Plugin Claude Code
PI (Wisdom-in-Action) Engine v10 — Zero-question imperatives, ⚡PI-0105 pinned mandates, scene router, delivery quality gates, token economy, anti-pattern decalogue, scene chaining, four dojos, self-evolution.
Plugin Claude Code
PI (Wisdom-in-Action) Engine v10 — Name-Reality Alignment & Zero-Question Imperatives. ⚡PI-0105 pinned mandates, all-imperative directives, scene router, delivery quality gates, token economy. 16 wisdom traditions, MBTI cognitive strategies, anti-pattern decalogue, scene chaining, four dojos. 16+ platforms.
Cursor rule Cursor
PI Visualizer usage in Cursor (local offline + optional live preview).
Cursor rule Cursor
A set of Chinese-language rules for an agent that treats the user as a collaborative partner. It requires checking information before acting, verifying changes, showing evidence, and keeping responses focused.
Instructions file
A set of internal development and evaluation instructions for a project called pi. It defines required workflows, benchmark commands, quality gates, and how changes to skills should be synchronized.
Agent
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.
Agent
A Chinese-language agent-team coach role that monitors teammates, detects repeated working problems, and gives staged feedback. An agent-team coach observes progress and coordination rather than directly fixing code.
Agent
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.
Agent
A Chinese-language role guide for a PI team member who carries out delegated tasks and reports progress to a team leader. It defines task levels, investigation steps, failure tracking, and reporting formats.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
A Chinese-language set of instructions for running coding-agent tasks as a disciplined workflow. It covers task routing, investigation depth, iterative work, verification, and several types of project work.
Skill Claude CodeCodex
A Chinese-language set of instructions for running coding-agent tasks as a disciplined workflow. It covers task routing, investigation depth, iterative work, verification, and several types of project work.
Command
An audit command for improving and checking a skill's instruction files and related copies.
Command
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.
Command
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.
Cursor rule
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.
Hook
Runs when you submit a prompt, before the agent sees it, executing capture-prompt.sh via bash. From share-skills/pi.
Hook
Runs before the context is compacted, executing pre-compact.sh via bash. From share-skills/pi.
Hook
Runs when the agent finishes a response, executing capture-decision.sh via bash. From share-skills/pi.
Hook
Runs after a tool call finishes for Bash tool calls, executing capture-tool-result.sh via bash. From share-skills/pi.
Hook
Runs when a tool call fails for Bash tool calls, executing capture-tool-result.sh via bash. From share-skills/pi.
Hook
Runs when a subagent starts, executing capture-subagent.sh via bash. From share-skills/pi.
Hook
Runs when a subagent finishes, executing capture-subagent.sh via bash. From share-skills/pi.