK', // 无效的任务描述 TIMEOUT = 'TIMEOUT', // 执行超时 PERMISSION_DENIED = 'PERMISSION_DENIED', // 权限被拒绝 CLI_ERROR = 'CLI_ERROR' // CLI 执行错误 } ``` ### 错误处理示例 ```javascript try { const result = await codebuddy.execute({ task: '创建文件' }); } catch (error) { if (error.type === 'CLI_NOT_FOUND') { console.error('请先安装 CodeBuddy CLI'); } else if (error.type === 'TIMEOUT') { console.error('任务超时，请增加超时时间'); } else { console.error('执行失败:', error.message); } } ``` --- ## 📦 集成到 Agent ### Developer Agent 集成 ```javascript // developer/agent.js const codebuddy = require('codebuddy-coding'); class DeveloperAgent { async implementFeature(task) { // 使用 CodeBuddy 实现功能 const result = await codebuddy.execute({ task: task.description, context: { projectPath: this.projectPath, files: task.relatedFiles } }); return result; } } ``` ### Architect Agent 集成 ```javascript // architect/agent.js const codebuddy = require('codebuddy-coding'); class ArchitectAgent { async generateProjectScaffold(requirements) { // 使用 CodeBuddy 生成脚手架 const result = await codebuddy.execute({ task: `创建项目脚手架：${requirements}`, options: { permissionMode: 'bypassPermissions' } }); return result; } } ``` --- ## 🧪 测试 ### 运行测试 ```bash # 运行所有测试 npm test # 运行特定测试 npm test -- --grep "CLI Wrapper" ``` ### 测试覆盖 - ✅ CLI Wrapper 单元测试 - ✅ Progress Monitor 单元测试 - ✅ Integration 集成测试 - ✅ E2E 端到端测试 --- ## 📄 许可证 MIT License --- ## 🤝 贡献 欢迎提交 Issue 和 Pull Request！ --- ## 📞 支持 如有问题，请联系： - GitHub Issues: [OpenClaw Repository] - Email: support@openclaw.ai --- **让每个 Agent 都拥有 AI 编程能力！** 🚀

Archived SourceRecently Updated
--13770626440
Coding

anti-sycophancy

Three-layer sycophancy defense based on ArXiv 2602.23971. Use /anti-sycophancy install to deploy all layers, or manage individually via install-claude-code / install-openclaw / uninstall / status / verify. Layer 1: CC-only hook; Layer 2: SKILL (cross-platform); Layer 3: CLAUDE.md (CC) / SOUL.md (OC).

Archived SourceRecently Updated
--0xcjl
Coding

validation-rule-management

管理校验规则、规则组和校验场景的全流程操作。支持通过统一 CLI 工具快速执行 API 调用，自动处理参数解析、配置加载和错误提示。使用当用户需要进行校验规则管理、规则组维护、校验场景配置、启停操作或相关查询时，即使用户只说"帮我创建一条规则"或"查一下场景列表"也应触发。

Archived SourceRecently Updated
--12266601032
Coding

mcdonalds-skill

Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.

Archived SourceRecently Updated
--1052666