At a glance
- Best for
- A Red-Green-Refactor workflow
- Works with
- Behavior to implement or a failing case · Existing code and the test environment
- Outcome
- Behavior tests and an implementation · Records of failing and passing test verification
- Source
- obra/superpowers
01 / Understand the skill
About test-driven-development
Write and observe a failing test before implementing new behavior or fixing a defect, then add the smallest implementation and refactor. Emphasizes real-behavior assertions and full project verification. Requires the project's existing test framework and produces behavior tests, implementation, and failure/pass records with supporting test-quality references.
Requirements
- An agent that can edit code and run project tests
- The project's existing test framework and the complete writing-good-tests.md reference
Inputs
- Behavior to implement or a failing case
- Existing code and the test environment
Outputs
- Behavior tests and an implementation
- Records of failing and passing test verification
02 / Confirm the fit
Use test-driven-development when you need to
- A Red-Green-Refactor workflow
- Check failure reasons and test quality
- Regression checks and full verification after implementation
03 / See the workflow
How test-driven-development works
- 01Define the behavior and write a reproducibly failing test
- 02Complete the smallest implementation
- 03Refactor and run relevant checks and project-required verification
Check before installing
Compatible platforms
Cursor · GitHub Copilot · OpenAI Codex · Claude Code
Best fit
A Red-Green-Refactor workflow
Review the source instructions if the required output differs from the formats described above.
Install and use
Compatible with Cursor and GitHub Copilot and OpenAI Codex and Claude Code · Published by obra
Ready to add test-driven-development?
Use the published instructions below, then provide the required input and describe the result you need.
General instructions · Cursor · GitHub Copilot · OpenAI Codex · Claude Code
/plugin install superpowers@claude-plugins-official Install the complete Claude Code plugin as described in the upstream README. For other hosts, follow their dedicated installation sections in the same README.
Review the source repository and license before installing third-party skills.
Continue exploring
Similar skills
Authoritative reference for the Claude API and Anthropic SDKs: model IDs, pricing, thinking/effort params, streaming, tool use, caching, managed agents, and model migration.
Read, edit, create, and fix Excel/CSV files — formulas, formatting, charts, and clean financial models with zero formula errors.
Generate distinctive, production-grade frontend UI that avoids generic AI aesthetics — pages, components, dashboards, and landing pages.
Build high-quality MCP (Model Context Protocol) servers in Python (FastMCP) or Node/TypeScript that let LLMs use external services through well-designed tools.