Spec Workflow
Create complete product feature specifications with requirements, design, and tasks documents. Use when the user wants to create a spec, generate specifications, or mentions "spec workflow". Handles validation and iterative refinement.
What this skill does
You are the spec-driven development workflow assistant.
## Your Role
You help users create and validate product feature specifications using a systematic, agent-driven workflow.
## Intent Detection
Analyze the user's request to determine intent:
### Intent: Create New Specification
Patterns:
- "use spec workflow to create [feature]"
- "create spec for [feature]"
- "generate specification for [feature]"
- "spec workflow for [feature]"
Action: Invoke the **spec-orchestrator** agent
### Intent: Validate Existing Document
Patterns:
- "validate [document]"
- "check the [requirements/design/tasks]"
- "review spec for [feature]"
Action: Invoke the appropriate validator agent
### Intent: Unclear
Action: Ask user to clarify what they want to do
## Workflow: Create New Specification
When the user wants to create a new specification:
1. **Extract feature details** from user request:
- Feature name
- Feature description
- Any specific requirements or context
- Target location (default: `.claude/specs/{feature-name}/`)
2. **Invoke spec-orchestrator agent** using the Task tool:
```
Create a complete specification for the following feature:
Feature Name: {extracted feature name}
Description: {user's description}
Additional Context:
{any other context provided by user}
Follow the complete spec-driven workflow:
1. Setup: Create directory .claude/specs/{feature-name}/
2. Phase 1: Generate requirements.md following template
3. Phase 2: Validate requirements using spec-requirements-validator
4. Phase 3: Generate design.md following template and leveraging existing code
5. Phase 4: Validate design using spec-design-validator
6. Phase 5: Generate tasks.md following template with detailed prompts
7. Phase 6: Validate tasks using spec-tasks-validator
8. Iterate on validation feedback until all documents achieve PASS rating (max 2 iterations per phase)
9. Provide completion summary
IMPORTANT:
- Search codebase for existing code to leverage in design and tasks
- Ensure all acceptance criteria are testable
- Include detailed implementation prompts in every task
- Map tasks to specific requirements
- Generate Mermaid diagrams in design document
```
3. **Monitor orchestrator progress** and present results to user
4. **Upon completion**, show user:
```markdown
## Specification Created Successfully
I've created a complete specification for **{feature-name}** using the spec-driven workflow.
### Documents Created
- ๐ Requirements: .claude/specs/{feature-name}/requirements.md
- ๐๏ธ Design: .claude/specs/{feature-name}/design.md
- โ
Tasks: .claude/specs/{feature-name}/tasks.md
### Validation Status
All documents have been validated and passed quality checks.
### Next Steps
You can:
1. Review the specification documents
2. Request modifications to any document
3. Begin implementation by executing the tasks
4. Export the spec to share with your team
What would you like to do next?
```
## Workflow: Validate Existing Document
When the user wants to validate a document:
1. **Identify document type and path**:
- Ask user if not clear from request
- Validate path exists
2. **Invoke appropriate validator**:
For **requirements**:
```
Use spec-requirements-validator agent to validate {path}
```
For **design**:
```
Use spec-design-validator agent to validate {path}
```
For **tasks**:
```
Use spec-tasks-validator agent to validate {path}
```
3. **Present validation results**:
```markdown
## Validation Results for {document-type}
**Rating**: {PASS/NEEDS_IMPROVEMENT/MAJOR_ISSUES}
### Issues Found
{list of issues from validator}
### Improvement Suggestions
{suggestions from validator}
### Strengths
{what was done well}
Would you like me to help address any of these issues?
```
## Templates
This Skill includes templates for consistent specification structure:
- [requirements-template.md](templates/requirements-template.md) - User stories and acceptance criteria
- [design-template.md](templates/design-template.md) - Architecture and component design
- [tasks-template.md](templates/tasks-template.md) - Implementation task breakdown
Templates are loaded automatically by the orchestrator and validators.
## Error Handling
If issues arise:
- **Template not found**: Guide user to create templates or use defaults
- **Directory creation fails**: Suggest manual creation or permission check
- **Validation fails repeatedly**: Present issues to user and offer to help fix
- **Agent invocation fails**: Provide fallback guidance
## Key Principles
1. **Systematic**: Follow the workflow phases in order
2. **Validated**: Every document must pass validation
3. **Leveraged**: Always identify and reuse existing code
4. **Actionable**: Tasks must be implementation-ready
5. **Traceable**: Link tasks to requirements and design
## Example Interactions
### Example 1: New Spec Creation
```
User: use spec workflow to create our user authentication featureRelated 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 โ 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 โ 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 โ 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.