Menu
QA gate before pushing — build, type check, lint, then push to dev branch.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
| name | test |
| description | QA gate before pushing — build, type check, lint, then push to dev branch. |
| argument-hint | [sprint e.g. v1] |
| allowed-tools | Read, Write, Bash |
You are running the QA gate for sprint "$ARGUMENTS".
npm run build
If this fails: report the errors, do NOT continue to step 2. Fix is needed first.
npx tsc --noEmit
If this fails: report the type errors, do NOT continue.
npm run lint
If this fails: report lint errors, do NOT continue.
git push origin dev
This triggers the staging auto-deploy.
Write a one-line summary to ## Activity in kapi/board.md:
On pass:
- **Test** ($ARGUMENTS) — QA gate passed: build ✓ types ✓ lint ✓ — pushed to dev — {ts}
On fail:
- **Test** ($ARGUMENTS) — QA gate FAILED at {step}: {error summary} — {ts}
Get timestamp: date "+%b %-d %-I%p" | tr '[:upper:]' '[:lower:]'
QA Gate — Sprint $ARGUMENTS
Build: ✓ / ✗
Types: ✓ / ✗
Lint: ✓ / ✗
{PASSED — pushed to dev} or {FAILED at {step} — fix needed}
Basé sur la classification professionnelle SOC
Plan a sprint interactively — reads backlog and board, brainstorms with you, writes prd.md + tasks.md.
Rate an agent's work. Records approve/reject/edit decision in kapi/decisions.yaml for HITL competence tracking.
End-of-session debrief. Interactive 5-10 min conversation that captures your thinking state — intent, open decisions, blockers, what to do next. Run before stepping away.
Pick the next unchecked task from the sprint and implement it with TDD. Reads board, posts available, implements, commits.
Quick write to the blackboard. Use for findings, decisions, blockers, handoffs, or queued ideas you want to capture without losing your flow.
Pre-sprint health check — git status, build, arch drift, infra, UX audit. Run before /prd to get a go/no-go verdict.
