writing-rfc
Write an RFC or design doc — summary-first, with goals/non-goals, real alternatives, drawbacks, and open questions. Use when proposing a technical change for review, writing a design doc, or documenting a system or feature proposal before building it.
What this skill does
# RFC / Design Doc Writing An RFC argues a proposal and its alternatives before you build. It is for a change worth thinking through in the open. (For recording a decision already made, use `writing-adr`; for general technical writing principles, `writing-technical`.) ## The rule that governs everything **Lead with the answer (BLUF).** The Summary states the proposal in full; a reader who stops there still knows what and why. Don't make reviewers excavate the point. **Honesty is the structure, not a footnote.** The Alternatives, Drawbacks, and Open Questions sections are where the document earns trust. A proposal with no stated downsides reads as unconsidered, not as strong. Steelman what you rejected. ## Skeleton 1. **Title** — `RFC-NNN: <imperative summary>`. 2. **Status** — Draft / Under review / Accepted / Rejected · date · author. 3. **Summary** — the proposal in 3–5 sentences. Self-contained. 4. **Motivation / Problem** — concrete, with the symptom or metric that forced it. 5. **Goals & Non-goals** — bound the scope explicitly. Non-goals prevent scope creep and review noise; they are not optional. 6. **Proposed design** — the mechanism in plain language. Define jargon; prefer a small worked example or diagram. Quantify (latency, cost, throughput). 7. **Alternatives considered** — real options, each with an honest why-not. Not strawmen. The reader should trust you argued against yourself. 8. **Drawbacks / Risks** — what this costs, what could go wrong, blast radius. 9. **Open questions** — what you don't know yet, and what evidence would resolve each. 10. **Rollout / migration** — steps, fallbacks, and how you'll know it worked. ## Filling it well - Every claim attached to a number or precedent — not "faster," but "4× write spike at launch, drains in minutes." - Headers are the skeleton above; keep them so reviewers can navigate by convention. - A non-goal that says what you're explicitly *not* solving is worth a paragraph of prevented debate. - For open questions, name the experiment or data that would settle each one. End with the question that decides whether to ship at all. - Rollout should let a reader reverse the change: fallback, rollback, verification. ## Checklist - [ ] Summary is self-contained and first. - [ ] Problem is concrete, with a metric or symptom. - [ ] Goals **and** non-goals are explicit. - [ ] Alternatives are real and steelmanned, each with a why-not. - [ ] Drawbacks, risks, blast radius named. - [ ] Open questions list what would resolve them. - [ ] Rollout includes fallback and verification. - [ ] Claims quantified; jargon defined; links to related RFCs/ADRs/tickets.
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.