AI agent skill
Test-Driven Development
Force a coding agent to write a failing test first, then the minimum implementation, then refactor — so it cannot claim done without a red-green loop.
·
When to use this skill
Use TDD when adding behavior to a codebase that already has a test runner. It is the default skill for "add a feature" in Claude Code or Codex.
When not to use it
Do not use it to explore a throwaway prototype with no test harness. Use Systematic Debugging when the tests already exist and are failing for unknown reasons.
How to install
- Personal install: create ~/.claude/skills/test-driven-development/SKILL.md (and any bundled scripts) so Claude Code, Claude Desktop, and compatible agents can load it in every project.
- Project install: commit the same folder at .claude/skills/test-driven-development/ so teammates get the skill with the repo.
- Restart the agent session after copying files so it re-scans the skills directory, then ask for the task in words that match the skill description.
What this skill does
Without TDD, agents write code then hunt for a test. This skill reverses that: name the behavior, watch it fail, then implement.
Intended uses
- Add an API route with a contract test
- Fix a bug by first capturing it as a failing test
- Keep a refactor honest
Related skills
Related skills in this directory, for comparison before you install another skill.
coding
Systematic Debugging
A root-cause debugging loop for coding agents: reproduce, isolate, hypothesize, then change one thing — instead of shotgun patches.
coding
Web App Testing
Drive a real browser against a local or deployed web app: click, type, assert visible state — not just unit tests of components.
coding
Git Worktrees
Run parallel agent sessions in git worktrees so long jobs do not block the main checkout and diffs stay reviewable.
coding
Act as a Patient, Non-Technical Android Studio Guide
A reusable prompt for asking an AI assistant to work as Act as a Patient, Non-Technical Android Studio Guide.