Publisher: Jesse Vincent / Prime Radiant · Editorial profile by AI Tools Ratings · Review method
What task is this skill designed for?
Add a duration formatter that handles zero, ordinary values and invalid input in a small synthetic library.
What input and output should you expect?
Input: A precise function contract, representative inputs, expected outputs and the existing test command. Specify rounding and invalid-input behavior before implementation.
Output: Behavior-focused tests, a minimal implementation and evidence of the fail-then-pass cycle, followed by relevant suite results.
What does it need to run?
An executable test runner and a coding agent with file-editing and terminal access. The source also references guidance on writing meaningful tests.
Publisher README documents Claude Code, Codex and Cursor installation paths, among other harnesses. Tool availability and behavior depend on the host; this is publisher-declared support, not a cross-platform test result.
How should you approach installation?
- Review the pinned folder and its referenced files before enabling the workflow. The folder belongs to the broader Superpowers plugin, not an independently verified standalone installer.
- Follow the publisher README for your chosen coding-agent platform. The publisher documents several harnesses; use the instructions for your installed version and review plugin hooks and permissions.
- Try the suggested task in a disposable repository with synthetic inputs. Check the acceptance list before applying the workflow to shared work.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Can create and modify tests and production code, run project commands and make commits as part of a development workflow. Review project hooks and dependency commands for external side effects.
What does the skill cost?
No separate skill purchase is specified in the MIT-licensed source. Coding-agent subscriptions, model tokens, test compute and any external services have their own charges. Review or repeated execution can increase model usage.
What are its limits and alternatives?
Test-first work does not prove the specification is correct or that unmodeled cases are safe. The source strongly directs removal of implementation written before tests; preserve existing user work and agree scope before using that behavior in a shared repository.
Use a characterization-test approach for existing behavior you do not yet understand. Use Systematic Debugging first when the defect itself has not been isolated.
What could you ask in a small trial?
Try this with a small sample:
In this disposable library, add the agreed duration formatter using a failing behavior test first. Show why the failure demonstrates missing behavior, implement the smallest fix, then run the applicable suite.
How would you verify the result?
- A test fails because the behavior is missing, not because imports or tooling are broken.
- Tests exercise real returned values for zero, normal and invalid inputs.
- The final report separates the targeted test result from the wider suite result and identifies any unrelated existing failures.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
MIT — repository LICENSE at the reviewed commit. Dependencies and external services retain their own terms. License evidence
Version details and review scope
Source: obra/superpowers/skills/test-driven-development
Reviewed commit: 2ce8aa15d05bd57213e6f746f953aafb7ded7a8b
SKILL.md SHA-256: 64b03fce4aee5a97a93160cea8111f3ba13a17b7c001db4bd5836d67fd10705d
Source-document review. This profile covers the source workflow, stated dependencies and license evidence. See our editorial methodology for how we distinguish source reviews and hands-on evaluations.