team-skills

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - merge, PR, or cleanup

Use when task needs full spec→impl→test→review pipeline with CONFIRM_GOAL-HUMAN_ACCEPT human checkpoints and directed-graph rollback

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when code + tests exist and you need structured review + asset update

Use when starting a new feature, need SDD spec, or requirements are ambiguous

Use when requirements are fuzzy, need to discuss and form a plan before writing code

Use when receiving code review feedback, before implementing suggestions - requires technical verification, not performative agreement

Use when SDD exists and you need TDD implementation with 06-08 docs

Use when evaluating AI collaboration maturity of a project

Use when AI usage involves sensitive data, external services, or automated agents — produces security compliance audit report

Use when implementation exists and you need test matrix + coverage audit

Use when about to claim work is complete, fixed, or passing - requires running verification commands and confirming output before making any success claims

Use when starting any conversation with Team Skills - establishes how to find and use team skills, with skill selection matrix