From csdlc
Run QA against acceptance criteria for a completed story (CSDLC Step 5). Verify each criterion, test edge cases, provide evidence. Separate from implementation — dedicated QA step. Use when the user says "qa", "test this", "verify", "does it work", or after /review passes.
npx claudepluginhub danhannah94/claymore-plugins --plugin csdlcThis skill uses the workspace's default tool permissions.
QA this deliverable: **$ARGUMENTS**
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
QA this deliverable: $ARGUMENTS
Step 5 is a dedicated QA step, separate from implementation. Don't combine with the review (Step 4). The review checks "did the intern follow the spec?" QA checks "does it actually work?"
Identify the deliverable. Same as /review — PR URL, branch, or story ID.
Load acceptance criteria. From the story doc (Foundry or local).
Verify each criterion independently. For every acceptance criterion:
Test beyond the criteria. Look for:
Produce the QA report.
## QA Report: {Story ID}
### Verdict: PASS / FAIL
### Acceptance Criteria Verification
| # | Criterion | Method | Result | Evidence |
|---|-----------|--------|--------|----------|
| 1 | {criterion} | {how tested} | PASS/FAIL | {output/screenshot} |
| 2 | ... | ... | ... | ... |
### Edge Cases Tested
| Scenario | Expected | Actual | Result |
|----------|----------|--------|--------|
| {edge case} | {expected behavior} | {actual behavior} | PASS/FAIL |
### Regression Check
- Test suite: {N} passed, {M} failed (was {prev} before)
- Build: pass/fail
### Issues Found
- {issue description} — severity: {high/medium/low}
### Human Judgment Needed
- {anything that needs human eyes — UX, aesthetics, "does this feel right?"}
Write to Foundry. Post the QA report as an annotation on the story doc.
If FAIL: List specific issues. Don't fix them in this step — QA is separate from implementation. Either:
/intern)If PASS: The deliverable is ready for Step 6 (Human Review). Suggest /present.