What tests does
The tests skill detects the stack, reuses an existing test runner or installs the native choice, adds one small working example, records the command in AGENTS.md, and runs the resulting checks.
The opt-in switch
Once AGENTS.md declares a test command, logic-bearing implementation steps must include relevant tests and keep the suite green. UI and integration surfaces continue to use browser evidence and builds.
Interaction with Verify and CI
If AGENTS.md already declares a Verify command, /tests adds the real test command between typechecking and the build, then proves the updated recipe. It preserves existing workflows and never creates CI only because testing was added.
Run $ci in Codex or /ci in Claude Code when you want the project-specific Verify recipe to run automatically through GitHub Actions.
What it does not promise
The skill does not generate a complete test suite, coverage policy, browser automation, or CI workflow. It creates a trustworthy unit-testing foundation and makes future logic testing an explicit workflow requirement.
Use Browser Tests when the project needs a repeatable browser harness.
Good unit-test targets
Parsers, validators, formatters, slug builders, server actions, and other pure logic with meaningful edge cases are good targets. Visual markup and browser flows are not.