Tdd

This is a guardrail for test-driven development that stops Claude from writing tests when they'd be wasteful. It enforces the red-green-refactor loop only when the user explicitly asks for TDD or when the bug has an obvious, cheap test target. The workflow is strict: write a failing test, confirm it fails for the right reason, fix the bug, then verify it passes. If a proper regression test would need brittle mocks, slow infrastructure, or expensive setup, it tells Claude to skip it and use the closest practical verification instead. The core insight is that a bad test is worse than no test, and forcing TDD on integration-heavy or unclear paths creates more problems than it solves.

skills.sh installs: 3.9K
GitHub stars: 15.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cursor/plugins --skill tdd --agent claude-code

Installs into .claude/skills of the current project.

Files

TDD Bug Fix

When fixing a bug with a clear, cheap test path, make the broken behavior executable before changing production code. The goal is a focused regression test that fails before the fix and passes after it.

Do not force a test when it would be impractical. If the available test would require broad harness setup, brittle mocks, slow end-to-end infrastructure, production-only state, vague reproduction steps, or large unrelated fixture churn, skip adding a new test and use the closest useful verification instead.