Menu
QA — final verdict. Run the suite, check critical-path coverage vs target, write a PASS/NEEDS-WORK report.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Domain Engineering diagnostic — shows what the classifier decides for an objective (CMIS/DAS/profile/skills/mode). Observation-only; never mutates or blocks.
Business-driven methodology entry point — classify (intake), create/advance an Operation or Business work context, and drive the intake → operation → nested-workflow flow. Host-neutral; dry-run by default.
Workflow Navigator — shows the current phase, deliverables, and next commands for an ADR-0057 workflow. Read-only; never mutates state.
Start a focused session on one objective — locks scope, blocks opportunistic refactors.
Deterministic QA gate (ADR-0055) — run the project suite; green + complete acceptance criteria ⇒ qa-approve testing cards into conclusion; red ⇒ report (and qa-reject only attributable failures).
L6 — autonomous feature pipeline. Drives the full squad: design → implement → review → test → log. Checkpoints can be manual or automatic.
| name | source-command-qa-qa-signoff |
| description | QA — final verdict. Run the suite, check critical-path coverage vs target, write a PASS/NEEDS-WORK report. |
Use this skill when the user asks to run the migrated source command qa-signoff.
Act as qa-orchestrator and produce the final QA verdict.
contextkit/config.json → qa.criticalPaths and qa.coverageTarget.criticalPaths covered (happy + failure modes), not just the easy
lines?coverageTarget (where measurable)?visual-test.mjs status), did the visual suite
pass? An unintended screenshot diff is a NEEDS-WORK (have design-team confirm
intentional changes before refreshing baselines)./log-session).This is advisory by default — it informs /close-version, it doesn't hard-block.
Treat a NEEDS-WORK on a critical path as a real blocker worth fixing first.
Run the test suite through the compact runner so only a bounded summary enters context, not the full log:
node contextkit/tools/scripts/economy/run-compact.mjs <your test command>
The full log is written to runs/<id>/ (gitignored); the exit code is the only
pass/fail source. Skip only if economy.compaction.enabled is false in config.
If the host exposes quota/usage data during the run, write a metadata-only quota
snapshot so /token-report has real data:
node contextkit/tools/scripts/economics/quota-snapshot.mjs --write --source qa-signoff --capture-method manual <quota flags>
If quota data is not visible, report quota-snapshot skipped: no host quota data.