
Test Driven Development
This is TDD fundamentalism, and I mean that as a compliment. It enforces the red-green-refactor cycle with zero wiggle room: write a failing test, watch it actually fail, then write minimal code to pass. The iron law is no production code without seeing a test fail first, because a test that passes immediately proves nothing. If you write code before the test, you delete it and start over, no exceptions. It systematically dismantles every rationalization for skipping steps, from "I'll test after" to "deleting work is wasteful" to "I already manually tested it." Opinionated to the point of being confrontational, but that's exactly what you need when building the discipline. Use this when you want TDD done properly, not TDD-flavored development.
- skills.sh installs
- 1.3K
- GitHub stars
- 1.8K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add neolabhq/context-engineering-kit --skill test-driven-development --agent claude-codeInstalls into .claude/skills of the current project.
Files
Test-Driven Development (TDD)
Overview
Write the test first. Watch it fail. Write minimal code to pass.
Core principle: If you didn't watch the test fail, you don't know if it tests the right thing.
Violating the letter of the rules is violating the spirit of the rules.
When to Use
Always:
- New features
- Bug fixes
- Refactoring
- Behavior changes
Exceptions (ask your human partner):
- Throwaway prototypes
- Generated code
- Configuration files
Thinking "skip TDD just this once"? Stop. That's rationalization.
The Iron Law
NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
Write code before the test? Delete it. Start over.
No exceptions:
- Don't keep it as "reference"
- Don't "adapt" it while writing tests
- Don't look at it
- Delete means delete
Implement fresh from tests. Period.
Red-Green-Refactor
Sponsors
Details
- Repository
- github.com/neolabhq/context-engineering-kit
- Categories
- Testing & QA, Documentation
- First seen
- Jun 3, 2026
More from neolabhq/context-engineering-kit
All 63- Plan Task1.3K
- Judge1.3K
- Why1.3K
- Do And Judge1.3K
- Setup Serena Mcp1.3K
- Implement Task1.3K
- Write Tests1.3K
- Test Prompt1.3K
- Analyse Problem1.3K
- Do In Steps1.3K
- Create Rule1.3K
- Do In Parallel1.3K
- Add Task1.3K
- Analyse1.3K
- Review Pr1.3K
- Launch Sub Agent1.3K
- Create Agent1.3K
- Test Skill1.2K
- Apply Anthropic Skill Best Practices1.2K
- Tree Of Thoughts1.2K
- Cause And Effect1.2K
- Create Ideas1.2K
- Fix Tests1.2K
- Create Skill1.2K