superwall-editor
Build and edit live Superwall paywalls from the CLI. Attach to a running browser editor session using a pairing code, list the tools the browser exposes right now, and invoke them. Covers native sw-* elements, editing workflow, design standards, and the attach/call/release lifecycle. Use whenever the user wants to design, build, modify, or review a Superwall paywall, onboarding, or web2app flow.
What this skill does
# Superwall Paywall Editor Paywalls are built in a browser editor that exposes its tools over an authenticated relay. This skill drives that relay from the CLI — the exact same surface the MCP gateway uses — so every tool you invoke runs inside the live browser session the user has open. ## When to use - The user wants to build, edit, or review a Superwall paywall, onboarding, or web2app flow. - The user pastes a pairing code and asks you to take over editing. - The user asks "what tools can you run right now?" — discover them via the browser, not from memory. ## Start here: attach, then discover Never assume a tool name or signature from memory. The browser is the source of truth and its tool set changes across releases. Preferred API launch flow: 1. Create an auto-expose URL: `scripts/sw-editor.sh expose --application-id <id> --paywall-id <id> --agent-name <agent> --open --wait` 2. Ask the user to complete browser authorization if prompted. The editor auto-exposes; do not ask them to click the expose button. 3. Discover what is available right now: `scripts/sw-editor.sh tools` 4. Invoke tools: `scripts/sw-editor.sh call <tool-name> --args '<json>'` Fallback manual flow: 1. Ask the user for the **pairing code** shown in the editor UI. 2. Attach: `scripts/sw-editor.sh attach <pairing-code>` 3. Continue with `tools` and `call`. Full CLI reference: [references/cli.md](references/cli.md). ## How to build and edit - Workflow, build order, and when to use which tool: [references/workflow.md](references/workflow.md) - Native `sw-*` elements (multiple-choice, indicator, drawer, picker, lottie, navigation): [references/native-elements.md](references/native-elements.md) - Design standards, review checkpoints, typography, and conversion principles: [references/design.md](references/design.md) ## Orchestration rules - Always establish an attachment before editing. Use `expose --open --wait` when possible, otherwise use `attach <pairing-code>`. `tools`, `call`, `status`, `release` all require an attached session. - Prefer `expose --open --wait` when you have `SUPERWALL_API_KEY`, an application id, and a paywall id. It uses the same relay as manual pairing but removes the human pairing-code step. - Before calling a tool you have not used this session, run `tools` to confirm it exists and to read the current parameter schema. Tools are defined in the browser bundle — an updated editor ships new or renamed tools without any change to this skill. - Use `get_screenshot` (if present in the tool list) every 2–3 modifications to verify. Don't fly blind. - Prefer semantic tools (`update_styles`, `set_text_content`, `set_dynamic_value`, `move_nodes`) over re-running `write_html` on existing structure. See `references/workflow.md`. - Prefer native `sw-*` elements over hand-rolled `<div>` recreations whenever the UI represents a semantic control. See `references/native-elements.md`. - When parsing CLI output, use `jq` — never Python. Example: `sw-editor.sh call get_subtree --args '...' | jq -r '.content[0].text'` - Release when the user is done: `scripts/sw-editor.sh release`. ## When things go wrong - `session_not_ready`: the browser disconnected or reloaded. Ask the user to bring the editor tab back, then re-attach (the pairing code rotates — they'll need to read you the new one). - `session_locked`: another client is already attached. The user either attached from another MCP client, or a previous CLI attachment wasn't released. They can detach from the editor UI and you can retry. - `unauthorized`: the controller token is stale — re-attach with a fresh pairing code. - `attach_failed: provide a valid current pairingCode`: pairing codes expire after ~10 minutes and rotate on detach. Ask the user to show you the current one.
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.