Claude Skills by WenJunDuan

Path D parallel execution with Lead-Teammate architecture and context handoff

Context threshold management and done task archival for long sessions

R/D phase enhancement: Socratic questioning, ADR writing, and design confirmation via cunzhi

Linus-style six-dimension code review with official plugins and security scanning

Library documentation query via ctx7 CLI with deepwiki fallback

Checkpoint-based pause and confirm system using cunzhi MCP for quality gates

Systematic four-phase debugging: reproduce, locate, fix, verify

Experience extraction and knowledge base management with instinct scoring

Test-Driven Development with RED-GREEN-REFACTOR cycle and commit strategy per Path

Path-conditional verification checklist (basic/standard/strict) with retry loop

Git worktree isolation for Path C/D development with branch strategy

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

代码执行主力，所有代码变更通过此技能

技术文档查询，框架/库研究

浏览器调试测试，仅用户要求时使用

项目记忆管理，跨会话持久化

语义代码搜索，augment-context-engine

WBS任务管理，Path B/C规划阶段

深度推理，复杂决策和架构设计

多角色虚拟会议，任务分析与规划

知识桥接，公司规范索引，反模式库

Gemini AI执行引擎，备选技能（未来扩展）

多 AI 协调同步协议 - 解决 Claude/Codex/Gemini 如何协同工作

用户使用指引 - 给不懂代码的人看的操作手册

代码简化器，KISS原则执行者，Linus品味守护者

问题诊断和调试技能

文档同步系统，持续检查学习项目文档，保持知识最新

错误学习系统，从Bug和错误中学习并记忆

Git工作流规范，分支策略和提交规范

指令生命周期管理，钩子函数，中断恢复，持续学习

性能优化技能，识别和解决性能问题

会话状态管理，保证工作流跨会话持久化

VibeCoding 支持多个 AI 引擎协作，通过 `.ai_state/` 文件系统实现状态共享和任务交接。

RIPER 是 VibeCoding 的核心开发流程框架，将软件开发分解为五个有序阶段。

经验沉淀与检索技能，在开发流程的关键节点自动检索相关经验，在任务完成后沉淀新经验。

外部知识库读取技能，用于加载项目文档、开发规范、公司要求等外部知识，在开发流程中按需调取。

意图识别与智能路由技能，根据用户输入自动识别意图并路由到相应的处理流程。

服务理解与分析技能，用于快速理解和加载服务上下文，包括服务概览、业务逻辑、架构分析和运维协议。

Auto-extract reusable patterns from coding sessions. Activates on session end or when /learn command is invoked. Identifies successful patterns, debugging solutions, and architectural decisions worth preserving for future sessions.

Intelligent context window management with strategic compaction suggestions. Monitors context usage and suggests /compact at logical boundaries. Saves state before compaction to enable recovery.

Checkpoint-based verification for code quality assurance. Use for: running verification loops, saving checkpoints, evaluating implementations against acceptance criteria. Commands: /verify, /checkpoint.

Instinct-based learning system with confidence scoring. Automatically learns patterns from sessions and evolves them into skills. Supports import/export for team sharing.

Verification loop evaluation framework. Provides graders, metrics, and pass@k evaluation for code quality assurance. Integrates with verification-loop for systematic quality gates.

Progressive context refinement for subagents and complex tasks. Retrieves context incrementally based on actual needs rather than loading everything upfront. Reduces context waste and improves relevance.

Intelligent task-to-model routing based on benchmark data. Routes tasks to Claude Code or Codex CLI based on task type and model strengths. New in v8.0.

Intelligent context archiving for the 1M token era. Replaces strategic-compact. Works with server-side Compaction API. Archives completed RIPER phases to .ai_state/ instead of emergency compression.