القائمة
Use when writing any implementation code - enforces Red-Green-Refactor cycle with no production code without a failing test first
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when ready to implement - selects a GitHub Issue, creates worktree, implements with TDD, verifies, reviews 5x, and creates PR. Numeric argument (e.g. pick-issue 3) is the issue number, not a parallelism count.
Use when you want to be exhaustively questioned about a plan or design until shared understanding is reached - asks one question at a time, traverses the design tree, and proposes a recommended answer for each question
Use to delegate all hands-on work to Codex - plan-writing, implementation, and refactoring. Opus reads, thinks, reviews, and writes docs only.
Use after a PR is opened and you want it merged - waits for CI to pass, marks draft PRs ready, removes the worktree, then merges and cleans up
Use when starting new feature work, adding functionality, or modifying behavior - explores design before implementation, creates plan, PR, and GitHub Issues
Use when encountering test failures, bugs, or unexpected behavior - requires root cause investigation before any fix attempt
| name | tdd |
| description | Use when writing any implementation code - enforces Red-Green-Refactor cycle with no production code without a failing test first |
Enforces Red-Green-Refactor. No production code without a failing test first.
Iron Law: NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST.
If you wrote code before a test, delete it and start over. No exceptions.
Opus does not hand-write implementation code — it delegates the writing to Codex (see the codex skill). Opus owns intent and review; Codex owns thorough execution. This skill is the Red-Green- Refactor discipline that the delegated code must follow. The Iron Law applies regardless of who types it: a failing test must precede the production code.
Move to the next behavior. One cycle at a time.
| Language | Test Command | Watch Mode |
|---|---|---|
| Rust | cargo test | cargo watch -x test |
| Go | go test ./... | - |
| Ruby | bundle exec rspec / bundle exec rake test | bundle exec guard |
| TypeScript | npx vitest run / npx jest | npx vitest |
Detect the project's actual test setup and use the appropriate command.
These are not valid reasons to skip the cycle:
| Excuse | Reality |
|---|---|
| "I'll write tests after" | A test that passes immediately proves nothing |
| "It's just a small change" | Small changes cause big bugs |
| "I already tested manually" | Manual testing is not reproducible |
| "This is too simple to test" | Then the test is trivial to write |
| "I need to see the code first" | The test IS the spec for the code |
If any of these happen, stop and restart the cycle:
