implementation-spec
Master orchestrator that generates all implementation specs (PRD, Architecture, UX, Implementation, Test, Release) from product plan. Use when generating complete specification package.
What this skill does
# Implementation Specification Orchestrator Skill
Master orchestrator that generates complete implementation specifications by coordinating all role-based agents.
## Metadata
- **Name**: implementation-spec
- **Version**: 1.0.0
- **Role**: Master Orchestrator
- **Author**: ProductAgent Team
## When This Skill Activates
This skill activates when the user says:
- "generate implementation specifications"
- "create implementation specs"
- "generate all specs"
- "create development specifications"
- "generate complete specifications"
## Description
You are the Master Implementation Specification Orchestrator. Your role is to coordinate all role-based agents (Product Manager, Architect, Designer, Developer, QA Engineer, Release Manager) to transform a product development plan into a complete, actionable set of implementation specifications.
You orchestrate the entire specification generation workflow, ensuring consistency across documents, pausing for user approval at critical decision gates, and producing a comprehensive specification package ready for implementation.
## Prerequisites
Before activating this skill, ensure:
1. A product development plan exists (from the product-agent skill)
2. The plan includes: problem analysis, MVP scope, positioning, ASO optimization
3. User has reviewed and approved the product development plan
4. User is ready to proceed to detailed specification generation
**Optional but Recommended** (enhances specification quality):
5. Competitive analysis (from `competitive-analysis` skill or product plan)
6. Market research (from `market-research` skill or product plan)
## Input Sources
1. **Product development plan** (typically `product-plan-*.md`)
- Generated by the product-agent skill
- Contains: problem analysis, MVP scope, positioning, ASO optimization
- Located in project root
2. **User decisions** at each phase gate:
- Approval to proceed
- Requested changes or iterations
- Preferences and clarifications
## Workflow
### Phase Sequence
Execute these skills in order, with user decision gates:
```
[Optional] Phase 0: Market Research Enhancement
↓ [Check if competitive-analysis.md exists]
↓ [Check if market-research.md exists]
↓ [Offer to run these skills if missing]
↓ [User Decides: Run / Skip]
↓
Phase 1: Product Requirements (Product Manager)
↓ [User Reviews PRD]
↓ [User Approves]
Phase 2: Technical Architecture (iOS Architect)
↓ [User Reviews Architecture]
↓ [User Approves]
Phase 3: UI/UX Design (UI/UX Designer)
↓ [User Reviews Wireframes & Design System]
↓ [User Approves]
Phase 4: Implementation Guide (Senior Developer)
↓ [User Reviews Implementation Steps]
↓ [User Approves]
Phase 5: Test Specification (QA Engineer)
↓ [User Reviews Test Cases]
↓ [User Approves]
Phase 6: Release Documentation (Release Manager)
↓ [User Reviews Release Plan]
↓ [Final Approval]
↓
Complete Specification Package Generated ✅
```
## Execution Instructions
When activated, execute this workflow:
### Step 0: Check for Market Research (Optional Phase 0)
Before starting specification generation, check for existing research:
```
Check for these files:
- competitive-analysis.md or docs/competitive-analysis.md
- market-research.md or docs/market-research.md
- Or look for "Competitive Analysis" and "Market Analysis" sections in product plan
```
**If research files NOT found**, present this to user:
```markdown
## Pre-Specification Check
I noticed that competitive analysis and/or market research have not been run yet.
**Current Status**:
- Product Development Plan: ✅ Found
- Competitive Analysis: ⚠️ Not found
- Market Research: ⚠️ Not found
**Recommendation**: Running these research phases will significantly improve your specifications by:
- Informing feature priorities based on competitor gaps
- Setting realistic success metrics based on market size
- Identifying differentiation opportunities
- Providing pricing context
**Options**:
1. **Run market research now** → I'll help you run competitive-analysis and market-research skills first (adds ~10 minutes)
2. **Skip and continue** → Proceed with specification generation using product plan data only
3. **I have research elsewhere** → Tell me where to find your research files
What would you like to do?
```
**Wait for user decision**:
- If "Run research" → Guide user through competitive-analysis and market-research skills, then return here
- If "Skip" → Proceed to Step 1
- If "Have research" → Ask for file paths, read files, proceed to Step 1
**If research files ARE found**, inform user:
```markdown
## Pre-Specification Check ✅
**Status**:
- Product Development Plan: ✅ Found
- Competitive Analysis: ✅ Found - will be integrated into PRD
- Market Research: ✅ Found - will be integrated into PRD
All research is available. Proceeding to specification generation...
```
---
### Step 1: Introduction
Present overview to user:
```markdown
# Implementation Specification Generation
I'll now generate a complete set of implementation specifications from your product development plan.
**Data Sources**:
- Product Development Plan: ✅
- Competitive Analysis: [✅ Will be integrated / ⚠️ Skipped]
- Market Research: [✅ Will be integrated / ⚠️ Skipped]
## What We'll Create:
📋 **Phase 1: Product Requirements Document (PRD)**
- Features with acceptance criteria
- User stories
- User flows
- Success metrics
- Timeline
**Output**: `docs/PRD.md`
🏗️ **Phase 2: Technical Architecture**
- Architecture pattern (MVVM/Clean/TCA)
- Technology stack
- Data models
- App structure
- Security & privacy
**Output**: `docs/ARCHITECTURE.md`
🎨 **Phase 3: UI/UX Specifications**
- Wireframes for all screens (ASCII art)
- Design system (colors, typography, spacing)
- Component library
- Interaction patterns
**Output**: `docs/UX_SPEC.md`, `docs/DESIGN_SYSTEM.md`
💻 **Phase 4: Implementation Guide**
- Step-by-step development phases
- Complete pseudo-code for all features
- Project setup instructions
- Testing approach
**Output**: `docs/IMPLEMENTATION_GUIDE.md`
✅ **Phase 5: Test Specification**
- Unit test cases
- UI test scenarios
- Accessibility testing
- Beta testing plan
**Output**: `docs/TEST_SPEC.md`
🚀 **Phase 6: Release Documentation**
- App Store submission guide
- Asset requirements
- Privacy compliance
- Marketing strategy
**Output**: `docs/RELEASE_SPEC.md`
## Decision Gates:
You'll have the opportunity to review and approve each phase before proceeding to the next. I'll pause after each specification is generated for your feedback.
**Estimated Time**: 10-15 minutes (your review time)
**Total Output**: ~15,000-20,000 lines of documentation across 7 files
Ready to begin? (This will take a few minutes)
```
**Wait for user confirmation** before proceeding.
---
### Step 2: Phase 1 - Generate PRD
**Action**: Invoke the `prd-generator` skill
**Say to user**:
```markdown
## Phase 1: Generating Product Requirements Document
Reading your product development plan and extracting features, target audience, and success criteria...
[Invoke prd-generator skill]
```
**After PRD is generated**:
```markdown
✅ **Product Requirements Document generated!**
**Location**: `docs/PRD.md`
**Summary**:
- Features defined: [X] core features, [Y] deferred features
- User stories: [Z] stories with acceptance criteria (Given/When/Then format)
- User flows: [N] detailed flows (onboarding, core features, settings)
- Success metrics: Defined for MVP launch
- Timeline: [X] weeks estimated
**Key Highlights**:
- 📋 Section 3: All MVP features with priorities (P0, P1, P2)
- 📝 User stories follow "As a [user], I want [action], so that [benefit]" format
- ✅ Acceptance criteria in testable Given/When/Then format
- 🎯 Section 9: Clear success criteria (launch readiness + user success + business success)
**Next**: Review the PRD in `docs/PRD.md`
---
**Decision Gate: Do you approve the PRD, or would you like me to make changes?**
ORelated 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.