Test mini
Portable AI-engineering skills for Claude Code, Codex, and coding agents: bounded scope, mini-specs, vertical slices, verification, ship gates, and handoff.
npx -y skills add tmusser/ai-engineering-skills --skill test-miniAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Add focused deterministic tests, fixtures, or smoke checks.
SKILL.md
1.5 KB, as published. Nobody here has run it
Test Mini
Purpose
Protect against wrong behavior without heavy tests.
When to use
Use for ML model workflows, agents, dashboards, data transformations, metric calculations, scheduled jobs, and any behavior that can appear to run while being wrong.
Inputs
- Implemented slice
- Expected behavior
- Available fixtures or examples
- Build/test/run commands
Workflow
- Add one deterministic behavior test when possible.
- Add one fixture or golden example when useful.
- Add one smoke test or manual verification path.
- Run exact commands.
- Record command output and result.
- Keep tests focused on the changed behavior.
Test integrity
Prefer adding tests over changing existing tests.
If modifying existing tests:
- Record the changed test path.
- State why the old assertion was wrong or incomplete.
- Name the source of truth.
- Preserve the prior assertion or replace it intentionally.
- Mark verification as
REVIEW_REQUIREDunless the rationale is explicit.
Never weaken tests merely to match the implementation.
Outputs
- Focused test or fixture
- Smoke path
- Exact command results
- Remaining risk notes
Stop conditions
- The behavior is proven enough for the task risk.
- No deterministic check is possible without changing the design.
Anti-patterns
- Only checking that the code runs without checking correctness.
- Adding broad tests unrelated to the changed behavior.
- Hiding manual verification steps in chat.