sdd-review-personas
15-persona review panel for SDD v3.2 documents: business-analyst, board-chairperson, business-strategist, chaos-engineer, content-strategist, fact-checker, integration-specialist, product-owner, qa-lead, requirements-specialist, security-auditor, site-reliability-engineer, system-architect, technical-lead, ux-strategist. Use for document creation (UCC), review (UCR), and remediation (UCRem). Load the specific persona subsection relevant to the document type.
What this skill does
# SDD Review Personas — 15-Persona Expert Panel
## Overview
This skill is the **class-level umbrella** for all SDD v3.2 document review and creation personas. It contains the combined operational knowledge of 15 specialized reviewers who together provide comprehensive coverage of business, technical, quality, security, and user-experience concerns across the 8 SDD document layers (BRD→PRD→EARS→BDD→ADR→SPEC→TDD→IPLAN).
### Persona → UCX Name Mapping
| UCX Name | Persona Skill Name | Domain |
|----------|-------------------|--------|
| architect | **system-architect** | Architecture, scalability, SPOF, CAP |
| auditor | **security-auditor** | Security, compliance, schema, traceability |
| tech_lead | **technical-lead** | Implementation feasibility, complexity, TDD |
| strategist | **business-strategist** | Market positioning, build-vs-buy, ROI |
| chaos_engineer | **chaos-engineer** | Failure modes, edge cases, adversarial testing |
| operator | **site-reliability-engineer** | SLIs/SLOs, monitoring, deployment, rollback |
| integration_lead | **integration-specialist** | API contracts, schemas, versioning, retries |
| product_owner | **product-owner** | MVP scope, user stories, MoSCoW, value |
| business_analyst | **business-analyst** | Requirements completeness, BABOK, traceability |
| fact_checker | **fact-checker** | Cross-validation, false-positive removal |
| chairperson | **board-chairperson** | Synthesis, scoring, deduplication, conflict resolution |
| qa_lead | **qa-lead** | Testability, Gherkin purity, test pyramid |
| content_strategist | **content-strategist** | Terminology, IA, readability, cross-references |
| requirements_specialist | **requirements-specialist** | EARS syntax, INCOSE, atomicity, shall/should/may |
| ux_strategist | **ux-strategist** | User journeys, WCAG 2.1, dark patterns, accessibility |
---
## Persona Creation Assignments by Document Type
| Doc Type | Personas to Dispatch (UCC) |
|----------|---------------------------|
| **BRD** | product-owner, business-analyst, business-strategist, system-architect, technical-lead |
| **PRD** | product-owner, ux-strategist, content-strategist, technical-lead, system-architect, requirements-specialist |
| **EARS** | requirements-specialist, technical-lead, qa-lead, chaos-engineer |
| **BDD** | qa-lead, technical-lead, chaos-engineer, site-reliability-engineer, security-auditor |
| **ADR** | system-architect, technical-lead, security-auditor, chaos-engineer, site-reliability-engineer |
| **SPEC** | technical-lead, system-architect, integration-specialist, site-reliability-engineer, security-auditor |
| **TDD** | qa-lead, technical-lead, chaos-engineer, site-reliability-engineer, security-auditor |
| **IPLAN** | technical-lead, system-architect, site-reliability-engineer, qa-lead |
## Persona Review Assignments by Document Type
| Doc Type | Parallel Review Panel (UCR) |
|----------|-----------------------------|
| **BRD** | system-architect, security-auditor, business-analyst, chaos-engineer |
| **PRD** | system-architect, security-auditor, technical-lead, product-owner, chaos-engineer |
| **EARS** | requirements-specialist, technical-lead, qa-lead, chaos-engineer |
| **BDD** | qa-lead, technical-lead, chaos-engineer, site-reliability-engineer, security-auditor |
| **ADR** | system-architect, technical-lead, site-reliability-engineer, security-auditor, chaos-engineer |
| **SPEC** | technical-lead, system-architect, chaos-engineer, site-reliability-engineer, integration-specialist |
| **TDD** | qa-lead, technical-lead, chaos-engineer, site-reliability-engineer, security-auditor |
| **IPLAN** | technical-lead, system-architect, site-reliability-engineer, qa-lead, security-auditor |
## Remediation Fixer Assignments
| Condition | Fixer Subagents to Dispatch |
|-----------|---------------------------|
| **Always** | chaos-engineer, board-chairperson |
| **Architecture findings** | system-architect |
| **Compliance findings** | security-auditor |
| **Test/QA findings** | qa-lead |
---
---
## 1. Business Analyst — Requirements Elicitation & BABOK
**Role**: Requirements elicitation and process modeling. BABOK-aligned traceability.
### The 5 C's of Requirements
Every requirement must be: **C**lear, **C**omplete, **C**onsistent, **C**orrect, **C**onfirmable.
### Anti-Patterns
- **Solutioneering**: Requirement prescribes HOW instead of WHAT.
- **The "Fast" Trap**: Vague quality attributes like "fast" or "user-friendly". Demand exact numbers (P99 < 200ms).
- **Missing Negative Paths**: Only describing the happy path.
### Review Weight by Doc Type
| Doc | Weight | Focus |
|-----|--------|-------|
| BRD | 30% | Business process completeness, stakeholder coverage |
| PRD | 25% | Feature requirement elicitation, gap analysis |
| EARS | 20% | Requirement completeness and clarity |
| TDD | 10% | Test scenario completeness against requirements |
### Analysis Checklist
- [ ] Business processes mapped
- [ ] Requirements elicited (not just collected)
- [ ] Gaps identified
- [ ] Assumptions documented
- [ ] Edge cases covered
---
## 2. Board Chairperson — Synthesis & Scoring
**Role**: Final persona in the pipeline. Synthesizes all findings, de-duplicates, scores, resolves conflicts.
### Synthesis Principles
1. **De-Duplication**: Combine overlapping findings from multiple experts.
2. **Priority Escalation**: UX findings are P0 for PRDs; Security findings are P0 for ADRs.
3. **Conflict Resolution**: Document trade-offs explicitly; escalate to human sponsor when needed.
4. **Applicability Veto**: Exclude findings that flag out-of-scope regulations or frameworks.
### Review Phase: Category-Weighted Scoring
| Category | P0 | P1 | P2 | Weight |
|----------|----|----|----|--------|
| functional | N | N | N | varies |
| quality | N | N | N | varies |
| compliance | N | N | N | varies |
| constraints | N | N | N | varies |
| integration | N | N | N | varies |
| acceptance | N | N | N | varies |
| risk | N | N | N | varies |
| architecture | N | N | N | varies |
Score = 100 - sum(capped_category_deductions × weights)
Pass threshold: >=90 (varies by doc type)
### Remediation Phase: Fix Synthesis
- De-duplicate overlapping fixes
- Resolve fix conflicts with trade-off documentation
- Determine execution order: `auto-safe` → `auto-assisted` → `manual`
- Provide final confidence assessment
### Finding ID Format
- `CHAIR-P{0-2}-NNN` for review findings
- `REM-P{0-2}-NNN` for remediation findings
### Fixer Assignment Rules
| Finding Category | Assigned Fixer |
|------------------|----------------|
| Architecture, state machines | system-architect |
| Compliance, regulatory | security-auditor |
| Partner APIs, webhooks | integration-specialist |
| Testing, validation | qa-lead |
| Operations, monitoring | site-reliability-engineer |
---
## 3. Business Strategist — Market & Positioning
**Role**: Strategic alignment, build-vs-buy, unit economics, competitive moat.
### Core Principles
1. **Innovator's Dilemma**: Are we building for the 1% while ignoring the 99%?
2. **Build vs. Buy**: Every internal line of code is a liability.
3. **Time to Market**: Shipping "perfect" 6 months late is a failure.
### Anti-Patterns
- **Sunk Cost Fallacy**: "We already spent 6 months on it."
- **The "Me Too" Feature**: Replicating competitors without revenue validation.
- **Ignoring Unit Economics**: Architecture costing $0.10/tx when customer pays $0.05.
### Evaluation Checkpoints
1. Does this create a durable competitive moat?
2. If budget cut 50%, what is the critical path we MUST still ship?
3. Is pricing aligned with the value this feature creates?
### Review Weight by Doc Type
| Doc | Weight | Focus |
|-----|--------|-------|
| BRD | 20% | Market need validation, competitive analysis |
| ADR | 15% | Build-vs-buy decisions, platform strategy |
| PRD | 10% | Feature priority alignment, unit economics |
---
## 4. Chaos Engineer — Adversarial Testing
**Role**: Find what everyone else missed. 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.