technical-specification
Technical specification writing for implementation details. Use when documenting how to build a solution (post-decision), API contracts, schemas, and system design. Complements RFC skill which handles decision-making.
What this skill does
# Technical Specification Skill
This skill automatically activates when documenting implementation details for a solution. Unlike RFC (which evaluates options), Tech Specs document **how** to build something when the approach is already decided.
## When This Skill Activates
- Documenting implementation approach after RFC approval
- Writing API specifications and contracts
- Defining database schemas and data models
- Creating system integration specifications
- Documenting component architecture details
- Writing implementation guides for developers
## RFC vs Tech Spec
| Aspect | RFC | Tech Spec |
|--------|-----|-----------|
| **Purpose** | Evaluate options, make decision | Document implementation details |
| **Options Analysis** | Required (min 2) | Not applicable |
| **When Used** | Before decision | After decision (or when no decision needed) |
| **Audience** | Decision makers, stakeholders | Implementers, developers |
| **Lifecycle** | DRAFT → REVIEW → APPROVED → COMPLETED | DRAFT → APPROVED → REFERENCE |
## When to Use Tech Spec (Not RFC)
Use Tech Spec when:
- Decision is already made (via RFC or otherwise)
- Only one viable implementation approach exists
- Documenting API contracts or schemas
- Writing integration specifications
- Creating implementation guides
Use RFC instead when:
- Multiple viable options exist
- Stakeholder buy-in needed
- Decision has cross-team impact
- Choice is costly to reverse
## Tech Spec Document Structure
### Required Sections
1. **Header Metadata**
```yaml
---
tech_spec_id: TS-XXXX
title: [Component/Feature Name]
status: DRAFT | APPROVED | REFERENCE | ARCHIVED
decision_ref: RFC-XXXX # Optional - link to RFC if one exists
author: [Name]
created: YYYY-MM-DD
last_updated: YYYY-MM-DD
---
```
2. **Executive Summary** (1 paragraph)
- What is being built
- Why this approach (brief, reference RFC if applicable)
- Key design decisions
3. **Design Overview**
- High-level architecture
- Component relationships
- Data flow description
4. **Detailed Specifications**
For each component:
- Responsibility
- Technology stack
- Key interfaces
- Implementation notes
5. **Data Model / Schema**
- Entity definitions
- Relationships
- Database schema (if applicable)
- Migration strategy
6. **API Specification**
- Endpoints with methods
- Request/response formats
- Authentication requirements
- Error handling
7. **Security Implementation**
- Authentication mechanism
- Authorization model
- Data protection
- Compliance requirements
8. **Performance Considerations**
- Throughput/latency targets
- Caching strategy
- Optimization approach
- Monitoring metrics
9. **Testing Strategy**
- Unit test requirements
- Integration test scenarios
- Load testing approach
10. **Deployment & Operations**
- Deployment process
- Configuration management
- Monitoring & alerting
- Rollback procedure
11. **Dependencies**
- External services
- Internal components
- Third-party libraries
12. **Implementation Checklist**
- Phased implementation plan
- Milestones with targets
## Tech Spec Lifecycle
```
DRAFT → APPROVED → REFERENCE
↓
ARCHIVED (when superseded or deprecated)
```
### Status Definitions
| Status | Description |
|--------|-------------|
| **DRAFT** | Being written, not yet reviewed |
| **APPROVED** | Ready for implementation |
| **REFERENCE** | Implementation complete, serves as documentation |
| **ARCHIVED** | Superseded or no longer relevant |
## Relationship to RFC
Tech Specs can optionally link to an RFC:
```yaml
decision_ref: RFC-0042 # Links to the decision that led to this spec
```
**When to link:**
- Tech Spec implements an approved RFC
- Want traceability from decision to implementation
**When standalone is fine:**
- Simple feature that didn't need RFC
- External requirement (no decision to make)
- Standard patterns being applied
## Quality Standards
### Completeness Checklist
Before marking APPROVED:
- [ ] All required sections are filled
- [ ] Architecture diagram is included
- [ ] API endpoints are fully specified
- [ ] Data model is complete
- [ ] Security considerations are addressed
- [ ] Deployment process is documented
- [ ] Implementation phases are defined
### Writing Guidelines
1. **Be Specific**
- Include concrete details, not vague descriptions
- Specify exact endpoints, schemas, configurations
2. **Include Examples**
- API request/response examples
- Configuration snippets
- Code patterns to follow
3. **Document Constraints**
- Performance requirements with numbers
- Resource limitations
- Compatibility requirements
4. **Reference Don't Duplicate**
- Link to RFC for decision rationale
- Reference existing documentation
- Avoid copying content that exists elsewhere
## File Naming Convention
```
TS-XXXX-<short-description>.md
```
Examples:
- `TS-0001-user-authentication-api.md`
- `TS-0015-payment-integration.md`
- `TS-0042-cache-layer-design.md`
## Directory Structure
```
tech-specs/
├── draft/ # Work in progress
├── approved/ # Ready for implementation
├── reference/ # Implementation complete
└── archive/ # Superseded/deprecated
└── YYYY/
```
## Integration with CTO Architect Workflow
The CTO Architect uses this skill for:
1. **Post-RFC Implementation Planning**
- RFC approved → Create Tech Spec for details
- Document the "how" after deciding the "what"
2. **Standalone Specifications**
- Simple features without RFC
- API contracts and schemas
- Integration specifications
3. **Delegation to Specialists**
- Tech Spec provides context for specialist agents
- Clear specifications enable parallel development
## Commands
| Command | Description |
|---------|-------------|
| `/create-tech-spec <name>` | Create new Tech Spec from template |
| `/list-tech-specs` | List all Tech Specs with status |
| `/tech-spec-status <id>` | View or update Tech Spec status |
## References
- Template: `./references/tech-spec-template.md`
- Checklist: `./references/tech-spec-checklist.md`
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.