
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when implementation is complete and all tests pass, to choose and execute the integration path: merge locally, push PR, keep as-is, or discard.
Use when porting a Claude Code skill to Pi/agentskills.io format. Covers frontmatter, tool references, cross-references, companion files, and subagent patterns.
Use after completing a session goal, or when the user asks to update or refine project docs, to distil session learnings back into docs/.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when reviewing an existing Pi skill for quality, spec compliance, or token efficiency.
Use when implementing any feature or bugfix, before writing implementation code
Use when starting any conversation or task, to determine which skills apply before responding or taking any action.
Use when creating or editing any Pi skill, or checking an existing skill's format for agentskills.io spec compliance and Pi content rules.
Use at the start of any task in a project to load existing context from docs/ before responding or planning.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Use before any creative work — creating features, building components, adding functionality, or modifying behavior — to explore intent, requirements, and design before implementation begins.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when starting feature work that needs isolation from the current workspace, or before executing an implementation plan.
Use when you have a spec or requirements for a multi-step task, before touching code
Use when writing or editing human-facing prose that needs clearer, more concise wording.