Skip to content

lidge-jun/codexclaw / plugins/codexclaw/skills/qa

cxc-qa

Verified

Use for manual web, TUI, CLI, API and desktop QA. Triggers: smoke test, visual QA, screenshot check, CJK clipping, 수동 QA, 실제로 되는지 확인, 동작 확인, 직접 돌려봐.

references/scope-and-binding.md

View on GitHub
## 0. Scope split (single ownership)

- `cxc-dev-testing` owns AUTOMATED verification: unit, contract, E2E,
  Playwright suites and CI gates. Browser selection lives in the shared dev policy;
  `dev-testing` §4.7 connects that policy to exploratory tests.
- `cxc-qa` (this skill) owns the manual QA PROCEDURE: scenario matrix,
  faithful channels, evidence contract, adversarial classes, oracle passes,
  teardown receipts.
- Both feed PABCD C. Neither replaces the other: a green suite without a
  driven surface can still ship a broken border or a dead route; a driven
  surface without a suite has no regression guard. Promote a QA flow to a
  deterministic test (dev-testing §4.1) when it must stay guarded.

## 7. Binding to PABCD C

A user-facing surface change closes C with BOTH: the automated gate
(dev-testing) AND this skill's QA matrix — any FAIL verdict blocks the C>D
claim until repaired (LOOP-REPAIR-01 counts apply) or the criterion is
re-scoped through a P-phase amendment, never silently. This is E7 discipline:
no hook reads verdict.json. The E2 touchpoint: QA delegated to a registered `executor`
subagent rides the existing SubagentStop receipt gate (legacy `worker` also supported) — the executor cannot
finish without a non-empty receipt under the resolved evidence root (see `cxc state path`).
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
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: 197kUpdated Claude CodeCodexVerifiedInstall