メニュー
Wire the QA suite into CI. Use when the user wants tests running automatically on every PR or on a schedule: "add this to CI", "run tests on every push", "/qa-ci". Generates GitHub Actions workflows for the generated Playwright suite and (optionally) scheduled full audits.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Full QA audit orchestrator. Use when the user asks to "test my app", "run a full QA audit", "test everything", or invokes /qa-audit. Discovers what kind of application this is, selects the relevant QA agents (ui-inspector, api-sentinel, security-scout, perf-guardian, data-validator, regression-watcher), runs them, and merges their reports into one master QA report.
Onboard the QA toolkit onto any project. Use on first contact with a new codebase, when the user says "set up QA", "qa init", "/qa-init", or when any QA agent finds no qa-profile.md. Studies the project deeply and writes the persistent QA profile that every other agent reads first — the toolkit's long-term memory for this project.
Self-healing for the generated test suite. Use when previously-green Playwright tests are failing, the user says "my tests broke", "fix the tests", "/qa-heal", or after a UI refactor breaks selectors. Classifies each failure (real bug vs test drift) and repairs the drift — never papers over real bugs.
Compare two QA audit runs and report what improved, what regressed, and what persists. Use when the user asks "did it improve since last time?", "compare audits", "QA trend", or invokes /qa-trend. Requires at least two timestamped runs under qa-reports/runs/.
Audit web pages for WCAG 2.1 compliance. Use when the user asks about accessibility, a11y, WCAG, screen readers, or contrast issues.
Generate and execute API contract tests from OpenAPI/Swagger specs. Use when the user wants contract tests or schema validation for an API.
SOC 職業分類に基づく
| name | qa-ci |
| description | Wire the QA suite into CI. Use when the user wants tests running automatically on every PR or on a schedule: "add this to CI", "run tests on every push", "/qa-ci". Generates GitHub Actions workflows for the generated Playwright suite and (optionally) scheduled full audits. |
Two tiers. Always offer tier 1; tier 2 only if the user wants scheduled AI audits (it consumes Claude API credits in CI).
Generate .github/workflows/qa-tests.yml:
pull_request + push to main.npm ci →
npx playwright install --with-deps chromium → npx playwright test.playwright-report/ and traces as artifacts.services: block (postgres/mysql) matching
what qa-profile.md says the app uses.The regression tests generated from audit findings run here too — every bug ever found stays guarded on every PR, no AI involved.
Generate .github/workflows/qa-audit-scheduled.yml:
schedule: cron (ask cadence; default weekly) + manual
workflow_dispatch.anthropics/claude-code-action with prompt /qa-audit, requires
ANTHROPIC_API_KEY as a repo secret — tell the user exactly where to add
it (Settings → Secrets and variables → Actions). Never write a key into
any file.qa-reports/runs/<timestamp>/ folder to a
qa-reports branch (not main) or upload as artifact — user's choice./qa-trend reads those runs to chart improvement over time.npx yaml-lint or python yaml.safe_load).gh CLI is available and the user agrees: push a branch and confirm the
workflow triggers. Otherwise tell the user the file paths and that the
workflow activates on next push.