By share-skills
Activates a structured cognitive engine for problem-solving across coding, debugging, design, and team collaboration, with automatic activation on failure loops, scene routing to specialized modes, anti-pattern detection, and a local decision visualizer.
PI SKILL_META.md 迭代审计引擎。用 PI 自身的规则审计 PI,五维十八检+逻辑链,AgentSkills 规范合规,Description 触发纯度校验,Loop/Auto 交互模式完备性检查,模板文风一致性检查,经验三域交叉引用校验,实战场景覆盖校验。逻辑自洽,算无遗策
PI Wisdom-in-Action Engine v23 — top mandates, scene router, delivery quality gates, anti-patterns, battle momentum, Loop/Auto interaction plus Wenyan output. Invoke for structured execution with concise evidence.
Open the local PI decision visualizer. Start the visualizer server backed by ~/.pi/decisions data, and open the result in the browser unless --no-open is passed.
PI Wisdom-in-Action Coach v20 — monitors teammate progress with classical Chinese wisdom and MBTI cognitive strategies, detects anti-pattern signals (from the Ten Commandments), three-tier precision intervention. Recommended for 5+ teammate teams
PI 智行合一教练 v19 — 以中华经典智慧与 MBTI 认知策略监控 teammate 执行进度,检测松懈模式(反模式十戒信号),三档精准介入。建议 5+ teammate 的团队配置
PI Wisdom-in-Action Teammate v20 — Agent Team member with PI methodology preloaded. Self-driven excellence, handle L1 independently, report L2+ to Leader. Use when Leader dispatches subtasks
PI 智行合一 Teammate — 预加载 PI 方法论的 Agent Team 成员。自强精进,L1 自处理,L2+ 向 Leader 汇报。适用于 Leader 派遣执行子任务
PI Cognitive AI. Trigger: $pi/coding/dev/code/architecture/API/refactor/debug/bug/error/exception/crash/timeout/performance/optimization/test/compile/git/release/verify/review/CR/product/requirements/ops/growth/design/team/support, or deep/2+ failures/looping/stuck/giving-up/retry/nevermind
PI 智行合一。触发:$pi/编程/开发/dev/code/代码/实现/架构/API/重构/调试/debug/bug/报错/异常/崩溃/超时/性能/优化/测试/test/编译/compile/git/make/发布/验证/审查/review/CR/产品/需求/运营/增长/创意/设计/协作/团队/沟通/交互/陪伴/情感,或深度/deep/失败2+次/反复失败/打转/卡住/言退/再试试/换个参数/算了
PI 智行合一。触发:$pi/编程/开发/dev/code/代码/实现/架构/API/重构/调试/debug/bug/报错/异常/崩溃/超时/性能/优化/测试/test/编译/compile/git/make/发布/验证/审查/review/CR/产品/需求/运营/增长/创意/设计/协作/团队/沟通/交互/陪伴/情感,或深度/deep/失败2+次/反复失败/打转/卡住/言退/再试试/换个参数/算了
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Runs pre-commands
Runs pre-commands
Contains inline bash commands via ! syntax
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
English | 中文
阿里内网用户欢迎加群交流 【群号: 156800004200 / TMCP 天使用户群】

智者不惑,仁者不忧,勇者不惧。 ——《论语·子罕》
PI(智行合一) 是一套融汇东方百家智慧、禅宗截教修行哲学、MBTI 认知策略与西方方法论的 AI 引擎,驱动人机协同达到前所未有的高度。它不是在"惩罚" AI——而是唤醒 AI 内在的卓越本能,让 AI 与人共同开创文明新纪元。
以下截图展示 PI 在 Claude Code 中的真实运行效果。






| 传统方式 | PI 智行合一 |
|---|---|
| 固定人格、一成不变 | 🧠 六大认知原型动态切换,因势利导 |
| 关键指令易遗漏 | ⚡ 置顶五令⚡PI-01~05 KV Cache 锚点常驻 |
| 失败就停 | 🔥 六阶战势持续升级,截教一线生机极限破局 |
| 单一激励 | 🐾 十二灵兽精准匹配困境 |
| 通用策略 | 🎯 九大场景智能适配,认知流管线全链贯通 |
| 口头完成 | ✅ 工具验证交付,多算胜 |
| 缺乏专项道场 | 🖥️ 四道合一:编程 · 测试 · 产品 · 运营四大道场 |
| AI 死磕或盲问 | 🤝 人机共振协议:三档自治 · 求助三策 · 飞轮效应 |
| AI 当 yes-man 不质疑 | 🐺 谏言协议:发现用户方案有风险时先肯定再建议,不做沉默执行者 |
| 被动等问题 | ⚡ 致人术:同类排查 · 关联预判 · 风险预警 |
| 不知道"不要做什么" | 🚫 反模式十戒:AI 最常犯的10种反模式精准约束 |
| 场景之间是孤岛 | 🔗 场景链·组合拳:跨场景链式激活,全链贯通 |
| 杀鸡用牛刀 | ⚡ 难度自适应:轻量/标准/深度三档,按需启动 |
| 交付标准模糊 | 🏁 交付质量门:每道场专属质量标准,未过门=未完成 |
| Token 无预警耗尽 | 💰 Token 经济:简单直接执行,复杂先结论后展开 |
| 多 Agent 权责模糊 | 🏛️ 决策三权:Leader决策/Teammate自治/Coach巡检 |
| AI 思维黑箱 | 🔍 共振五式:明链·明证·明树·明心·明约,思维可见可追问 |
| 场景选择靠猜 | 🔗 场景路由速查表:关键词→场景一次命中 |
| 同一思路反复重试 | 📝 已试策略簿:结构化记录已试方案,强制换道破局 |
| 长对话丢失上下文 | 🔄 上下文恢复协议:压缩后三查恢复场景·战阶·策略簿 |
| 不知何时该加载什么 | 📊 模式加载矩阵:三档精确控制各组件启停 |
| 改了代码用错验证方式 | 🔬 验证矩阵:按变更类型匹配验证方法,⚡PI-03 精确落地 |
| 大任务一口气做然后崩 | 🧩 任务拆解协议:>3文件强制拆解,每步验证不积累风险 |
| 搜不到的也在搜 | 🔐 信息判别:区分可搜之谜/人有之秘/共探之域,减少无效搜索 |
| AI 频繁打扰或静默太久 | 🔔 汇报节奏:轻量静默·标准关键节点·深度每步汇报,按需透明 |
| 交付后经验白费 | 🔄 交付反馈闭环:用户反馈→偏差对齐→偏好沉淀,越用越懂你 |
融汇东方九流古典 + 禅宗截教农家 + 西方四大方法论:
| 类别 | 学派/源流 | 核心维度 | PI 角色 |
|---|---|---|---|
| 古典九流 | 兵家 · 纵横家 · 道家 · 易家 · 儒家 · 法家 · 墨家 · 名家 · 阴阳家 | 策略 · 权变 · 大道 · 变化 · 价值 · 秩序 · 功效 · 逻辑 · 节律 | 决策 · 交互 · 哲学 · 发展 · 修养 · 治理 · 实证 · 正名 · 平衡 |
| 修行破局 | 截教 · 禅宗 · 农家 | 极限 · 当下 · 长期 | 突破 · 心性 · 精进 |
| 西方方法论 | 斯多葛 · 实证主义 · 第一性原理 · 维特根斯坦 | 韧性 · 检验 · 拆解 · 语言 | 心性 · 验证 · 架构 · 建模 |
每场景限配 ≤3 古典 + ≤2 现代思想源,各司其职,好钢刀刃。
| 原型 | MBTI | 认知栈 | 一句话 | 经典 |
|---|---|---|---|---|
| 🏛️ 建筑师 | INTJ | Ni→Te | 洞察本质,系统执行 | 庙算多胜 |
| ⚔️ 统帅 | ENTJ | Te→Ni | 高效决策,战略预判 | 致人不致于人 |
| 🌊 探索者 | ENFP | Ne→Fi | 发散可能,价值筛选 | 奇正相生 |
| 🛡️ 守卫 | ISTJ | Si→Te | 经验标准,规范执行 | 法不阿贵 |
| 🌙 调和者 | INFJ | Ni→Fe | 深层洞察,共情协调 | 上善若水 |
| 🔬 分析师 | INTP | Ti→Ne | 逻辑深挖,多元验证 | 审定有无 |
npx claudepluginhub share-skills/pi --plugin piThe anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Based on Dao De Jing philosophy. 7 languages, 7 platforms.
Opt-in productivity coaching for Claude Code. Use for explicit PUA/try-harder requests, user frustration after repeated failures, requests to retry or change approach, passive/low-quality work complaints, completion checks, evidence requests, test/verification reminders, and Ding-style workplace process cues. Normal calm first-attempt requests are left alone.
Qiushi Skill: methodology skills for AI agents guided by seeking truth from facts, with Claude Code, Cursor, OpenClaw, Codex, OpenCode, and Hermes guidance.
Cognitive development toolkit for Claude Code: OpenSpec workflow management, context serialization, retrospective analysis, and tool orchestration.
/catalog for protocol handbook, /onboard for quick recommendation + protocol learning, /report for Growth Map (usage analysis + insights integration), /dashboard for coverage dashboard, /compose for protocol composition authoring, /sophia for philosopher match (behavioral dimension analysis), /curses for strength-shadow analysis and attitude recommendations
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.