figma-use
figma use
What it does
- Progress reporting: return { createdNodeIds: [...], count: 5, errors: [] }
- Error info: Thrown errors are automatically captured and returned — just let them propagate or throw explicitly.
- console.log() output is never returned to the agent
- Always return actionable data (IDs, counts, status) so subsequent calls can reference created objects
- Type: FRAME, TEXT, RECTANGLE, ELLIPSE, COMPONENT, INSTANCE, SECTION (case-insensitive)
- Attribute exact: [name=Card], [visible=true], [opacity=0.5]
- Attribute substring: [name=art] (contains), [name^=Header] (starts-with), [name$=Nav] (ends-with)
Requirements & configuration
- These APIs reduce boilerplate, eliminate ordering errors, and compress token output. Always prefer them over the verbose alternatives.
- Children can immediately use layoutSizingHorizontal/Vertical = 'FILL' after being appended — no need to set sizing modes manually.
- Capture a node as a PNG and return it inline in the response. Eliminates the need for a separate getscreenshot call.
- When to use: After creating or modifying nodes, call screenshot() to visually verify the result within the same script. No need for a separate getscreenshot call.
- 4. Return IDs from every call. Always return created node IDs, variable IDs, collection IDs as objects (e.g. return { createdNodeIds: [...] }). You'll need these as inputs to subsequent calls.
Configuration: FIXEDFILLALL_SCOPESFRAMETEXTRECTANGLEELLIPSECOMPONENT
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
figma-use FAQ
What does the figma-use skill do?
**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the Figma file context — e.g. create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills, bind variables to properties, or inspect file structure programmatically. Progress reporting: return { createdNodeIds: [...], count: 5, errors: [] } Error info: Thrown errors are automatically captured and returned — just let them propagate or throw explicitly.
What does figma-use require?
These APIs reduce boilerplate, eliminate ordering errors, and compress token output. Always prefer them over the verbose alternatives. Children can immediately use layoutSizingHorizontal/Vertical = 'FILL' after being appended — no need to set sizing modes manually. Capture a node as a PNG and return it inline in the response. Eliminates the need for a separate getscreenshot call. When to use: After creating or modifying nodes, call screenshot() to visually verify the result within the same script. No need for a separate getscreenshot call. 4. Return IDs from every call. Always return created node IDs, variable IDs, collection IDs as objects (e.g. return { createdNodeIds: [...] }). You'll need these as inputs to subsequent calls. Configuration keys: FIXED, FILL, ALL_SCOPES, FRAME, TEXT, RECTANGLE, ELLIPSE, COMPONENT.
How do I install figma-use?
Run: npx -y skills add https://github.com/figma/mcp-server-guide --skill figma-use --agent claude-code — the source lives at github.com/figma/mcp-server-guide.
Maintain figma-use?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/skills/figma-mcp-server-guide-figma-use?ref=badge) npx agentictools info skills/figma-mcp-server-guide-figma-use The second line is the CLI lookup for this page — handy in READMEs and docs.