Name: qa
Author: fatihkan

Prompt file imported from fatihkan/badi (.claude/commands/qa.md). Copyright stays with the author.

QA sign-off command. Verifies a change against acceptance criteria, runs the test suite, probes edge cases, and issues a ship / no-ship verdict via the qa-lead agent.

Required Tools

Read (change, specs, acceptance criteria)
Grep / Glob (locate affected tests and behavior)
Bash (run the test suite, exercise the CLI/app)
Agent (delegate to qa-lead)

When to Use

After implementation, before /ship. Run this to get an evidence-backed verdict on whether the change is safe to release. Complements /review (which reads the diff) by actually executing and judging behavior.

Procedure

Step 1: Establish Acceptance Criteria

Derive checkable criteria from the spec, /eng-review plan, or the user's intent.
If criteria are unclear, state the assumptions being verified.

Step 2: Delegate to QA Lead

Launch the qa-lead agent. Ask it to:

Map the change to each acceptance criterion (PASS/FAIL).
Run the project's full test suite and capture real pass/fail counts.
Probe edge cases (empty, max, invalid, concurrent) and negative paths.
Check for regressions in adjacent features.
Smoke-test the primary user path.

Step 3: Collect Evidence

Ensure every PASS/FAIL cites the command run and its real output. A skipped check is reported as skipped; a flaky/failing test blocks SHIP.

Step 4: Issue the Verdict

SHIP — all criteria pass, suite green, no regressions.
SHIP WITH RISK — passes with a named, accepted risk.
NO-SHIP — blocking issues; list exactly what must be fixed.

Step 5: Record

Add the verdict and any blocking issues to the task board.
On NO-SHIP, route defects back to the implementing agent.

Output Format

Verdict (SHIP / SHIP WITH RISK / NO-SHIP)
Acceptance Criteria (each PASS/FAIL + evidence)
Test Run (pass/fail counts + quoted failures)
Edge & Regression Findings
Blocking Issues (if any)

Install qa and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

QA sign-off command. Verifies a change against acceptance criteria, runs the test suite, probes edge cases, and issues a ship / no-ship verdict via the qa-lead agent. # Required Tools - Read (change, specs, acceptance criteria) - Grep / Glob (locate affected tests and behavior) - Bash (run the test suite, exercise the CLI/app) - Agent (delegate to qa-lead) # When to Use After implementation, before `/ship`. Run this to get an evidence-backed verdict on whether the change is safe to release. Complements `/review` (which reads the diff) by actually executing and judging behavior. # Procedure ### Step 1: Establish Acceptance Criteria - Derive checkable criteria from the spec, `/eng-review` plan, or the user's intent. - If criteria are unclear, state the assumptions being verified. ### Step 2: Delegate to QA Lead Launch the **qa-lead** agent. Ask it to: - Map the change to each acceptance criterion (PASS/FAIL). - Run the project's full test suite and capture real pass/fail counts. - Probe edge cases (empty, max, invalid, concurrent) and negative paths. - Check for regressions in adjacent features. - Smoke-test the primary user path. ### Step 3: Collect Evidence Ensure every PASS/FAIL cites the command run and its real output. A skipped check is reported as skipped; a flaky/failing test blocks SHIP. ### Step 4: Issue the Verdict - **SHIP** — all criteria pass, suite green, no regressions. - **SHIP WITH RISK** — passes with a named, accepted risk. - **NO-SHIP** — blocking issues; list exactly what must be fixed. ### Step 5: Record - Add the verdict and any blocking issues to the task board. - On NO-SHIP, route defects back to the implementing agent. # Output Format - **Verdict** (SHIP / SHIP WITH RISK / NO-SHIP) - **Acceptance Criteria** (each PASS/FAIL + evidence) - **Test Run** (pass/fail counts + quoted failures) - **Edge & Regression Findings** - **Blocking Issues** (if any)

{ "prompt": "QA sign-off command. Verifies a change against acceptance criteria, runs the test suite, probes edge cases, and issues a ship / no-ship verdict via the qa-lead agent.\n\n# Required Tools\n- Read (change, specs, acceptance criteria)\n- Grep / Glob (locate affected tests and behavior)\n- Bash (run the test suite, exercise the CLI/app)\n- Agent (delegate to qa-lead)\n\n# When to Use\nAfter implementation, before `/ship`. Run this to get an evidence-backed verdict on whether the change is safe to release. Complements `/review` (which reads the diff) by actually executing and judging behavior.\n\n# Procedure\n\n### Step 1: Establish Acceptance Criteria\n- Derive checkable criteria from the spec, `/eng-review` plan, or the user's intent.\n- If criteria are unclear, state the assumptions being verified.\n\n### Step 2: Delegate to QA Lead\nLaunch the **qa-lead** agent. Ask it to:\n- Map the change to each acceptance criterion (PASS/FAIL).\n- Run the project's full test suite and capture real pass/fail counts.\n- Probe edge cases (empty, max, invalid, concurrent) and negative paths.\n- Check for regressions in adjacent features.\n- Smoke-test the primary user path.\n\n### Step 3: Collect Evidence\nEnsure every PASS/FAIL cites the command run and its real output. A skipped check is reported as skipped; a flaky/failing test blocks SHIP.\n\n### Step 4: Issue the Verdict\n- **SHIP** — all criteria pass, suite green, no regressions.\n- **SHIP WITH RISK** — passes with a named, accepted risk.\n- **NO-SHIP** — blocking issues; list exactly what must be fixed.\n\n### Step 5: Record\n- Add the verdict and any blocking issues to the task board.\n- On NO-SHIP, route defects back to the implementing agent.\n\n# Output Format\n- **Verdict** (SHIP / SHIP WITH RISK / NO-SHIP)\n- **Acceptance Criteria** (each PASS/FAIL + evidence)\n- **Test Run** (pass/fail counts + quoted failures)\n- **Edge & Regression Findings**\n- **Blocking Issues** (if any)", "variables": [], "notes": "QA sign-off command. Verifies a change against acceptance criteria, runs the test suite, probes edge cases, and issues a ship / no-ship verdict via the qa-lead agent.", "metadata": { "source": { "provider": "github-claude-commands", "repository": "https://github.com/fatihkan/badi", "path": ".claude/commands/qa.md", "ref": "9dda3a57e9fb2327c9c12eaf2b5414a1dbedc93b", "url": "https://github.com/fatihkan/badi/blob/9dda3a57e9fb2327c9c12eaf2b5414a1dbedc93b/.claude/commands/qa.md", "key": "fatihkan/badi/.claude/commands/qa.md" } } }

qa

About