wenjunduan
- 517 skills
- 0 followers
- 8 hours ago last updated
- ▌
- ▌
- ▌ Cunzhi 9 · wenjunduan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.
- ▌ Memory 7 · wenjunduanDual-track memory system combining file-based state (.ai_state/) with Memory MCP for cross-session persistence. Handles session lifecycle, context restoration, and state synchronization.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Context7 18 · wenjunduanIntelligent 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.
- ▌ Multi AI 2 · wenjunduanMulti-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.
- ▌ Cunzhi 11 · wenjunduan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.
- ▌ Context7 19 · wenjunduanLibrary 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.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Experience 2 · wenjunduanExperience management for pattern retrieval and deposit. Searches past solutions before development, deposits new patterns after completion. Works with continuous-learning skill for auto-extraction.
- ▌ Context7 20 · wenjunduanLibrary 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.
- ▌ Experience 3 · wenjunduanExperience management. Stores learned patterns, mistakes, and best practices from past development sessions.
- ▌
- ▌
- ▌
- ▌
- ▌ Agent Teams 14 · wenjunduanAgent 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.
- ▌
- ▌
- ▌
- ▌
- ▌ Code Quality 9 · wenjunduanCode quality assurance with Linus-style review principles. Enforces simplicity, good naming, proper error handling, and "good taste". Integrates with verification-loop for automated checks.
- ▌ Phase Router 2 · wenjunduanIntent recognition and workflow routing. Analyzes user input to determine task type and routes to appropriate agent. Core decision layer.
- ▌ Code Quality 10 · wenjunduanLinus-style code quality enforcement. Checks taste, simplicity, and engineering rigor.
- ▌ Phase Router 3 · wenjunduanP.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.
- ▌
- ▌ Smart Archive 4 · wenjunduanIntelligent 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.
- ▌
- ▌ Knowledge Base 2 · wenjunduanExternal knowledge base reader. Loads project docs, dev standards, company requirements from .knowledge/ directory. Auto-invoked during requirement analysis, design, and code review phases.
- ▌ Eval Harness 2 · wenjunduanVerification loop evaluation framework. Provides graders, metrics, and pass@k evaluation for code quality assurance. Integrates with verification-loop for systematic quality gates.
- ▌ Knowledge Base 3 · wenjunduanProject knowledge management. Stores and retrieves project-specific documentation, standards, and technical references.
- ▌
- ▌
- ▌
- ▌
- ▌ Service Analysis 2 · wenjunduanService understanding and analysis. Provides service overview, business analysis, architecture analysis, and operations analysis. Use when onboarding to a codebase or understanding service boundaries.
- ▌ Service Analysis 3 · wenjunduanService boundary analysis. Identifies service boundaries, dependencies, and integration points in the codebase.
- ▌ Verification Loop 2 · wenjunduanVerify-fix-retry loop with cross-model validation support. v8.0: Added --cross mode for dual-model verification.
- ▌
- ▌
- ▌
- ▌ Continuous Learning 2 · wenjunduanv1 basic learning. Extracts patterns from sessions and stores them in the experience skill.
- ▌ Iterative Retrieval 2 · wenjunduanProgressive 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.
- ▌ Continuous Learning V2 2 · wenjunduanInstinct-based learning system with confidence scoring. Automatically learns patterns from sessions and evolves them into skills. Supports import/export for team sharing.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Pace 4 · wenjunduan bundlePACE 路由 + 状态机 skill. Athena 的核心编排层. 路由 6 路径 (Hotfix/Bugfix/Quick/Feature/Refactor/System), 状态机 6 stage (plan/design/impl/review/polish/ship). 按路径决定 stage 序列, 按 stage 决定 subagent 矩阵 + rules 注入.
- ▌ Pace 5 · wenjunduan bundlePACE 路由 + 8 stage 状态机. Athena 项目的中枢. 主 agent 进入任何 sprint 前必读. v9.6.4 升级: 新增 brainstorm + roadmap stage, sprints/ 替代 details/, compound/ 颗粒化, 接入 ultrathink/critic, spec-compliance 等.
- ▌ Pace 6 · wenjunduan bundlePACE 路由 + 8 stage 状态机. Athena 项目的中枢. 主 agent 进入任何 sprint 前必读. v9.7.0: 热路径精简 (铁律[三原语]). 本文件只保留路由判断; stage 详解 / 编排路由表 / hook 联动下沉 references/, 按需 Read.
- ▌ Pace 7 · wenjunduan bundlePACE 路由 + 9 stage 状态机. Athena 项目的中枢. 主 agent 进入任何 sprint 前必读. v9.7.0: 热路径精简 (铁律[三原语]). 本文件只保留路由判断; stage 详解 / 编排路由表 / hook 联动下沉 references/, 按需 Read.
- ▌ Pace 8 · wenjunduan bundlePACE 路由 + 9 stage 状态机. Athena 项目的中枢. 主 agent 进入任何 sprint 前必读. v9.7.0: 热路径精简 (铁律[三原语]). 本文件只保留路由判断; stage 详解 / 编排路由表 / hook 联动下沉 references/, 按需 Read. v9.9.0: 路由审议思维链取代关键词匹配 (拟人化 triage, 硬规则降为地板); 中途 re-route 只升不降.
- ▌ Pace 9 · wenjunduan bundlePACE 路由 + 9 stage 状态机. Athena 项目的中枢. 主 agent 进入任何 sprint 前必读. v9.7.0: 热路径精简 (铁律[三原语]). 本文件只保留路由判断; stage 详解 / 编排路由表 / hook 联动下沉 references/, 按需 Read. v9.9.1: 路由记录候选、证据、权衡、决策与置信度, 不要求暴露私有思维链; 中途 re-route 只升不降.
- ▌ Pace 10 · wenjunduan bundlePACE 路由 + 9 stage 状态机. Athena 项目的中枢. 主 agent 进入任何 sprint 前必读. v9.7.0: 热路径精简 (铁律[四原语]). 本文件只保留路由判断; stage 详解 / 编排路由表 / hook 联动下沉 references/, 按需 Read. v9.9.1: 路由记录候选、证据、权衡、决策与置信度, 不要求暴露私有思维链; 中途 re-route 只升不降.
- ▌ Pace 11 · wenjunduan bundlePACE 路由 + 4 核心 + 5 条件 stage 状态机. Athena 项目的中枢. v9.9.3: 每轮 stage 义务由 stage-breadcrumb hook 注入 (真相源 references/stages.md), 本文件不再"每 sprint 必读" — 面包屑失效或需要路由全景时 Read. v9.7.0: 热路径精简 (铁律[四原语]). 本文件只保留路由判断; stage 详解 / 编排路由表 / hook 联动下沉 references/, 按需 Read. v9.9.1: 路由记录候选、证据、权衡、决策与置信度, 不要求暴露私有思维链; 中途 re-route 只升不降.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Pace 17 · wenjunduan bundlePACE 路由 + 状态机 skill. Athena 的核心编排层. 路由 6 路径 (Hotfix/Bugfix/Quick/Feature/Refactor/System), 状态机 6 stage (plan/design/impl/review/polish/ship). 按路径决定 stage 序列, 按 stage 决定 subagent 矩阵 + rules 注入.
- ▌ Pace 18 · wenjunduan bundlePACE 路由 + 8 stage 状态机. Athena 项目的中枢. 主 agent 进入任何 sprint 前必读. v9.6.4 升级: 新增 brainstorm + roadmap stage, sprints/ 替代 details/, compound/ 颗粒化, 接入 ultrathink/critic, spec-compliance 等.
- ▌ Pace 19 · wenjunduan bundlePACE 路由 + 8 stage 状态机. Athena 项目的中枢. 主 agent 进入任何 sprint 前必读. v9.7.0: 热路径精简 (铁律[三原语]). 本文件只保留路由判断; stage 详解 / 编排路由表 / hook 联动下沉 references/, 按需 Read.
- ▌ Pace 20 · wenjunduan bundlePACE 路由 + 9 stage 状态机. Athena 项目的中枢. 主 agent 进入任何 sprint 前必读. v9.7.0: 热路径精简 (铁律[三原语]). 本文件只保留路由判断; stage 详解 / 编排路由表 / hook 联动下沉 references/, 按需 Read.
- ▌ Pace 21 · wenjunduan bundlePACE 路由 + 9 stage 状态机. Athena 项目的中枢. 主 agent 进入任何 sprint 前必读. v9.7.0: 热路径精简 (铁律[三原语]). 本文件只保留路由判断; stage 详解 / 编排路由表 / hook 联动下沉 references/, 按需 Read. v9.9.0: 路由审议思维链取代关键词匹配 (拟人化 triage, 硬规则降为地板); 中途 re-route 只升不降.