Menu
Use after /finish to validate stories via curl (API) or browser (full-stack). Bugs found loop back through /tdd.
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.
Basé sur la classification professionnelle SOC
Use when implementation is complete and all tests pass. Verifies with fresh evidence, presents completion options (merge, PR, keep, discard), and cleans up.
Use when creating or updating a pull request. Analyzes the full diff against the base branch, writes a concise title and structured body, and creates or updates the PR via gh.
Interactive, phone-drivable idea→spec loop. The operator hands the host agent a raw idea; the agent routes it to the right repo, runs the FULL DECIDE phase (explore [track] → complexity → prd [product track] → architecture-diagram → architecture-review → stories → conflict-check → plan, tier-aware) in that repo, opens a spec PR there, and nudges that repo's daemon. Runs independently of any build/execution loop. Use when capturing and routing new work, NOT when building inside one repo (that's plain conduct).
Use after stories are written and conflict-check has passed clean. Converts user stories into a step-by-step implementation plan with 2-5 minute task granularity.
Use when executing an implementation plan with multiple tasks. Factory orchestration with three autonomy levels, quality gates, rework budgets, and audit trails.
Use when implementing any feature or bugfix. Five-step cycle: RED → DOMAIN → GREEN → DOMAIN → COMMIT. Enforces test-first development with domain integrity review at every phase boundary.
| name | manual-test |
| description | Use after /finish to validate stories via curl (API) or browser (full-stack). Bugs found loop back through /tdd. |
| enforcement | gating |
| phase | ship |
| standalone | false |
| requires | ["finish","verify-claims"] |
Validates that implemented stories actually work by exercising the running application. Automated tests verify code correctness; manual testing verifies the system works end-to-end as a user would experience it.
Correctness gate: a "story X passes" result is a claim. Per the /verify-claims protocol, a
pass is verified — you actually observed the response/behavior — never assumed from the code or
inferred from a green unit test. If a story was not actually exercised, do not claim it passed;
report it as untested rather than presenting an assumption as a result.
Runs AFTER /finish and BEFORE /retro.
Before starting manual testing, check the stories in .docs/stories/ for this feature:
rails console smoke test or script execution.| Indicator | Testing Method |
|---|---|
| API-only (no views) | curl commands against running server |
| Full-stack (views exist) | Browser automation via Chrome MCP or Capybara |
Ensure the application is running and accessible:
Rails:
# Start server in background
bin/rails server -d -p 3000
# Or if using Docker:
docker compose up -d
Node:
npm start &
# Or: npm run dev &
Always stop and restart the server before testing. A stale server from a prior session runs old code and gives false results. Kill any existing server process, then start fresh:
# Kill existing server (check common ports)
lsof -ti:3000 | xargs kill -9 2>/dev/null || true # Rails
lsof -ti:8000 | xargs kill -9 2>/dev/null || true # FastAPI/Django
lsof -ti:5173 | xargs kill -9 2>/dev/null || true # Vite
# Start fresh
After starting, verify it's up: curl -s http://localhost:3000/up (or health check endpoint).
For each story in .docs/stories/, execute the acceptance criteria manually using curl:
# Story: Create a short link (happy path)
curl -s -X POST http://localhost:3000/links \
-H "Content-Type: application/json" \
-d '{"link": {"original_url": "https://example.com"}}' | python3 -m json.tool
# Story: Expired link returns 410 (negative path)
curl -s -o /dev/null -w "%{http_code}" http://localhost:3000/abc123
# Expected: 410
For each story, record:
| Story | Criterion | Expected | Actual | Pass? |
|---|---|---|---|---|
| Create link | 201 with short_code | 201 + 6-char code | 201 + "xK9mR2" | PASS |
| Expired link | 410 Gone | 410 | 410 | PASS |
| Invalid URL | 422 with error | 422 | 500 Internal Server Error | FAIL |
Use browser automation (Chrome MCP if configured, otherwise manual Capybara-style):
Display results to the user in the conversation AND save the same table to
.pipeline/manual-test-results.md. The conductor's completion gate reads this
file to verify manual-test ran for the current feature — without it, the
step has no objective on-disk evidence and cannot pass. This is run evidence,
not a committed design artifact: it lives under .pipeline/ (gitignored) and
uses a stable filename.
Append, never overwrite. Each run of this skill adds a new
## Attempt N — <ISO timestamp> section to the file (create the file with
## Attempt 1 — … on the first run). The conductor's gate evaluates only the
LATEST attempt section, so a fixed old FAIL doesn't block you — but the history
of what earlier attempts found is preserved for audit. Rewriting or deleting a
previous attempt's rows destroys run evidence; do not do it.
Use this format (both in chat and in the file):
# Manual Test Results
**Server:** localhost:3000
**Tester:** Claude (automated curl) / User (browser)
## Attempt 1 — 2026-07-06T10:00:00Z
| Story | Criterion | Result | Notes |
|---|---|---|---|
| ... | ... | PASS/FAIL | ... |
### Bugs Found
1. **BUG-001:** Invalid URL returns 500 instead of 422 (story: create-link, negative path: invalid input)
2. **BUG-002:** ...
.pipeline/manual-test-results.md is gitignored, so it is never committed —
which is what the conductor's freshness check needs (the file's mtime must be
newer than the current session's start; a committed copy from a prior run
would defeat that).
Whitewash guard (#367): when the gate observes FAIL rows it records the current commit sha; a later attempt whose rows are all PASS is accepted only if new commits exist since that sha. Recording PASS without actually committing a fix will be refused by the gate — the fix in Step C below MUST land as commits before the re-verify attempt. In daemon runs, a manual_test that keeps failing is kicked back to the build step with the FAIL rows as evidence (bounded), then HALTs for a human if the bug survives the kickback budget.
Any FAIL result becomes a bug that loops back through /tdd:
Step A — Confirm the buggy code path is supposed to exist (the /debugging Phase 4
GATE). Manual-test surfaces defects on shipped code — read the governing APPROVED ADR/PRD for
the affected component first. If the buggy path violates or is superseded by an approved
decision, the fix is a conformance finding (kickback), not a patch — a bug on a condemned
path is a removal signal. This cheap design check precedes the expensive RED→fix→suite cycle.
Step B — If the cause is not obvious, discover it before fixing. A manual FAIL gives you the
symptom (e.g. "500 instead of 422"), not the cause. When you cannot point to the root cause
with confidence from the failure alone, do NOT guess a fix or a reproducing test — dispatch the
/debugging protocol (root cause before fix; no fixes without evidence) in a fresh sub-session,
handing it the failing story, the observed-vs-expected result, and any server output/logs. Come
back with an evidence-backed root cause, then proceed. Skip this step only when the cause is
genuinely self-evident from the failure.
Step C — Fix via TDD, now that the cause is known:
Do NOT proceed to /retro with known bugs. The manual test gate must be clean.
/finish → /manual-test → bugs found? → /debugging (discover cause, if not obvious) → /tdd (fix each bug) → /manual-test (re-verify) → /retro
The loop continues until all stories pass manual testing.
Stop the application server after testing:
# Rails
kill $(cat tmp/pids/server.pid)
# Docker
docker compose down
.pipeline/manual-test-results.md BEFORE
exiting — the completion gate reads this file; a run that tests everything but
records nothing fails the step