ui-dev:figma-data
This skill should be used when the user asks to "extract Figma design data", "get CSS properties from Figma", "trace prototype chain", "export assets from Figma", "get component variants", or needs exact design values (colors, spacing, typography, interactions) from Figma nodes via API.
What this skill does
# figma-data
Extract precise design data from the Figma REST API — prototype graph traversal (BFS), interactions, exact CSS values, component APIs, and asset export.
## Figma MCP vs API Scripts
Use MCP tools for quick overview and visual confirmation. Use API scripts when exact values matter.
| Need | Use |
| --------------------------------------------------- | -------------------------------------------------------------------------------- |
| Visual reference, approximate code | `get_design_context` (MCP) |
| Screenshot | Do NOT use `get_screenshot` — use `figma-screenshot` skill or API export instead |
| Layer structure overview | `get_metadata` (MCP) |
| Design tokens / variables | `get_variable_defs` (MCP) |
| Exact CSS values (colors, spacing, radius, shadows) | `extract-node-properties.ts` (API) |
| Prototype interactions, transitions, easing | `trace-prototype-chain.ts` + `query-prototype-chain.ts` (API) |
| SVG/PNG asset export | `export-node-images.ts` (API) |
| Component variant props and combinations | `get-component-variants.ts` (API) |
| All pages/frames in a file | `list-file-frames.ts` (API) |
## Recommended Workflow
1. **Overview**: `get_design_context` (MCP) for reference code + screenshot
2. **Structure**: `list-file-frames.ts` to discover all pages/frames
3. **Exact values**: `extract-node-properties.ts` for the node being implemented
4. **Components**: `get-component-variants.ts` if implementing a component with variants
5. **Assets**: `export-node-images.ts` for icons/illustrations as SVG
6. **Interactions**: `trace-prototype-chain.ts` + `query-prototype-chain.ts` for transitions
## Core Principle: Query Only What Is Being Implemented Right Now
Query data on-demand per node. Never bulk-fetch all nodes upfront — each query loads data into context, and unused data wastes tokens.
## Inputs
| Parameter | Required | Description |
| --------- | -------- | --------------------------------------- |
| `fileKey` | Yes | Figma file key (from URL path) |
| `nodeId` | Yes | Node ID (colon or dash format accepted) |
Extract from a Figma URL like `https://www.figma.com/design/<fileKey>/...?node-id=<nodeId>`.
## Mode Selection
Choose **one** mode per invocation. Never run Mode B as a prerequisite for Mode A.
| Situation | Mode |
| ------------------------------------------ | -------------- |
| List all pages/frames in a file | C |
| Figma URL with page/frame node (default) | A |
| Landing page with scroll animations | A |
| Multi-step onboarding flow | A |
| Prototype already traced (reuse JSON) | A (query only) |
| Single button or icon interaction | B |
| Verify if a specific node has interactions | B |
## Mode A: Prototype Graph Trace (default)
### Step 1 — Trace (once per Figma URL)
```bash
${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/trace-prototype-chain.ts \
--file-key <fileKey> --node-id <nodeId> --output <outputPath>
```
BFS-traverses the entire prototype graph from the starting node. Discovers all connected frames by scanning `interactions[].actions[].destinationId` on any node including children (buttons, instances, etc.).
Saves PNG screenshots of all frames to `<output-dir>/screenshots/` and records file paths in the JSON.
After the trace completes, confirm frame counts and JSON path. **Stop here.** Return to implementation and only proceed to Step 2 when a specific node's interaction data is needed.
### Step 2 — Query (on-demand, per-node or full page map)
When actively writing code for a specific node and interaction details are needed:
```bash
${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/query-prototype-chain.ts \
--json-path <path> --node-id <nodeId>
```
To view the full page map with all frame connections:
```bash
${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/query-prototype-chain.ts \
--json-path <path> --node-id map
```
Both colon (`18067:11823`) and dash (`18067-11823`) formats are accepted.
Relay the markdown output directly. Never parse the graph JSON manually.
## Mode B: Single Node Inspection
For quick checks on a single isolated node:
```bash
${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/fetch-figma-node-response.ts \
--file-key <fileKey> --node-id <nodeId>
```
Confirm whether the target node resolved to a real `document` or `null`.
## Mode C: List All Pages and Frames
List every page and top-level frame in a Figma file. Use this to discover all node IDs before tracing a specific chain.
```bash
${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/list-file-frames.ts \
--file-key <fileKey> [--output <outputPath>]
```
Without `--output`, prints JSON to stdout. With `--output`, writes JSON to file and prints summary to stdout.
## Scripts
All scripts are standalone executable TypeScript files with a shebang. Do NOT run them via `bun` — execute them directly (e.g., `${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/trace-prototype-chain.ts --help`).
| Script | Purpose | Input | Output |
| ------------------------------------------------------------------------------ | ------------------------------- | --------------------------------------------------------- | ---------------------- |
| `${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/list-file-frames.ts` | List all pages/frames | `--file-key [--output]` | JSON to stdout or file |
| `${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/extract-node-properties.ts` | Exact CSS-equivalent properties | `--file-key --node-id [--depth] [--output]` | JSON to stdout or file |
| `${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/get-component-variants.ts` | Component variant analysis | `--file-key --node-id [--output]` | JSON to stdout or file |
| `${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/export-node-images.ts` | Export SVG/PNG assets | `--file-key --node-ids --output-dir [--format] [--scale]` | Files to directory |
| `${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/trace-prototype-chain.ts` | BFS prototype graph trace | `--file-key --node-id --output` | JSON file |
| `${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/query-prototype-chain.ts` | Query graph (per-node or `map`) | `--json-path --node-id` | Markdown to stdout |
| `${CLAUDE_PLUGIN_ROOT}/skills/figma-data/scripts/fetch-figma-node-response.ts` | Single node raw fetch | `--file-key --node-id` | JSON to stdout |
## Error Handling
| Error | Cause | Resolution |
| ------------------------------- | ---------------------------------------------------------- | ------------------------------------------ |
| `FIGMA_ACCESS_TOKEN is not set` | Missing eRelated 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.