All 94 skillsQuality2 of 13
stryx:test
When tests must be written or fixed, or you want the test written first (TDD).
/stryx:testInside its piece: 26 specks, one for each file on its shelf. Its twelve group-mates glow on the open book behind it. The light splits toward orange, the band of Quality.
In numbers
counted 2026-10-12 in the installed set- 21reference files
- 3helper scripts
- 26files in the skill
- 313KB on disk
- 17chapters
- 1agent works by this book
Use it when
in the skill’s own wordsWhen writing, fixing or reviewing tests
- Doing TDD (test first, red-green-refactor)
- Fixing a bug that needs a regression test
- Setting up Vitest or migrating from Jest
- Testing React components, Zustand stores, Electron IPC or sql.js code
- Writing Playwright or Cypress E2E tests
- Writing deterministic, isolated tests
- Judging coverage or whether assertions mean anything
- Auditing which tests are missing
- Browser-testing the routes a branch or PR changed
- Dogfooding a branch end to end (only when the user asks)
- Collecting iOS simulator evidence
- Also Pester and VBA test harnesses and the TDD method for pytest (pytest mechanics are stryx:python)
Not for
another skill does it- Diagnosing why an existing test fails or flakes→ stryx:debug
- Writing the shell script itself→ stryx:shell
- Java's JUnit, Mockito and Spring Boot test tools→ stryx:java
What it covers
6 parts- TDD
- the edge-case matrix
- mocking
- the test completion gate
- coverage targets
- @sacred regression tests and live-QA evidence
On its shelf
26 files, 313 KB- references/21
- scripts/3
- SKILL.md1
- evals/1
Inside the book
17 chapters, by title only- Pick the mode
- Procedure in short (the order of work; each step is detailed in the numbered section it names)
- The Iron Law
- Red-Green-Refactor
- Edge-case matrix
- Writing the test
- Mocking
- Where tests live
- Test completion gate
- Anti-premature-completion
- The 3-strike rule
- What to test, what not
- Coverage
- Regression tests and @sacred tests
- Live QA evidence (browser check, dogfood, simulator)
- Scoring a change
- Tests for code that already exists, and coverage audits
Its helper
1 agent works by this book- stryx:testerWhen tests must be written: test-first for a new feature, or tests for code that has none.
Works with
the skills it names most- stryx:debug→Something is broken: a bug, an error, a crash, a failing test or wrong data.
- stryx:verify→When Claude is about to say done, fixed or ready to commit: fresh proof comes first.
- stryx:ai-power→When you are not sure which skill fits, or you say "load aipower": it is the map of all skills.
- stryx:browser→When Claude must drive a live web page: open, click, fill a form, take a screenshot.
- stryx:java→When writing, fixing or upgrading Java code: builds, Spring Boot, tests, version moves.
- stryx:python→When writing or fixing Python 3.11 or newer: types, async code, packaging, pytest.
Claude loads it by itself when the moment comes; by hand, type the line at the top. It comes with the whole set: Installs all 94 skills, 32 agents and the brain program as one set. The skill’s own text is private source and is not shown here.