planning
Translates an approved design specification into a sequenced list of TDD implementation tasks, each representing 2–5 minutes of work. Use after the researching skill produces an approved design.md, before writing any implementation code.
What this skill does
# Planning: Design Spec to Implementation Tasks
Translate an approved design specification into a concrete, ordered list of TDD implementation tasks. Each task is small enough to complete in 2–5 minutes, follows the red → green → commit cycle, and adheres to the `engineering-principles` skill.
Do **NOT** write any implementation code. This skill produces only `plan.md` — the full task list for implementation. Every line of code comes after the plan is approved.
## Quick Start
1. Have an approved `docs/features/<NNN>-<slug>/design.md` ready
2. Invoke this skill: `/planning docs/features/<NNN>-<slug>`
3. Output: `docs/features/<NNN>-<slug>/plan.md` — an ordered list of TDD tasks
## Checklist
You **MUST** use `TodoWrite` to create a task for each item below and complete them in order.
1. **Locate design spec**: Find `docs/features/<NNN>-<slug>/design.md` — derive the feature path from the argument or context.
2. **Read design spec**: Read the full spec: goals, architecture, component breakdown, and implementation notes.
3. **Spawn task-decomposer**: Delegate to the `task-decomposer` agent with the design spec path to produce a draft task list.
4. **Review draft**: Check the draft for task sizing, ordering, and format. Adjust as needed before writing the plan.
5. **Write plan**: Write to `docs/features/<NNN>-<slug>/plan.md` using [templates/plan.md](templates/plan.md).
6. **Spawn plan-reviewer**: Delegate to the `plan-reviewer` agent with the path to `plan.md`. Edit based on its findings.
7. **User review**: Use `AskUserQuestion` to present the plan path; iterate until the user approves.
8. **Commit**: Commit `plan.md` to git using the `git-commits` skill.
## Process Flow
```mermaid
flowchart TD
A([Start]) --> B[Read design.md]
B --> C[Spawn task-decomposer agent]
C --> D[Review & adjust draft]
D --> E[Write plan.md]
E --> F[Spawn plan-reviewer agent]
F --> G[Edit based on findings]
G --> H[User reviews plan.md]
H --> I{Approved?}
I -- Revisions needed --> D
I -- Approved --> J[Commit plan.md]
J --> Z([Done])
```
## Decomposition Guidelines
### What counts as one task
A task is a single verifiable behavior — one function, one method, one endpoint, one data structure. If you cannot write a single test that captures it, it is either too small (merge it) or too large (split it).
**Rule of thumb:**
- One pure function with defined inputs/outputs → one task
- One data structure or type definition → one task (if it has testable logic)
- One API endpoint (routing + handler) → one task
- One integration point (DB query, external call) → one task
- Project scaffolding with no testable logic → bundle into a single setup task and mark as no-test
### Ordering rules
1. **Test infrastructure first** — if the project lacks a test runner or fixtures, task 001 sets them up
2. **Pure functions before consumers** — utilities and helpers before the code that calls them
3. **Data layer before business logic** — models and queries before services
4. **Business logic before transport** — services before controllers and handlers
5. **Happy path before edge cases** — implement the core behavior first, then add error handling in a separate task
### Applying engineering principles
Before writing a task, verify against the `engineering-principles` skill:
- **Single Responsibility** — the test should only assert one thing
- **Encapsulation** — the task's implementation should not leak internal state
- **YAGNI** — only implement what the design spec calls for
- **KISS** — if a task still feels large, split it into simpler steps
If a component in the spec has mixed responsibilities, split it before planning tasks.
## Task Format
Each task in the plan follows this structure:
````
### Task NNN: [Title]
**Files**:
- Create: `path/to/new_file.py`
- Modify: `path/to/existing_file.py`
- Test: `path/to/test_file.py`
- [ ] **Step 1**: Write failing test in `path/to/test_file.py`
```python
def test_[behavior]():
# arrange
# act
result = [function_under_test](...)
# assert
assert result == [expected]
```
- [ ] **Step 2**: Run `<test-command>` — confirm it fails
Expected: `[failure message or assertion error]`
- [ ] **Step 3**: Write minimal implementation in `path/to/new_file.py`
```python
def [name]([params]):
# minimal implementation
pass
```
- [ ] **Step 4**: Run `<test-command>` — confirm it passes
Expected: `✓ [test name]`
- [ ] **Step 5**: Commit using the `git-commits` skill
`git commit -m "<type>(<scope>): <message>"`
````
**Title conventions:**
- Start with an action verb: `add`, `implement`, `create`, `parse`, `validate`, `expose`
- Be specific: `implement parse_token(token)` not `add auth helper`
## Guidelines
- Do not write implementation code — this skill produces `plan.md` only
- If the design spec is missing a test command or tech stack detail, use `AskUserQuestion` before writing the plan
- If a component has no testable behavior (e.g., pure config), mark the task as `no-test` and explain why
- Use `AskUserQuestion` for all user-facing questions and decisions
- Ask one question at a time
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.