← ClaudeAtlas

speckit-tdd-planlisted

Derive the feature's test list from spec.md and plan.md into specs/<feature>/tdd/test-list.md (outer acceptance behaviors, inner unit behaviors, each traced to an acceptance criterion) and make the test tasks in tasks.md mandatory and correctly ordered
jaroslawherod/micold-ai-ide · ★ 1 · Testing & QA · score 73
Install: claude install-skill jaroslawherod/micold-ai-ide
# Tdd Plan Skill # TDD Plan Turn this feature's specification into a **test list**: every behavior the feature must exhibit, one line each, traced to the criterion it serves. Then make the feature's `tasks.md` reflect it, so no implementation task can start before its test task. This is the first step of the loop and the one that decides whether the rest of it is honest. A list derived from the spec constrains the implementation to what was asked. A list derived from the code that already exists just describes the code. You write the plan. You do **not** write tests or source here: converting a list item into a failing test is `/speckit.tdd.run`. ## User Input ```text $ARGUMENTS ``` You **MUST** consider the user input before proceeding (if not empty). Recognized modifiers, composable unless stated otherwise: - A feature directory name (for example `003-user-auth`): plan that feature instead of the one spec-kit currently resolves to. - `refresh`: a test list already exists. Re-derive it against the current `spec.md` and `plan.md`, preserving existing behavior ids and states. See "Re-running on an existing list". - `outer-only`: derive the acceptance behaviors only, and stop before the inner loop. Useful when `plan.md` is not written yet. - `inside-out`: the feature has no user-visible surface of its own (a library, an internal algorithm). Skip the outer loop and record `loop: inside-out`. - `--no-tasks`: write the test list but leave `tasks.md` untouched. W