Why does this skill insist on watching a test fail first?

Watching a test fail (the RED phase) is the only way to prove the test actually verifies the behavior you are trying to implement. If you don't see it fail, you don't know if it's testing the right thing or just passing by accident.

What is the 'Iron Law' of TDD in this skill?

The Iron Law states: No production code without a failing test first. If code is written before a test, this skill advocates for deleting it and starting fresh from a test-first perspective.

Can I use this skill for bug fixes?

Yes, TDD is highly effective for bug fixes. You first write a test that reproduces the bug (RED), then write the minimal code to fix it (GREEN), and finally refactor the fix for clarity.

Does this skill work with any testing framework?

Yes, the TDD workflow is a methodology that can be applied to any language or framework, such as Jest for TypeScript, Pytest for Python, or JUnit for Java.

Test-Driven Development (TDD) Workflow

Name: Test-Driven Development (TDD) Workflow
Author: lifangda

bylifangda

•

Security & Testing

Enforces a rigorous Red-Green-Refactor cycle to ensure every line of production code is verified by a failing test first.

This skill integrates a strict Test-Driven Development (TDD) methodology into Claude's coding process, mandating the 'Iron Law' of software quality: no production code is written without a preceding failing test. By guiding Claude through the Red-Green-Refactor cycle, it ensures that tests are meaningful, code is minimal and purposeful, and regressions are caught immediately. It is ideal for developers who prioritize high-confidence deployments and maintainable codebases by preventing the common pitfall of writing tests that only pass because they mirror existing implementation errors.

Key Features

01Structured refactoring phase to clean code without altering behavior

02Comprehensive TDD best practices and rationalization checks

03Strict enforcement of the Red-Green-Refactor cycle

04Minimalist code implementation (GREEN) to prevent over-engineering

05Mandatory verification of test failure (RED) to prove test validity

0616 GitHub stars

Use Cases

01Developing new features with 100% test coverage from the start

02Fixing bugs by first reproducing them with a failing test case

03Safe refactoring of complex logic while maintaining existing behavior

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add lifangda/claude-plugins test-driven-development

For use in Claude.ai and ChatGPT

Download Skill