EricTechPro/super-board / skills/super-qa
super-qa
VerifiedSuper QA canonical workflow for functional bug-bash, evidence capture, and fix-ready issue filing. Crawls routes from `docs/super-qa/queue.md` with Playwright, records screenshots/logs/HARs, files product-readable issues with clear type/priority/area labels, and continues until traversal is complete or only human-gated blockers remain. Crawling is always browser-driven, but the regression test it leaves behind is written at whichever layer the defect actually lives — unit or integration in Vitest, e2e in Playwright only when the browser is the thing that broke. Use when the user says "run super-qa", "QA review", "bug bash", "verify and fix", or invokes `/super-qa`.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.5 KB |
| SKILL.md | skill md | 38.7 KB |
| examples/runtime-demo/demo.py | script | 3.3 KB |
| examples/runtime-demo/scenario.mjs | script | 338 B |
| references/iteration-preamble.md | markdown | 38.9 KB |
| references/project-verifier.md | markdown | 7.3 KB |
| references/runtime-verification.md | markdown | 8.3 KB |
| scripts/runtime_browser.mjs | script | 2.7 KB |
| scripts/runtime_compare.py | script | 17.5 KB |
README.md
View on GitHub# /super-qa
The Tester: proves a card's acceptance criteria with tests and evidence, or sends it back to Build with a precise failure.
## What It Does
- **One observable test per AC**, written at the layer the defect lives (unit or integration in Vitest, e2e in Playwright only when the browser is what broke).
- **Test-gap check after build**: maps every AC to tests, hunts edge cases with exact values, names weak tests. High gaps are written red-first; Medium/Low are listed and never block.
- **Captures evidence**: screenshots at desktop, tablet and mobile, logs and HARs, committed to the branch and embedded inline in the PR comment.
- **Runs `pr-security-review` on every PR diff.** Each finding fails QA and goes back to Build, like any failing check. For a whole-repo audit it points you at `security-audit`.
- **Files what it finds** off-ticket as `source:qa` cards instead of fixing them silently.
## When To Use It
- Inside a super-board run (the QA lane). This is the normal path.
- Standalone, as `/super-qa`, to bug-bash an app: a browser crawl from `docs/super-qa/queue.md` that grows a Playwright suite and files fix-ready issues.
## Standalone flags
| Command | Does |
|---|---|
| `/super-qa` | 10 iterations |
| `/super-qa 5` | 5 iterations |
| `/super-qa --resume` | Continue from the last iteration |
| `/super-qa --continue-on-error` | Don't halt on one failed iteration |
## Install
Part of the super-board pack: `./install.sh /path/to/project`. Run it against staging, not production. Lane details: `skills/super-board/references/run.md` → Tester.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |