test-driven-development
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
Best use case
test-driven-development is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
Teams using test-driven-development should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/test-driven-development/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How test-driven-development Compares
| Feature / Agent | test-driven-development | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Test-Driven Development ## Overview Enforces the TDD discipline in all CC10X BUILD workflows. The RED-GREEN-REFACTOR cycle is mandatory and cannot be skipped or deferred. ## TDD Cycle 1. **RED**: Write failing test first. Run with `CI=true npm test` or `--run` flag. Exit code MUST be 1. 2. **GREEN**: Write minimal code to make test pass. Exit code MUST be 0. 3. **REFACTOR**: Clean up implementation while keeping tests green. Exit code MUST remain 0. ## Non-Negotiable Rules - Always use run mode (`CI=true npm test` or `--run` flag) - NEVER use watch mode (prevents hanging processes) - Use timeout guards (`timeout 60s`) as backup - Record exit codes as evidence at each phase - If tests fail 3 consecutive times in GREEN, report failure status - Never skip RED phase (failing test must exist before implementation) - Never defer tests to "later" -- TDD means tests first ## Scope Discipline - If implementation requires >3 file changes, flag for scope review - Architectural choices require user approval unless pre-approved in plan - New dependencies require user approval ## When to Use - Every feature implementation in BUILD workflow - Every bug fix in DEBUG workflow (regression test) ## Agents Used - `component-builder` (primary consumer) - `bug-investigator` (regression tests)
Related Skills
vue-development
Vue 3 development with Composition API, reactivity system, component patterns, TypeScript integration, and best practices.
vitest
Vitest configuration, mocking, coverage, snapshot testing, and performance.
react-testing-library
React Testing Library patterns, queries, user events, and accessibility testing.
react-development
Specialized skill for React component development, hooks patterns, state management, context API, performance optimization, and modern React best practices.
angular-development
Angular development patterns including modules, components, services, dependency injection, signals, and enterprise architecture.
load-test-generator
Generate load test scripts for k6, Locust, and Gatling from OpenAPI specs
cloud-security-testing
Multi-cloud security assessment and penetration testing capabilities. Execute Prowler/ScoutSuite assessments, analyze IAM policies, identify cloud misconfigurations, test permissions, and enumerate cloud resources across AWS/GCP/Azure.
contract-test-framework
Consumer-driven contract testing for SDK-API compatibility. Generate Pact consumer tests, verify provider contracts, configure Pact broker, and implement can-i-deploy checks.
compatibility-test-matrix
Multi-version, multi-platform SDK compatibility testing
test-data-generation
Synthetic test data generation and management using Faker.js and similar tools. Generate realistic test data, create data factories, implement database seeding, and manage test data anonymization.
Stryker Mutation Testing
Stryker mutation testing for assessing test suite quality and effectiveness
pytest Testing
Expert pytest framework for Python unit, integration, and functional testing