Agent skills by task
Agent Skills for Test-Driven Development and Testing
These skills make a coding agent prove its work: write a failing test first, keep each change small, and run real checks before it says a task is done. Use them when an agent keeps shipping code that looks right but breaks.
- skills
- 7
- packs
- 3
The skills
In the order we would try them
-
/tddTest-driven development for coding agentsBuilds features or fixes bugs test-first, one failing test and one fix at a time.
-
/test-driven-developmentStrict red-green-refactor test-driven developmentEnforces writing a failing test first, then minimal code, then cleanup.
-
/verification-before-completionRequires running checks and reading their output before claiming work is done.
-
/webapp-testingTests local web applications with Python Playwright scripts, screenshots and browser logs.
-
/setup-pre-commitSets up Husky pre-commit hooks running formatting, type checks and tests.
-
/implementBuilds a piece of work from a spec or tickets, test-first, then reviews it.
-
/migrate-to-shoehornReplaces as type assertions in test files with the shoehorn library.
Questions
Do I need both TDD skills?
No. Matt Pocock’s /tdd and Superpowers’ /test-driven-development cover the same loop. Installing both gives the agent two competing sets of instructions; choose the pack you use for the rest of your workflow.
Can a skill run my tests for me?
A skill only tells the agent how to work. The agent runs your existing test command; skills like /verification-before-completion make it read the output before claiming success.
Skills for other jobs
Lists picked by trendhub from public skill packs. Each skill lives in its author’s repository; read the current text there before installing.