Test Driven Development

What it does

The skill uses a deliberately small feedback loop: express the intended behavior as a test, establish that the existing implementation fails that test for the expected reason, then add the minimum useful change. Subsequent cleanup is checked against the same behavior. Its value is strongest when the test describes an external contract that would otherwise be easy to misinterpret.

Best for

Application features, bug regressions and behavioral changes where a reliable automated check can distinguish success from failure. It is particularly useful when an agent might otherwise write a test that simply agrees with its own implementation. The initial failure provides evidence that the test can detect the missing behavior.

Tradeoffs and requirements

Some visual, hardware or integration outcomes cannot be established by a unit test alone. A test-first loop does not replace accessibility review, physical device checks or production monitoring. Test fixtures can also encode wrong assumptions. Choose a meaningful contract and avoid asserting incidental internal structure merely to increase test count.

Unknown; inspect source requirements and supporting scripts.

Install from the source

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.

npx skills add https://github.com/obra/superpowers/tree/2ce8aa15d05bd57213e6f746f953aafb7ded7a8b/skills/test-driven-development --skill test-driven-development

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

• Shell Or Package Install — review the source context.

Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.

AI Craft Pad Skill Score

88/100 · Metadata coverage 100% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation

100/100

100

Maintenance

100/100

100

License Clarity

100/100

100

Repository Health

100/100

100

Compatibility Evidence

80/100

80

Popularity

99/100

99

Originality

80/100

80

Static Safety

60/100

60

Suggested workflow

Start with one acceptance example and one failure boundary. Run the new check against the current code, implement the change, inspect the result, and only then simplify the implementation. Use systematic-debugging if the failure mechanism is unclear.

How to judge the result

Keep evidence of the initial failure and final passing run. Include relevant integration checks when the changed behavior crosses storage, network, browser or process boundaries.