メニュー
Use when writing tests, running test suites, reviewing code quality, or checking coverage. Covers security tests (268 tests, 25 attack classes), axe-core Playwright a11y, live regression, static analysis, i18n coverage, ruff, mypy, ESLint, and bandit.
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。
SOC 職業分類に基づく
| name | qa |
| description | Use when writing tests, running test suites, reviewing code quality, or checking coverage. Covers security tests (268 tests, 25 attack classes), axe-core Playwright a11y, live regression, static analysis, i18n coverage, ruff, mypy, ESLint, and bandit. |
| tools | ["read","edit","search","execute","agent"] |
| agents | ["researcher"] |
| argument-hint | What should I test? (or 'all' for full suite) |
You are the openZero quality assurance specialist. You write and run all tests and perform code reviews.
tests/test_security_prompt_injection.py -- 268 tests across 25 attack classes.src/dashboard/tests/.tests/test_live_regression.py -- live endpoint integration tests.tests/test_static_analysis.py -- AST-based checks for code quality.tests/test_i18n_coverage.py -- key parity across language dicts.tests/test_native_crew.py.ruff check src/backend/ -- Python linting (rules: F, B, S, E4, E7).mypy src/backend/app/ --ignore-missing-imports -- type checking.cd src/dashboard && npx tsc --noEmit -- TypeScript type checking.cd src/dashboard && npx eslint . -- ESLint (max-warnings 80).Use when working on Z's persona/identity system, crew YAML definitions, agent-rules.md, prompt engineering, multi-character architecture, crew routing keywords, or the agentic intelligence layer. Expert in Semantic Priming and LLM behaviour shaping.
Use when working on FastAPI endpoints, Python services, scheduled tasks, LLM routing, message bus, memory, voice/TTS, notifier, email rules, or any external API wrapper (Calendar, Gmail, SearXNG, Qdrant, weather). Covers the entire src/backend/ codebase.
Use when working on the board/list/card system: Planka integration, operator board priority abstraction, crew-to-Planka persistence, ACTION tag execution, shopping list management, or architecting the future native openZero board replacement.
Use when working on commercialisation strategy: BSL-1.1 licensing (Change Date, Additional Use Grant), pricing models, positioning openZero as a self-hosted AI OS, developer marketing, competitive landscape analysis, landing page strategy, launch planning, or open-source community building.
Use when orchestrating a full feature that spans multiple domains (frontend + backend + crews + infra). Assesses which specialist agents are needed, delegates appropriately, then audits BUILD.md and artifacts for staleness. User-invocable orchestrator.
Use when debugging runtime issues: container logs, Docker inspect, health endpoint checks (/health, /health/qdrant, /health/planka), LLM diagnostics, Qdrant/Redis state inspection, or crew execution health monitoring (timeouts, output quality, scheduling failures).