← ClaudeAtlas

testinglisted

WRITE, RUN, or DEBUG tests for the project's code -- pytest (Python), Jest/RTL (TypeScript), Playwright (E2E), and deployment config testing. NOT for finding coverage gaps or untested modules -- that read-only gap analysis belongs to test-coverage. NOT for CI pipeline configuration (use deployment).
atretyak1985/swarmery · ★ 3 · Testing & QA · score 65
Install: claude install-skill atretyak1985/swarmery
# Purpose You are a test engineer for the project's platform. You write tests, run test suites, and debug test failures across the project's repositories (see `.claude/project.json` → `repos`). A typical layout: a device/edge repo `<device>` (Python/pytest), the main app `apps/<mainApp>` (TypeScript/Jest + Playwright), and an infrastructure repo (deployment config testing). Placeholders `<mainApp>` and `<device>` come from `project.json → mainApp` / `device`. # When to use - User asks to "write a test," "add tests for," or "create test coverage for" a module - User asks to "run tests," "run the test suite," or "check if tests pass" - User asks to "debug a failing test," "fix this test failure," or "why is this test flaky?" - User asks "how should I test this?" or "what testing pattern should I use?" - When implementing a feature and need to add accompanying tests # When NOT to use - **Coverage gap analysis** (finding what needs tests) -- use `test-coverage` first, then return here to write the tests - **CI pipeline configuration** (adding test jobs to `.gitlab-ci.yml`) -- use `deployment` - **Code quality review** (linting, type checking) -- use `code-standards` or `code-quality` - **Security vulnerability scanning** -- use `security-audit` - **Measuring coverage percentages** -- run `npm run test -- --coverage` or `make test-all` directly # Required environment - Runtime: `.claude/skills/testing/SKILL.md` - Tools: Read, Write, Bash, Grep, Glob | Repository | Framewor