ux-usage-guide
This skill should be used after delivering a tool, system, or workflow when the user wants a guide for how to USE it. Trigger when the user says "make a usage guide", "how-to guide", "onboarding guide", "user guide", "explain how to use this", "guide for my teammates", "document how to use it from the UX side", or wants a user-facing overview oriented to what was delivered (not how it was built). Produces ONE self-contained, light, tabbed interactive HTML guide centered on user stories and copy-paste prompts.
What this skill does
# UX Usage Guide (Interactive HTML) After shipping something, produce a guide that teaches a person how to USE it — framed entirely around their experience and the actions they take, not the internals or how it was built. Output is one light, tabbed, self-contained HTML file. ## When to use - A tool/system/workflow was just delivered and the user (or their teammates) needs to learn to operate it. - The user explicitly wants the "how to use" angle, or a teammate-facing onboarding doc. ## The angle (most important) - **User's point of view only.** Document the surfaces the user touches and the moves they make. Never explain architecture, build steps, or implementation — those belong in a build playbook, not here. - **Include internals only when the user must act on them** — e.g. which files they read vs. add to, a setting they toggle, a folder they drop inputs into. Skip everything else. ## Why it works People learn a system by seeing themselves do things in it. User stories plus the exact words to say (copyable) make the guide actionable; a tabbed, terse layout prevents the "reads like a manual" overwhelm that kills usage guides. ## Workflow 1. **Build one self-contained HTML** per `../_shared/single-file-html-conventions.md` (inline CSS/JS, no deps, light/dark). Write it into the repo (usually `docs/`). 2. **Tabbed single-file layout** so only one thing shows at a time. A typical tab set: *Overview · Core moves · What you touch · Good to know · Start.* 3. **Overview tab:** one sentence on what it does + the mental model (the 2–3 surfaces the user interacts through), as icon cards. Nothing dense. 4. **Core moves tab (the centerpiece):** the N things the user actually does, as a card grid. Each card is icon + a one-line *situation*. Tapping a card reveals: the **exact words to say** (copy button), what happens, and what they get. Hiding the prompt behind a tap keeps the surface scannable. 5. **What you touch tab:** a who-owns-what view of the files/surfaces — which ones the user adds to vs. reads vs. co-owns. One-line rows with a small ownership pill; no prose. 6. **Good-to-know tab:** only the few things the user must monitor or respect (a reminder field, a status, a house rule like "no secrets"). Small cards, not paragraphs. 7. **Start tab:** a short getting-started checklist with the user's **real paths baked in** (interactive checkboxes are a nice touch). 8. **Density is a bug.** If the first pass feels heavy, rebuild lighter — fewer words, more whitespace, move detail behind taps. (A too-dense first draft is the common failure; a tabbed terse rebuild fixes it.) ## Content patterns - **Core move card → modal:** situation on the card; "Say this" prompt + numbered "what happens" steps in the popup. Provide a Copy button on the prompt. - **Ownership pills:** `you add` / `you read` / `co-own`, color-coded, on each file row. - **Mental-model strip:** 2–4 labeled chips naming the surfaces (e.g. "Talk to it", "Drop files here", "Browse in <app>"). ## Resources - **`../_shared/single-file-html-conventions.md`** — the shared single-file HTML technique. - **`references/sections.md`** — the recommended tab set, the core-move card schema, and copy-button logic. ## Pitfalls - Do not slip into "how it was built" — that is a different deliverable. - Do not dump every file/setting; include only what the user must act on. - Do not front-load text walls; lead with the moves, hide detail behind interaction.
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.