Coverage-design method for qa-engineer — pyramid ratios per archetype, equivalence/boundary/property case selection, mutation score as the real coverage signal, and a flake-quarantine policy. Turns "coverage is 90%" (a number with no method) into a defensible test plan. Emits TEST-STRATEGY-{slug}.md, which the QA gate checks exists.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Coverage % is a number with no method. This skill makes the QA plan defensible: what to test, why that set, and a real signal that the tests bite.
qa-engineer emits docs/qa-reports/TEST-STRATEGY-{slug}.md capturing the four
decisions below; the QA gate checks the file exists for medium/large features.
The right unit:integration:e2e mix depends on where the risk lives.
| Archetype | unit | integration | e2e | why |
|---|---|---|---|---|
| library / devtools / cli | 80% | 15% | 5% | logic-dense, few I/O seams |
| web-app / saas | 60% | 30% | 10% | request→db→render seams dominate |
| commerce / fintech / marketplace | 50% | 35% | 15% | money paths need cross-component proof |
| data-platform / streaming | 45% | 45% | 10% | correctness lives in pipelines, not units |
| ai-system / agent-product | 50% | 20% | 10% + evals 20% | behaviour is the contract → eval set (see [[decision-eval]]) |
State the chosen ratio in TEST-STRATEGY and justify any deviation.
Don't enumerate inputs; partition them.
decode(encode(x))===x, idempotency, ordering) instead of hand-picked cases. Use fast-check / Hypothesis where the logic warrants it.Line/branch coverage proves code ran, not that a test would fail if it broke. Mutation testing (Stryker / mutmut / cargo-mutants) flips operators/conditions and checks a test catches it. A "90% covered" module with 30% mutation score has assertion-free tests. Target: mutation score ≥ 60% on changed logic-dense files; report it in TEST-STRATEGY when the change is logic-heavy. Coverage % is the cheap proxy; mutation score is the truth.
A test that fails ~randomly trains the team to ignore red. Policy:
it.skip forever.flaky flag in
tests/eval/runner.mjs — stddev > 0.1 is a flake signal).# TEST-STRATEGY-{slug}
- Archetype + chosen pyramid ratio (+ justification for any deviation)
- Equivalence classes & boundaries enumerated per changed unit
- Property-based candidates (which logic, which invariants)
- Mutation-score target + result (for logic-dense changes)
- Quarantine list (flaky tests + their tracking bug)
Done = the plan answers "why THIS set of tests", not just "how much is covered".
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
great_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided by MEANING (Geist speaks, Geist Mono is machine-truth), tabular numerals, and a dash that is not a nought. Twelve checkable rules measured from packages/board and greatcto.systems, not designed for this file. Use when building or extending any great_cto surface — the board, the site, a report, a share page.
中文简介正在准备中。当前显示原文说明。
Catalogue of known SDLC anti-patterns that great_cto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
中文简介正在准备中。当前显示原文说明。
Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest reference, a mockup, a competitor's site, a component, a dashboard, a landing page. Also when they ask 'extract the design system from X', 'document the style of Y', 'analyze this visually', 'convert this image into tokens', 'help me replicate this design', 'what palette does this site use', 'how is this built'. Also for single elements: 'copy this navbar', 'recreate this illustration', 'give me a prompt to regenerate this graphic' — element mode outputs a focused element.md, with token-grounded image-model prompts when the element is visual art. If the user brings any visual source and wants to understand it at a design level — this skill should activate.
中文简介正在准备中。当前显示原文说明。
Shared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow. Defines the output artifact (TM-{slug}.md), mandatory sections, severity scale, verdict format, the workflow scaffold (when-invoked, Step-0 read-inputs, HANDOFF), and the "domain heuristic vs generic check" boundary. Eliminates duplication across the ~30 reviewer prompts.
中文简介正在准备中。当前显示原文说明。
Structured idea generation + multi-LLM debate for the product-owner stage. Diverge (generate genuinely different bets), debate (a 4-persona panel on 4 models argues over 2 rounds), converge (synthesize a recommendation). Used by product-owner before architect; available to architect for design-space exploration.
中文简介正在准备中。当前显示原文说明。
Run the great_cto controlled Codex lifecycle with controller-owned writes, verifier evidence, human gates and optional artifact release.
中文简介正在准备中。当前显示原文说明。