figma-automation
npx machina-cli add skill davepoon/buildwithclaude/figma-automation --openclawFigma Automation via Rube MCP
Automate Figma operations through Composio's Figma toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/figma
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Figma connection via
RUBE_MANAGE_CONNECTIONSwith toolkitfigma - Always call
RUBE_SEARCH_TOOLSfirst to get current tool schemas
Setup
Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitfigma - If connection is not ACTIVE, follow the returned auth link to complete Figma auth
- Confirm connection status shows ACTIVE before running any workflows
Core Workflows
1. Get File Data and Components
When to use: User wants to inspect Figma design files or extract component information
Tool sequence:
FIGMA_DISCOVER_FIGMA_RESOURCES- Extract IDs from Figma URLs [Prerequisite]FIGMA_GET_FILE_JSON- Get file data (simplified by default) [Required]FIGMA_GET_FILE_NODES- Get specific node data [Optional]FIGMA_GET_FILE_COMPONENTS- List published components [Optional]FIGMA_GET_FILE_COMPONENT_SETS- List component sets [Optional]
Key parameters:
file_key: File key from URL (e.g., 'abc123XYZ' from figma.com/design/abc123XYZ/...)ids: Comma-separated node IDs (NOT an array)depth: Tree traversal depth (2 for pages and top-level children)simplify: True for AI-friendly format (70%+ size reduction)
Pitfalls:
- Only supports Design files; FigJam boards and Slides return 400 errors
idsmust be a comma-separated string, not an array- Node IDs may be dash-formatted (1-541) in URLs but need colon format (1:541) for API
- Broad ids/depth can trigger oversized payloads (413); narrow scope or reduce depth
- Response data may be in
data_previewinstead ofdata
2. Export and Render Images
When to use: User wants to export design assets as images
Tool sequence:
FIGMA_GET_FILE_JSON- Find node IDs to export [Prerequisite]FIGMA_RENDER_IMAGES_OF_FILE_NODES- Render nodes as images [Required]FIGMA_DOWNLOAD_FIGMA_IMAGES- Download rendered images [Optional]FIGMA_GET_IMAGE_FILLS- Get image fill URLs [Optional]
Key parameters:
file_key: File keyids: Comma-separated node IDs to renderformat: 'png', 'svg', 'jpg', or 'pdf'scale: Scale factor (0.01-4.0) for PNG/JPGimages: Array of {node_id, file_name, format} for downloads
Pitfalls:
- Images return as node_id-to-URL map; some IDs may be null (failed renders)
- URLs are temporary (valid ~30 days)
- Images capped at 32 megapixels; larger requests auto-scaled down
3. Extract Design Tokens
When to use: User wants to extract design tokens for development
Tool sequence:
FIGMA_EXTRACT_DESIGN_TOKENS- Extract colors, typography, spacing [Required]FIGMA_DESIGN_TOKENS_TO_TAILWIND- Convert to Tailwind config [Optional]
Key parameters:
file_key: File keyinclude_local_styles: Include local styles (default true)include_variables: Include Figma variablestokens: Full tokens object from extraction (for Tailwind conversion)
Pitfalls:
- Tailwind conversion requires the full tokens object including total_tokens and sources
- Do not strip fields from the extraction response before passing to conversion
4. Manage Comments and Versions
When to use: User wants to view or add comments, or inspect version history
Tool sequence:
FIGMA_GET_COMMENTS_IN_A_FILE- List all file comments [Optional]FIGMA_ADD_A_COMMENT_TO_A_FILE- Add a comment [Optional]FIGMA_GET_REACTIONS_FOR_A_COMMENT- Get comment reactions [Optional]FIGMA_GET_VERSIONS_OF_A_FILE- Get version history [Optional]
Key parameters:
file_key: File keyas_md: Return comments in Markdown formatmessage: Comment textcomment_id: Comment ID for reactions
Pitfalls:
- Comments can be positioned on specific nodes using client_meta
- Reply comments cannot be nested (only one level of replies)
5. Browse Projects and Teams
When to use: User wants to list team projects or files
Tool sequence:
FIGMA_GET_PROJECTS_IN_A_TEAM- List team projects [Optional]FIGMA_GET_FILES_IN_A_PROJECT- List project files [Optional]FIGMA_GET_TEAM_STYLES- List team published styles [Optional]
Key parameters:
team_id: Team ID from URL (figma.com/files/team/TEAM_ID/...)project_id: Project ID
Pitfalls:
- Team ID cannot be obtained programmatically; extract from Figma URL
- Only published styles/components are returned by team endpoints
Common Patterns
URL Parsing
Extract IDs from Figma URLs:
1. Call FIGMA_DISCOVER_FIGMA_RESOURCES with figma_url
2. Extract file_key, node_id, team_id from response
3. Convert dash-format node IDs (1-541) to colon format (1:541)
Node Traversal
1. Call FIGMA_GET_FILE_JSON with depth=2 for overview
2. Identify target nodes from the response
3. Call again with specific ids and higher depth for details
Known Pitfalls
File Type Support:
- GET_FILE_JSON only supports Design files (figma.com/design/ or figma.com/file/)
- FigJam boards (figma.com/board/) and Slides (figma.com/slides/) are NOT supported
Node ID Formats:
- URLs use dash format:
node-id=1-541 - API uses colon format:
1:541
Quick Reference
| Task | Tool Slug | Key Params |
|---|---|---|
| Parse URL | FIGMA_DISCOVER_FIGMA_RESOURCES | figma_url |
| Get file JSON | FIGMA_GET_FILE_JSON | file_key, ids, depth |
| Get nodes | FIGMA_GET_FILE_NODES | file_key, ids |
| Render images | FIGMA_RENDER_IMAGES_OF_FILE_NODES | file_key, ids, format |
| Download images | FIGMA_DOWNLOAD_FIGMA_IMAGES | file_key, images |
| Get component | FIGMA_GET_COMPONENT | file_key, node_id |
| File components | FIGMA_GET_FILE_COMPONENTS | file_key |
| Component sets | FIGMA_GET_FILE_COMPONENT_SETS | file_key |
| Design tokens | FIGMA_EXTRACT_DESIGN_TOKENS | file_key |
| Tokens to Tailwind | FIGMA_DESIGN_TOKENS_TO_TAILWIND | tokens |
| File comments | FIGMA_GET_COMMENTS_IN_A_FILE | file_key |
| Add comment | FIGMA_ADD_A_COMMENT_TO_A_FILE | file_key, message |
| File versions | FIGMA_GET_VERSIONS_OF_A_FILE | file_key |
| Team projects | FIGMA_GET_PROJECTS_IN_A_TEAM | team_id |
| Project files | FIGMA_GET_FILES_IN_A_PROJECT | project_id |
| Team styles | FIGMA_GET_TEAM_STYLES | team_id |
| File styles | FIGMA_GET_FILE_STYLES | file_key |
| Image fills | FIGMA_GET_IMAGE_FILLS | file_key |
Powered by Composio
Source
git clone https://github.com/davepoon/buildwithclaude/blob/main/plugins/all-skills/skills/figma-automation/SKILL.mdView on GitHub Overview
Automate Figma operations through Composio's Figma toolkit via Rube MCP. It covers files, components, design tokens, comments, and exports, and workflows always start by querying current tool schemas with RUBE_SEARCH_TOOLS.
How This Skill Works
The agent uses Rube MCP to manage Figma connections and execute toolkit actions. Start by verifying current schemas with RUBE_SEARCH_TOOLS, then connect to Figma with RUBE_MANAGE_CONNECTIONS using the figma toolkit and ensure the connection is ACTIVE. Core tasks leverage FIGMA_GET_FILE_JSON, FIGMA_RENDER_IMAGES_OF_FILE_NODES, FIGMA_EXTRACT_DESIGN_TOKENS, and FIGMA_GET_COMMENTS_IN_A_FILE as part of standard workflows.
When to Use It
- When you need to inspect a Figma file's data and list its published components
- When you want to export design assets as images (PNG/JPG/SVG/PDF)
- When you need to extract design tokens for development and potentially convert to Tailwind
- When you want to view or add comments and inspect version history
- When you want to verify MCP schemas and an ACTIVE Figma connection before running workflows
Quick Start
- Step 1: Verify Rube MCP is available by calling RUBE_SEARCH_TOOLS to fetch current tool schemas
- Step 2: Connect to Figma with RUBE_MANAGE_CONNECTIONS using the figma toolkit; complete auth if status is not ACTIVE
- Step 3: Confirm the connection is ACTIVE and run a Core Workflow (e.g., Get File Data and Components) or proceed with a specific task
Best Practices
- Always call RUBE_SEARCH_TOOLS first to fetch the current tool schemas
- Ensure RUBE_MANAGE_CONNECTIONS is called with the figma toolkit and the status is ACTIVE
- Use correct parameter formats: file_key as string, ids as a comma-separated string, and manage depth carefully
- Limit payload size to avoid 413 errors by narrowing the scope or reducing depth
- Note that only Design files are supported; FigJam and Slides will return 400 errors
Example Use Cases
- A designer inspects a Figma file and lists all published components for a design review
- A developer exports specific nodes as images to include in a product spec document
- A design system engineer extracts tokens and routes them toward a Tailwind config
- A reviewer fetches and comments on a file, then checks its version history
- A project lead validates that the Figma connection is ACTIVE before a release campaign
Frequently Asked Questions
Related Skills
ab-test-setup
ranbot-ai/awesome-skills
Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.
Database Design Expert
martinholovsky/claude-skills-generator
Expert in database schema design with focus on normalization, indexing strategies, FTS optimization, and performance-oriented architecture for desktop applications
web-artifacts-builder
anthropics/skills
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
canva-automation
davepoon/buildwithclaude
Automate Canva tasks via Rube MCP (Composio): designs, exports, folders, brand templates, autofill. Always search tools first for current schemas.
miro-automation
davepoon/buildwithclaude
Automate Miro tasks via Rube MCP (Composio): boards, items, sticky notes, frames, sharing, connectors. Always search tools first for current schemas.
architect
aiskillstore/marketplace
Design systems, plan implementations, review architecture decisions - Use when you need to plan a complex feature, design system architecture, or make high-level technical decisions.