Menu
Test-driven development workflow enforcing tests FIRST with 80%+ coverage
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Use when implementing features, fixing bugs, refactoring code, optimizing performance, resolving deprecations, or any multi-step development task requiring planning, implementation, testing, and review. Orchestrates specialized agent teammates through research, architecture, coding, QA, code review, adversarial review, and documentation phases. Triggers on: "implement", "build", "fix bug", "refactor", "add feature", "develop this", "help me build", "add functionality", "optimize performance", "resolve deprecation", "systematic development". Do NOT trigger on: simple questions ("what does this code do?"), file searches ("where is the auth function?"), one-off commands ("run the tests"), code explanations, quick edits, or non-development tasks.
Multi-lens adversarial review with Skeptic, Architect, and Minimalist lenses and 7+ attack vectors
Auto-improve any agent prompt using Karpathy's autoresearch method with iterative test-measure-improve loops
Safety guardrail that blocks destructive commands for the current session
Core development rules and philosophy for coding standards, git practices, and quality guidelines
Directory freeze guardrail that restricts file edits to a specific directory for the current session
| name | tdd-workflow |
| description | Test-driven development workflow enforcing tests FIRST with 80%+ coverage |
Enforce test-driven development methodology for writing new features, fixing bugs, or refactoring code. Scaffold interfaces, generate tests FIRST, then implement minimal code to pass. Ensure 80%+ coverage including unit, integration, and E2E tests.
Triggers on: feature implementation, bug fixes, refactoring, "write tests first", "TDD"
Define the public API (function signatures, types, interfaces) before any implementation. Write failing tests that describe expected behavior. Cover: happy paths, error paths, edge cases (null, empty, boundaries), integration points. Execute test suite to confirm tests fail as expected. Write minimum code to make tests pass. No extra logic beyond what tests require. Execute test suite to confirm all tests pass. Remove duplication, improve naming, optimize. Re-run tests to verify no regressions. Run coverage report. Verify 80%+ across branches, functions, lines, statements. Write additional tests if below threshold. No code without tests. This is not optional. Must have unit tests Must have integration tests Must have E2E tests null, empty, invalid types, boundaries, errors, race conditions, large data, special characters No shared state between tests Branches, functions, lines, statements Supabase, Redis, OpenAI, network calls Testing implementation details (internal state) instead of user-visible behavior Tests depending on execution order or shared state Missing edge case tests (only testing happy path) Writing implementation before tests