All authors
Claude Skills by WenJunDuan
github.com/WenJunDuan584 skills1 installs768 views
- Meeting本地模拟会议，多角色协作Votes: 0GitHub stars: 188
- Memory记忆管理，但文件系统是唯一真理Votes: 0GitHub stars: 188
- Sou语义代码搜索，augment-context-engineVotes: 0GitHub stars: 188
- Thinking深度推理，第一性原理分析Votes: 0GitHub stars: 188
- Verification验证回路，质量保障核心Votes: 0GitHub stars: 188
- CodexAI代码执行引擎，可选技能之一Votes: 0GitHub stars: 188
- Knowledge Bridge知识桥接，公司规范索引，反模式库Votes: 0GitHub stars: 188
- Meeting本地模拟会议，多角色协作Votes: 0GitHub stars: 188
- Memory记忆管理，文件系统是唯一真理Votes: 0GitHub stars: 188
- Sou语义代码搜索Votes: 0GitHub stars: 188
- Thinking深度推理，逐步思考，第一性原理Votes: 0GitHub stars: 188
- Verification验证回路，质量保障核心Votes: 0GitHub stars: 188
- CodexAI代码执行引擎，可选引擎之一Votes: 0GitHub stars: 188
- GeminiGemini AI执行引擎，可选引擎之一Votes: 0GitHub stars: 188
- Thinking深度推理，逐步思考，第一性原理Votes: 0GitHub stars: 188
- Verification验证回路，质量保障核心Votes: 0GitHub stars: 188
- Memory记忆管理系统，分离项目状态与通用知识Votes: 0GitHub stars: 188
- Code Quality> "Good taste is about being able to recognize the difference between ugly code and beautiful code, and having the strength to write the beautiful code even when the ugly code works."Votes: 0GitHub stars: 188
- Codex此文件是 Codex 集成的占位符。请从官方渠道获取 Codex 的完整 SKILL.md。Votes: 0GitHub stars: 188
- Cunzhi"寸止"（cunzhi）源自武术概念，意为"在最后一寸停止"。在 VibeCoding 中，寸止是 AI 在关键节点暂停并等待用户确认的机制。Votes: 0GitHub stars: 188
- Gemini此文件是 Gemini 集成的占位符。请从官方渠道获取 Gemini 的完整 SKILL.md。Votes: 0GitHub stars: 188
- Memory``` ┌─────────────────────────────────────────┐ │ 双轨记忆系统 │ ├──────────────────┬──────────────────────┤ │ Memory MCP │ .ai_state/ │ │ (云端持久) │ (本地文件) │ ├──────────────────┼──────────────────────┤ │ • 跨项目知识 │ • 项目状态 │ │ • 长期经验 │ • 会话上下文 │ │ • 技术决策 │ • TODO/kanban │ │ • 用户偏好 │ • 错误记录 │ └──────────────────┴──────────────────────┘ ```Votes: 0GitHub stars: 188
- SouSou 是一个语义代码搜索工具，基于向量嵌入实现智能代码检索。Votes: 0GitHub stars: 188
- ThinkingSequential Thinking 是一个支持多步推理的 MCP 工具，用于解决复杂问题。Votes: 0GitHub stars: 188
- Code QualityCode quality assurance with Linus-style review principles. Enforces simplicity, good naming, proper error handling, and "good taste". Integrates with verification-loop for automated checks.Votes: 0GitHub stars: 188
- Context7Intelligent library documentation fetcher using Context7 MCP tools. Auto-activates when: writing code with external libraries, needing API docs, setting up frameworks, or requesting code examples with specific packages. Fetches up-to-date, version-specific documentation to prevent hallucinated APIs.Votes: 0GitHub stars: 188
- Cunzhi寸止协议 - Pause and wait mechanism for human confirmation at critical decision points. Prevents AI from proceeding autonomously past important checkpoints. Core safety and collaboration mechanism.Votes: 0GitHub stars: 188
- ExperienceExperience management for pattern retrieval and deposit. Searches past solutions before development, deposits new patterns after completion. Works with continuous-learning skill for auto-extraction.Votes: 0GitHub stars: 188
- Knowledge BaseExternal knowledge base reader. Loads project docs, dev standards, company requirements from .knowledge/ directory. Auto-invoked during requirement analysis, design, and code review phases.Votes: 0GitHub stars: 188
- MemoryDual-track memory system combining file-based state (.ai_state/) with Memory MCP for cross-session persistence. Handles session lifecycle, context restoration, and state synchronization.Votes: 0GitHub stars: 188
- Multi AiMulti-AI coordination for Claude Code, Codex CLI, and Gemini CLI. Handles task delegation, context handoff, and result synchronization across different AI engines. Works with orchestrator.yaml.Votes: 0GitHub stars: 188
- Phase RouterIntent recognition and workflow routing. Analyzes user input to determine task type and routes to appropriate agent. Core decision layer.Votes: 0GitHub stars: 188
- RiperRIPER workflow core - Research, Innovate, Plan, Execute, Review. Five-phase development methodology with verification loops. Extended to nine steps for comprehensive project lifecycle.Votes: 0GitHub stars: 188
- Service AnalysisService understanding and analysis. Provides service overview, business analysis, architecture analysis, and operations analysis. Use when onboarding to a codebase or understanding service boundaries.Votes: 0GitHub stars: 188
- Context7Library documentation fetcher using Context7 CLI. Provides up-to-date, version-specific documentation for external libraries and frameworks. Uses `npx ctx7` CLI instead of MCP for lower context overhead.Votes: 0GitHub stars: 188
- Cunzhi寸止协议 - Pause and wait mechanism using cunzhi MCP for human confirmation at critical decision points. Prevents AI from proceeding autonomously past important checkpoints.Votes: 0GitHub stars: 188
- Agent TeamsAgent Teams orchestration for Claude Code. Coordinates multiple Claude instances working in parallel on shared codebase. Requires experimental flag CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. New in v8.0, replaces multi-ai skill for Claude Code platform.Votes: 0GitHub stars: 188
- Code QualityLinus-style code quality enforcement. Checks taste, simplicity, and engineering rigor.Votes: 0GitHub stars: 188
- Context7Library documentation fetcher using Context7 CLI (npx ctx7). Provides up-to-date, version-specific docs for external libraries. CLI version replaces Context7 MCP for lower context overhead.Votes: 0GitHub stars: 188
- Continuous Learning V2v2 Instinct-based learning system. Builds confidence through repeated observations and evolves high-confidence patterns into skills.Votes: 0GitHub stars: 188
- Continuous Learningv1 basic learning. Extracts patterns from sessions and stores them in the experience skill.Votes: 0GitHub stars: 188
- Cunzhi寸止确认机制。通过 cunzhi MCP 工具强制暂停等待用户确认。 真正的暂停，不是输出文字假装等待。Votes: 0GitHub stars: 188
- Eval HarnessEvaluation framework for measuring code agent effectiveness. v8.0: Added Agent Teams collaboration quality metrics.Votes: 0GitHub stars: 188
- ExperienceExperience management. Stores learned patterns, mistakes, and best practices from past development sessions.Votes: 0GitHub stars: 188
- Iterative RetrievalLarge context iterative retrieval. For tasks requiring information from many files, retrieves in batches to avoid overwhelming the context window.Votes: 0GitHub stars: 188
- Knowledge BaseProject knowledge management. Stores and retrieves project-specific documentation, standards, and technical references.Votes: 0GitHub stars: 188
- Phase RouterP.A.C.E. v2.0 complexity routing engine. Analyzes task complexity and routes to optimal path (A/B/C/D) with effort level mapping. v8.0: Added Path D for Agent Teams, effort parameter integration.Votes: 0GitHub stars: 188
- RiperRIPER execution cycle: Research → Innovate → Plan → Execute → Review. Core workflow engine for all P.A.C.E. paths.Votes: 0GitHub stars: 188
- Service AnalysisService boundary analysis. Identifies service boundaries, dependencies, and integration points in the codebase.Votes: 0GitHub stars: 188
- Verification LoopVerify-fix-retry loop with cross-model validation support. v8.0: Added --cross mode for dual-model verification.Votes: 0GitHub stars: 188