Loading...
Loading...
Found 82 Skills
Use after QA strategy and test-case synthesis to build the requirements-to-test traceability matrix, identify missing coverage and test blockers, and score readiness for QA execution. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.
Add ADR references to code for traceability. TRIGGERS - ADR traceability, code reference, document decision in code.
Make every number in the final PDF traceable to the exact code line that produced it. Uses \hypertarget/\hyperlink LaTeX commands and \num{formula} evaluated at compile time. Use for reproducibility and data integrity verification.
Generate architectural wikis with source code traceability. Creates comprehensive documentation including architecture overviews, module docs, data flow diagrams, and interactive static sites. Use when asked to document a codebase, generate architecture docs, create a wiki, or explain how a project is structured.
Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL verdict. The architecture equivalent of /design-review.
Analyze, prioritize, and document test cases in TMS (Jira/Xray) -- the bridge between manual QA and test automation. Use when creating Test/ATP/ATR artifacts, calculating ROI to choose which tests to automate, maintaining US-ATP-ATR-TC traceability, or repairing broken TMS links. Supports four scopes: module-driven (exhaustive module exploration), ticket-driven (QA-approved user story), bug-driven (regression TC for a closed bug), and ad-hoc/exploratory. Produces three outcomes per TC: Candidate (feeds test-automation), Manual (terminal), Deferred (terminal). Triggers on: document tests, create test cases in Jira/Xray, prioritize for automation, ROI analysis, which tests to automate, Candidate vs Manual, link ATP to ATR, fix TMS traceability, stage 4, turn this bug into a regression test. Do NOT use for writing test code (test-automation) or running suites (regression-testing).
Comprehensive project planning and documentation generator for software projects. Creates structured requirements documents, system design documents, and task breakdown plans with implementation tracking. Use when starting a new project, defining specifications, creating technical designs, or breaking down complex systems into implementable tasks. Supports user story format, acceptance criteria, component design, API specifications, and hierarchical task decomposition with requirement traceability.
Complete Problem-Based Software Requirements Specification methodology following Gorski & Stadzisz research. Use when you need to perform requirements engineering from business problems to functional requirements with full traceability.
Use when you need to generate or update `{FEATURE_DIR}/verification/usecase.md` (test cases) during the verification phase of the Spec Pack, and require AC traceability and a structure that supports automated script generation.
Manage feature manifests for code traceability. Use when creating new features, updating existing features, checking feature health, or exploring the feature-to-code relationship. Activates for manifest validation, feature creation, changelog updates, and traceability queries.
AI SDLC repository delivery-graph and evidence-freshness workflow. Use when an AI assistant needs to index lifecycle traceability, resolve end-to-end paths, report gaps or orphans, register evidence identity, propagate stale dependencies, or calculate fresh evidence coverage. Supports `--quick-flow` for deterministic local analysis and `--full-flow` for strict trace and evidence review.
Two-way traceability between commits and tickets. (A) When committing any change, make sure the commit message carries the ticket / work-item number — derive it from the user's words, the branch name, or the current task, ask if unknown (a commit-msg hook is bundled but install it only on explicit request). (B) When the user asks WHY code is the way it is — "why was this changed", "who decided this", "is this hardcode intentional", "ทำไมถึงแก้อันนี้", "มีเหตุผลป่าว" — trace the line through git blame/log to the commit, extract the ticket number from the message, fetch the ticket from the tracker (Azure DevOps, GitHub Issues, JIRA), INCLUDING downloading and reading attached images (requirements often live only in an annotated screenshot), and answer with commit + ticket evidence. Trigger on any commit request in a ticketed repo, on "install commit hook", and on any why-is-this-code-like-this / change-archaeology question — even when the user doesn't mention tickets.