architecture-readiness
Use this skill for requirements elicitation, discovery interviews, and creating or evaluating Product Owner Specifications documenting business requirements before architecture design
What this skill does
# Architecture Readiness Skill
## Description
This skill helps Product Owners document business requirements and context before architecture design begins. It provides templates and guidance for creating Product Owner Specifications that feed into technical ARCHITECTURE.md documents.
The skill includes four primary functions:
1. **Requirements Elicitation**: Guided discovery interview to surface business requirements when no PO Spec exists
2. **PO Spec Creation**: Templates and guidance for documenting business requirements
3. **PO Spec Evaluation**: Scoring methodology to assess if a PO Spec is ready for architecture team handoff
4. **Async Intake**: File-based requirements extraction from tickets, emails, or documents — produces a gap report for async follow-up
## When to Use This Skill
Invoke this skill when:
- No existing PO Spec is found in the project and the user needs to capture business requirements
- User says they don't know where to start with business requirements
- User asks for requirements discovery, elicitation, or a requirements interview
- User asks to create a Product Owner Specification
- User asks about documenting business requirements for architecture
- User mentions "business context", "product requirements", or "requirements gathering" in relation to architecture
- User wants to prepare business documentation before technical architecture design
- User asks to evaluate or score a Product Owner Specification
- User wants to know if their PO Spec is ready for the architecture team
- User has business context in a file (ticket export, email, requirements doc) and wants to extract a PO Spec
- User says "async intake", "ticket context", "email context", or "intake from file"
- User provides a file path containing business requirements from an external async source
## Files in This Skill
- **REQUIREMENTS_ELICITATION_GUIDE.md**: Structured discovery interview methodology — 4 phases, probing techniques, Discovery Summary, and transition to PO Spec drafting
- **PRODUCT_OWNER_SPEC_GUIDE.md**: Comprehensive guide with 8-section template, examples, and best practices
- **templates/PO_SPEC_TEMPLATE.md**: Quick-start template for creating a new PO Specification
- **PO_SPEC_SCORING_GUIDE.md**: Weighted scoring methodology to evaluate PO Spec readiness (0-10 scale)
- **ASYNC_INTAKE_GUIDE.md**: File-based async intake methodology — extraction rules, keyword indicators, gap report template, and follow-up question generation
## How to Use This Skill
### 1. Async Intake (Non-Interactive)
⛔ **This flow NEVER transitions to elicitation.** It analyzes a file, produces a gap report with email-ready questions, and STOPS. The output is meant to be sent back to the requester asynchronously (email, ticket, Slack).
When business context arrives via ticket, email, or document (not a live conversation):
1. **Locate the context file**: Ask the user for the file path, or detect common patterns (`business-context.*`, `ticket-*.*`, `requirements-*.*`, `email-*.*`)
2. **Read and parse the file**: Load the full content
3. **Load scoring guide**: Read `PO_SPEC_SCORING_GUIDE.md` for the 8-section weighted rubric
4. **Load async intake guide**: Read `ASYNC_INTAKE_GUIDE.md` for extraction methodology and keyword indicators
5. **Map content to 8 PO Spec sections**: Extract what's present, mark what's missing per section
6. **Score against the rubric**: Calculate per-section completeness % and weighted total score
7. **Generate gap report** (`PO_SPEC_GAP_REPORT.md`): Structured markdown containing:
- **Source file**: filename and processing date
- **Extraction summary**: what was found mapped to each of the 8 sections with completeness %
- **Score**: weighted total and per-section breakdown
- **Gap report**: for each section below 75% completeness:
- What's missing (specific sub-criteria from the scoring guide)
- 2-3 ready-to-send questions for the requester
- Priority level (HIGH / MEDIUM / LOW based on section weight)
- **Ready-to-Send Message**: A complete, copyable email/ticket message block with subject line, prioritized gap questions, and sign-off — ready to paste into email, ticket, or Slack (see ASYNC_INTAKE_GUIDE.md for template)
- **Next steps**: "Send the Ready-to-Send Message to the requester → receive answers → re-run async intake with the updated file"
8. **Save gap report**: Write to `PO_SPEC_GAP_REPORT.md` in the project root
9. **If score ≥ 7.5**: Also draft `PRODUCT_OWNER_SPEC.md` from the extracted data using `templates/PO_SPEC_TEMPLATE.md`; flag any inferred values with `[Default — confirm before architecture handoff]`
10. **If score < 7.5**: Save gap report only — do NOT draft a PO Spec, do NOT start elicitation. The gap report with its Ready-to-Send Message is the final output.
### 2. Requirements Elicitation (Interactive)
When this skill is activated and no existing PO Spec is found (or the user requests discovery/elicitation):
1. **Detect existing PO Spec**: Search for `PRODUCT_OWNER_SPEC.md`, `PO_SPEC.md`, `**/po-spec*`, `**/product-owner*`
- If found: offer Evaluation or Creation workflows instead
- If not found: proceed with elicitation
2. **Load the guide**: Read `REQUIREMENTS_ELICITATION_GUIDE.md` fully before starting
3. **Detect language**: Infer from user's first message; ask if ambiguous
4. **Conduct the 4-phase interview**:
- Phase 1 — Foundation (Business Context, Stakeholders)
- Phase 2 — Value & Boundaries (Objectives, Constraints) ← highest weight, invest depth here
- Phase 3 — Behavior (Use Cases, User Stories) ← deepest phase, use case count reflects architecture complexity
- Phase 4 — Experience & Measurement (UX Requirements, Success Metrics)
5. **Produce Discovery Summary**: Structured by all 8 sections with confidence levels and open questions; present for PO confirmation before drafting
6. **Draft PO Spec**: Load `templates/PO_SPEC_TEMPLATE.md`, fill from elicited data, self-score against `PO_SPEC_SCORING_GUIDE.md`
7. **Gap loop if needed**: If score < 7.5, ask targeted follow-ups on weakest sections; re-score; save final as `PRODUCT_OWNER_SPEC.md`
### 3. PO Spec Creation (Template-Guided)
When this skill is activated for document creation:
1. **Read the guide**: Load PRODUCT_OWNER_SPEC_GUIDE.md to understand the 8-section structure
2. **Understand user context**: Ask clarifying questions about their product/feature
3. **Provide appropriate template**:
- For guidance and understanding: Reference PRODUCT_OWNER_SPEC_GUIDE.md
- For quick start: Provide templates/PO_SPEC_TEMPLATE.md
4. **Guide document creation**: Help user fill out each section with business context
5. **Reference mapping**: Explain how PO Spec maps to ARCHITECTURE.md (see guide Section "Mapping to ARCHITECTURE.md")
### 4. PO Spec Evaluation (Score Existing)
When this skill is activated to evaluate a PO Spec:
1. **Read the scoring guide**: Load PO_SPEC_SCORING_GUIDE.md to understand the weighted scoring methodology
2. **Read the PO Spec**: Load the user's Product Owner Specification document
3. **Evaluate each section**: Assess completeness of all 8 sections using the evaluation criteria
4. **Calculate weighted score**: Apply section weights and compute total score (0-10 scale)
5. **Provide detailed feedback**:
- Overall score and readiness interpretation
- Section-by-section breakdown showing completeness %
- Identify gaps in critical sections (Use Cases, Business Constraints, Business Objectives)
- Provide actionable recommendations for improvement
6. **Determine readiness**: Score ≥7.5/10 indicates ready for architecture team handoff
## Key Principles
- **Business-focused**: No technical details or architecture decisions in PO Spec
- **User-centric**: Emphasize user needs, personas, and pain points
- **Measurable**: All goals and success criteria must be quantifiable
- **Constraint-aware**: Document all business constraints (budget, timeline, compliance)
## InteRelated 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.