A collection of Figma design automation skills/scripts for accessibility auditing, component analysis, design tokens, annotations, and design-code parity checking
This server has 10 tools with significant definition gaps. Most tools lack visible input schemas in the provided source code, only 2 tools (import-tokens-figma, analyze-component-set-figma) show explicit parameter definitions in comments or code. Descriptions are present but generic (50-150 chars), lacking LLM-optimized guidance on WHEN to use each tool or what happens on failure. No output schemas documented. Tool names use domain-specific suffixes (-figma) but lack clear action verbs (e.g., 'scan-code-accessibility' vs 'audit-code-accessibility'). Error handling and recovery guidance are absent. The server appears to be a collection of Figma plugin scripts wrapped as MCP tools, but the tool registration mechanism and schema enforcement are not visible in the provided source.
Variant state machine + CSS pseudo-class mapping + per-variant diffs. Analyzes a component set to extract visual signatures, state mappings, and differences from the default variant.
Read annotations from a Figma node (and optionally its children). Returns the node's annotations + available categories.
Write annotations to a Figma node. Undoable in Figma (Cmd+Z). Supports replace or append mode.
Organize variants into a labeled grid with a titled container. Positions variants in a grid layout, creates row/column labels, and builds a white container with title.
Deep a11y scorecard for one component / component set. Analyzes coverage of interactive states, focus indicators, color contrast, non-color differentiation, and color-blind accessibility.
No visible input schemas for 8 of 10 tools. Only import-tokens-figma and analyze-component-set-figma show explicit parameter definitions in code comments. Remaining tools lack JSON Schema definitions, making it impossible for LLMs to validate inputs or understand parameter types.
No output schemas documented for any tool. LLMs cannot plan downstream calls or extract required fields (e.g., node IDs for chaining). Responses are unstructured, forcing LLMs to parse free-text output.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | 2026-07-28+ | v2 |
Diff a Figma node's specs against a code spec. Compares visual properties, spacing, typography, and accessibility attributes between design and code.
Add / edit / delete a component property. Properties live on the parent COMPONENT_SET (or a standalone COMPONENT) — NOT on a variant.
Instantiate a component and set its instance properties. Supports published library components and local components.
Push design tokens INTO Figma as variables (create + update). Two-pass: pass 1 creates/updates literal values; pass 2 wires aliases (so targets exist first). Matches existing variables by saved Figma id → key → exact name, so re-imports don't duplicate.
Standalone axe-core + JSDOM accessibility scanner for HTML (code side of the Figma a11y workflow)
Descriptions lack LLM-optimized guidance. Most are 50 - 150 chars and state WHAT the tool does but not WHEN to use it, what prerequisites exist, or what happens on error. E.g., 'Standalone axe-core + JSDOM accessibility scanner' doesn't explain when to call it vs audit-accessibility-figma.
No error handling or recovery guidance. Tools do not document what errors are retryable, user-fixable, or fatal. No guidance on what to do if a node is not found, a collection doesn't exist, or a write fails.
Tool names lack clear action verbs. 'scan-code-accessibility-figma' and 'audit-accessibility-figma' are similar and could be confused. 'annotations-figma' is split into (get) and (set) but not named get_annotations_figma / set_annotations_figma. Naming inconsistency increases LLM confusion.