task-decomposition
Break down complex tasks into parallel workstreams for efficient execution. Use when planning multi-component features, large refactors, or any work that benefits from parallelization.
What this skill does
This skill provides methodology for decomposing complex tasks into independent, parallelizable units that can be executed by multiple engineers simultaneously.
## When to Invoke This Skill
Automatically activate for:
- Complex features requiring multiple components
- Large refactoring spanning many files
- Multi-domain work (frontend + backend + database)
- Any task where "this could be parallelized" applies
- Planning sprints or implementation roadmaps
## Task Decomposition Principles
### 1. Independence First
Tasks must be independent to run in parallel:
```
GOOD: Each task can complete without waiting
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ Task A: Auth UI │ │ Task B: Auth API│ │ Task C: DB Schema│
│ (no deps) │ │ (no deps) │ │ (no deps) │
└─────────────────┘ └─────────────────┘ └─────────────────┘
BAD: Sequential dependency chain
Task A → Task B → Task C (no parallelism possible)
```
### 2. Clear Boundaries
Each task must have:
- **Single responsibility**: One deliverable per task
- **Defined inputs**: What data/context is needed
- **Expected outputs**: What artifact is produced
- **Acceptance criteria**: How to verify completion
### 3. Right-Sized Tasks
| Size | Duration | Complexity | Assignment |
|------|----------|------------|------------|
| Small | < 30 min | Single file, routine | Junior engineer |
| Medium | 30-60 min | Multi-file, some decisions | Senior engineer |
| Large | 1-2 hours | Cross-cutting, architectural | Lead or split further |
**Rule**: If a task is "Large", decompose it further.
## Decomposition Framework
### Step 1: Identify Domains
Map the work to distinct domains:
```
Feature: User Authentication
├── Frontend Domain
│ ├── Login form component
│ ├── Registration flow
│ └── Password reset UI
├── Backend Domain
│ ├── Auth middleware
│ ├── JWT token service
│ └── User validation
├── Data Domain
│ ├── User schema
│ ├── Session storage
│ └── Migration scripts
└── Infrastructure Domain
├── OAuth provider setup
└── Environment config
```
### Step 2: Map Dependencies
Create dependency graph:
```
[DB Schema] ──┬──> [Auth Middleware] ──> [Integration Tests]
│
├──> [JWT Service]
│
└──> [User Validation]
[Login UI] ────────────────────────────> [E2E Tests]
[Registration UI] ─────────────────────> [E2E Tests]
```
### Step 3: Identify Parallel Lanes
Group independent tasks into lanes:
```
Lane 1 (Backend) Lane 2 (Frontend) Lane 3 (Infra)
───────────────── ───────────────── ─────────────────
[DB Schema] [Login UI] [OAuth Setup]
│ [Registration UI] [Env Config]
▼ [Reset UI]
[Auth Middleware]
[JWT Service]
[User Validation]
```
### Step 4: Define Integration Points
Where lanes must synchronize:
```
Sync Point 1: API Contract
- Backend exposes POST /auth/login
- Frontend implements against contract
- Both can develop in parallel with mock
Sync Point 2: Integration Testing
- All lanes complete
- Run integration test suite
- Fix cross-cutting issues
```
## Task Template
Use this template for each decomposed task:
```markdown
## Task: [Clear, action-oriented title]
**Lane**: [Backend | Frontend | Infra | Data]
**Size**: [Small | Medium]
**Dependencies**: [None | Task IDs that must complete first]
### Context
[1-2 sentences on why this task exists]
### Deliverables
- [ ] [Specific artifact 1]
- [ ] [Specific artifact 2]
### Acceptance Criteria
- [ ] [Measurable criterion 1]
- [ ] [Measurable criterion 2]
- [ ] Tests pass
- [ ] Linting clean
### Notes
[Any implementation hints or decisions already made]
```
## Parallelization Patterns
### Pattern 1: Component Parallel
Split by UI component when each is independent:
```
/leader --team-size=3 --mode=parallel
Task 1: Build LoginForm component
Task 2: Build RegistrationForm component
Task 3: Build PasswordResetForm component
```
### Pattern 2: Layer Parallel
Split by architectural layer:
```
/leader --team-size=3 --mode=parallel
Task 1: Implement API endpoints (backend)
Task 2: Implement UI components (frontend)
Task 3: Set up infrastructure (devops)
```
### Pattern 3: Hybrid
Critical path sequential, supporting work parallel:
```
/leader --team-size=3 --mode=hybrid
Sequential (Critical Path):
Task 1: Design database schema
Task 2: Implement core API
Parallel (After Task 1):
Task 3: Build UI components
Task 4: Write integration tests
Task 5: Set up monitoring
```
## Anti-Patterns to Avoid
### Over-Decomposition
```
BAD: 20 tiny tasks that have coordination overhead
GOOD: 3-5 meaningful tasks per engineer
```
### Hidden Dependencies
```
BAD: "Task B assumes Task A's schema design"
GOOD: "Task B depends on Task A (schema must be finalized)"
```
### Unclear Ownership
```
BAD: "Someone should handle auth"
GOOD: "Engineer 2 owns auth middleware (Task B)"
```
### Missing Integration Plan
```
BAD: 5 parallel tasks with no sync point
GOOD: Parallel tasks + defined integration checkpoint
```
## Output Format
When decomposing tasks, produce:
```markdown
## Task Decomposition: [Feature Name]
### Overview
- Total tasks: N
- Parallel lanes: M
- Critical path: [sequence]
- Estimated parallelism: X%
### Dependency Graph
[ASCII diagram showing task relationships]
### Task Breakdown
#### Lane 1: [Domain]
| ID | Task | Size | Deps | Engineer |
|----|------|------|------|----------|
| T1 | ... | Medium | None | Senior 1 |
| T2 | ... | Small | T1 | Senior 1 |
#### Lane 2: [Domain]
| ID | Task | Size | Deps | Engineer |
|----|------|------|------|----------|
| T3 | ... | Medium | None | Senior 2 |
### Integration Points
1. After T1, T3: API contract validation
2. After all: Full integration test
### Execution Plan
Phase 1: T1, T3, T5 (parallel)
Phase 2: T2, T4 (parallel, after Phase 1)
Phase 3: Integration (sequential)
```
## Checklist
Before finalizing decomposition:
- [ ] Each task has single responsibility
- [ ] Dependencies are explicit (not assumed)
- [ ] No task exceeds "Medium" size
- [ ] Integration points defined
- [ ] Ownership is clear
- [ ] Acceptance criteria are testable
- [ ] Critical path identified
- [ ] Parallelism opportunities maximized
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.