Use when a spec and a test suite both exist but nobody can say which requirements are covered, before a release sign-off, an audit or planning test effort. Uses an LLM to map existing tests to spec sections, outputs a coverage matrix per spec ID and names the gaps. It does not write new tests.

Use when an existing API test suite should be rerun under network faults to prove retries, timeouts, circuit breakers and fallbacks work. Injects latency, timeouts, dropped connections, bandwidth caps and packet loss with Toxiproxy and reports which assertions break under which fault.

Use whenever an Apollo Server v4+ GraphQL service needs tests: in-process executeOperation calls, supertest against an ephemeral port, context injection, response and error assertions, and checks that production config disables introspection and enforces persisted queries.

Use whenever one mobile UI test suite must run on iOS and Android (native or React Native apps), or an Appium suite fails, flakes or breaks after an upgrade: XCUITest, UiAutomator2 and Espresso drivers, capabilities, clients in JS, Python, Java, Ruby or .NET, simulators, emulators and device farms.

Use when building or reviewing a custom interactive widget with no native HTML equivalent (combobox, dialog, menu, tabs, tree and more). Gives the W3C ARIA Authoring Practices pattern: required roles and states, keyboard interaction and common violations.

Use whenever pages or components need automated accessibility scanning: axe-core via axe.run(), @axe-core/playwright or the CLI on every PR, rule configuration and CI-gateable results, plus pa11y, Lighthouse CI accessibility, WAVE and IBM Equal Access (Section 508) in its references.

Use when someone reports a problem informally, a CI failure (JUnit XML, Allure, pytest or Playwright output) must become a bug report, or a draft needs a quality check before filing. Fills summary, environment, steps, expected vs actual and severity rationale, then checks each field is usable.

Use whenever a Node.js or TypeScript service uses BullMQ and its queues or workers need tests: producers, worker processors, retries, backoff and repeat jobs, FlowProducer parent-child jobs and QueueEvents, against real Redis (Docker, Testcontainers) or ioredis-mock.

Use when a C project wants Unity, CMock and CException run by one build command, or CMock mocks need writing or reading: Ceedling project scaffolding, project.yml, test tasks, JUnit XML, gcov coverage, host vs cross builds and CI. The Unity assertion API is unity-test-framework-c.

Use when a chaos experiment is already designed and a fault is about to be injected into a running system. Sets the go/no-go gates (non-production, healthy baseline, live monitoring, tested rollback), blast-radius bound, abort criteria, inject and abort commands and the recovery check.

Use when designing how tests run in CI on any platform (GitHub Actions, GitLab CI, Jenkins, CircleCI): how many shards, which failures are safe to retry, quarantine, artifact retention, per-PR vs nightly cadence, cancel-on-push, timeouts and secrets. CircleCI config patterns are in its references.

Use when a project needs fuzz testing, a fuzz campaign must be written or maintained, or fuzzer crashes need triage. Picks libFuzzer, AFL++, cargo-fuzz, Go fuzzing, Atheris or Jazzer by language, then covers fuzz targets, seed corpora, dictionaries, sanitizers, crash triage and CI smoke fuzzing.

Use when cron jobs, Kubernetes CronJobs, BullMQ repeat jobs, Sidekiq schedules or any time-based job need tests: cron expression validation, DST and leap-day edge cases, catch-up after downtime, overlapping-run locks with stale-lock recovery, and time zones.

Use when scoping a new data product or formalizing checks on an existing one. Reads a data PRD, dataset README or lineage doc and writes a data contract: schema with types, nullability and PII flags, freshness SLA, volume bounds, distribution rules and owner, for dbt, Great Expectations or Soda.

Use when a service that takes two or more locks hangs in production with no error, or before a release when lock order across code paths was never checked. Records lock order, finds cycles, uses lock timeouts to fail instead of hang, and reads jstack or gdb thread dumps.

Use whenever a React Native app needs end-to-end tests with Detox: gray-box runs inside the app, by.id, by.text and by.label matchers, waitFor for extra sync, and the Jest runner. Flutter is flutter-testing; cross-platform black-box is appium-testing; YAML flows are maestro-flows.

Use whenever an Electron desktop app needs end-to-end tests, or a Spectron suite must be migrated: Playwright's _electron.launch, renderer windows as Pages, main-process checks via electronApp.evaluate, and IPC and DOM assertions from one suite.

Use when code instrumented with Statsig, Optimizely, Split.io (Harness FME), Amplitude Experiment or VWO needs tests. Initializes the SDK offline from a committed config fixture, pins each test to an arm and checks assignment integrity, with per-vendor references.

Use whenever user stories, acceptance criteria, manual test steps or a spec section need to become Gherkin .feature files. Maps criteria to scenarios, finds Scenario Outlines and Background, reuses existing steps and flags hidden preconditions. Writes Gherkin only, not step code.

Use whenever the task is to run tests in GitLab CI/CD: test stages in .gitlab-ci.yml, parallel matrix jobs, junit and coverage artifact reports, Postgres or Redis services, needs between jobs, rules for triggers and retry policy.