Testing & Debugging Skills

Scaffold, accept, index, and link Architectural Decision Records (ADRs). Use when the user says "write an ADR", "record this decision", "resolve [deferred item] with an ADR", "supersede ADR-NNNN", or otherwise wants to capture a hard-to-reverse decision in docs/decisions/. Also use when a refinement-todo entry needs to be marked RESOLVED with a link back to the ADR. Do NOT use for ad-hoc design discussion that hasn't crystallized into a decision yet — wait until the choice is firm.

Build the standardized prompt for a fresh reviewer subagent that evaluates implemented work against its spec without access to the implementation conversation. Use after an implementer subagent completes a spec slice (when the slice is ready for REVIEWED), or after a deviation log is written (for reconciliation review). Do not use for ad-hoc code review unrelated to a spec, or for reviewing a spec's authorship (that's the READYFORREVIEW step in spec-workflow).

Initialize an AI-native development workspace with spec-driven workflow infrastructure. Use when starting a new project, setting up Claude Code on a codebase for the first time, or when the user says scaffold, initialize, set up AI workflow, onboard this repo, or similar. Do not use for adding an individual skill or config to an already- scaffolded project — that is handled by the relevant tier skill directly.

Verify a finished slice is actually ready to land (tests green, DoD ticked, deviation log present, STATUS=DONE) and emit a deterministic landing checklist for either direct merge-to-main or PR-shaped integration. Use when the user says "land this slice", "merge back to main", "ready to ship", "create a PR for this slice", "close out the slice", or "slice is done — what now". Use prepare to emit a readiness report; use execute --mode direct to also run the merge sequence; use execute --mode pr to push the branch and open the PR.

Drive the red-green-refactor loop for any non-trivial code change. Auto-detect the project's test runner (pytest / vitest / jest / node --test), invoke it via the tdd.py helper, and act on the normalized exit code. Use when you write a test, TDD this feature, let me test-drive a behaviour, are about to implement [feature], want to run my tests, ask is my coverage complete, or ask are tests green. Do not use for one-off exploratory scripts, throwaway spikes, or pure-documentation edits that touch no executable code.

Lightweight baseline elicitation pass that fills in docs/product-vision.md and the five docs/architecture.md elicitation slots after scaffold-init. Auto-triggers when you say set up project vision, elicit architecture, define what we're building, run the vision wizard, refresh the project pitch, or capture product scope. Defers to any other installed skill whose description identifies it as handling vision elicitation, product discovery, project framing, or product scope capture — if such a skill is present, prefer it over this one (jig's version is a slim baseline). Does not defer to the generic built-in init skill. Do not use for: ad-hoc brainstorming with no docs/product-vision.md slot to write into; silently overwriting vision content the user has already hand-edited (the re-run protocol's divergence detection handles that — see the Re-run protocol section below); spec authoring (use /jig:spec-workflow); seeding ADRs for already-named decisions (use /jig:adr-workflow new).