From blueprint
TDD variant of plan-review — restructures the plan to follow Red/Green/Refactor cycle. Triggers on "/bp-tdd-review", "/tdd-review", "tdd plan", "test-driven review", "red green refactor", or any request to prepare a plan for TDD execution. Also triggers on "tdd mode", "write tests first", "test-first approach", "tdd planning", "prepare plan for TDD", or "write tests before code". Injects Phase 0 (all tests written first, failing), GREEN implementation phases, and final Coverage & Refactor phase targeting 100% coverage.
npx claudepluginhub skaisser/blueprint-pluginThis skill uses the workspace's default tool permissions.
Read `blueprint/.config.yml` → `language`. If `auto`, detect from the user's messages. All generated content MUST be in the detected language. Skill instructions stay in English — only output changes.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Analyzes competition with Porter's Five Forces, Blue Ocean Strategy, and positioning maps to identify differentiation opportunities and market positioning for startups and pitches.
Share bugs, ideas, or general feedback.
Read blueprint/.config.yml → language. If auto, detect from the user's messages. All generated content MUST be in the detected language. Skill instructions stay in English — only output changes.
TDD variant of /plan-review. Restructures the plan to follow Red/Green/Refactor: all tests written first (failing), implementation makes them pass, coverage phase reaches 100%.
This skill ONLY restructures the plan file — NEVER write actual test or implementation code.
/plan → /bp-tdd-review → [clear context] → /plan-approved → /plan-check → /pr → /finish
references/team-execution.md at Step 1. NEVER fabricate plan details.mcp__sequential-thinking__sequentialthinking at Step 1. NEVER skip.[H]/[S]/[O]. NEVER leave unmarked tasks.Run these simultaneously:
blueprint meta — get plan metadatareferences/team-execution.md for execution mode selectionThen use mcp__sequential-thinking__sequentialthinking to validate completeness, dependencies, testability, file conflicts. During validation, extract a list of all models, endpoints, services, and features from the plan — this list drives Phase 0 test naming.
DO NOT proceed without reading the plan file AND team-execution.md.
Add ${CLAUDE_SESSION_ID} to the plan file:
`${CLAUDE_SESSION_ID}` DD/MM/YYYY HH:MM - TDD review — `claude -r ${CLAUDE_SESSION_ID}`sessions: array: - id: "${CLAUDE_SESSION_ID}" date: "DD/MM/YYYY HH:MM" note: "TDD review"Mark ALL tasks: [H] (simple), [S] (medium), [O] (complex/rare). Default to [H].
Insert Phase 0 at TOP of Phases section. Derive test class names directly from the plan's models, endpoints, and features extracted in Step 1. Each test task must target a specific entity from the plan.
Example (adapt to actual plan content):
### Phase 0: Write All Tests (RED)
> **TDD:** Write ALL tests before any implementation. Tests MUST fail at the end of this phase.
- [ ] [S] Write Feature tests: CreateOrderTest, UpdateOrderStatusTest (from Phase 1 tasks)
- [ ] [S] Write Unit tests: OrderServiceTest, PricingCalculatorTest (from Phase 2 tasks)
- [ ] [H] Run tests → verify ALL fail (failures expected)
- [ ] [H] Commit: `test: add failing tests for [feature] (RED)`
Naming rule: For each implementation task in the plan that produces testable behavior, create a corresponding test task in Phase 0. Use the format [Model]Test, [Feature]Test, or [Endpoint]Test — derived from the plan, never generic placeholders.
Add (GREEN) annotation to each implementation phase.
After annotating, verify 1:1 mapping: Walk through every Phase 0 test task and confirm there is a GREEN implementation task that will make those tests pass. If a test task has no corresponding implementation task, add one. If an implementation task has no corresponding RED test, add a test task to Phase 0. Document the mapping as a comment block in the plan:
<!-- RED/GREEN mapping:
Phase 0: CreateOrderTest → Phase 1: Create Order model + migration + controller
Phase 0: OrderServiceTest → Phase 2: Implement OrderService
-->
### Phase N+1: Coverage & Refactor (REFACTOR)
> **TDD:** Target 100% coverage on files touched by this feature.
- [ ] [S] Run coverage — identify uncovered lines
- [ ] [S] Write additional tests for uncovered branches
- [ ] [H] Confirm all green
- [ ] [H] Run code formatting
- [ ] [H] Commit: `test: complete 100% coverage (REFACTOR)`
Phase 0 (RED) is ALWAYS Round 1. Coverage is ALWAYS last round. Implementation phases follow standard mode selection.
Update plan header:
> **Mode:** TDD
> **Coverage Target:** 100%
> **Status:** Approved
git add blueprint/ && git commit -m "plan: tdd-review NNNN-<description>"
STOP. Use AskUserQuestion:
Use $ARGUMENTS as plan file path if provided.