figma-automation
Automate Figma tasks via Rube MCP (Composio): files, components, design tokens, comments, exports. Always search tools first for current schemas.
75
Quality
63%
Does it follow best practices?
Impact
96%
2.34xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/figma-automation/SKILL.mdEvaluation results
92%
41%Figma Design System to Tailwind Config
Design token Tailwind conversion
Search tools first
0%
100%
Manage connections call
0%
100%
Connection ACTIVE check
0%
100%
URL resource discovery
50%
100%
Extract design tokens
100%
100%
Convert to Tailwind
100%
100%
Full tokens object preserved
100%
100%
total_tokens and sources fields
0%
100%
data_preview awareness
0%
0%
Correct tool sequence order
100%
100%
Without context: $0.9086 · 3m 58s · 30 turns · 79 in / 10,976 out tokens
With context: $0.5540 · 2m 31s · 21 turns · 29 in / 8,424 out tokens
98%
58%Automate Marketing Asset Export from Figma
Image export with node ID handling
Search tools first
0%
71%
Connection setup
0%
100%
URL resource discovery
0%
100%
Node ID dash-to-colon conversion
100%
100%
ids as comma-separated string
100%
100%
Get file JSON before render
30%
100%
depth=2 for overview
0%
100%
simplify=true for inspection
0%
100%
Render images tool called
37%
100%
Download images array format
0%
100%
Null render handling
100%
100%
Without context: $0.2281 · 1m 21s · 12 turns · 16 in / 4,840 out tokens
With context: $0.2965 · 1m 19s · 13 turns · 267 in / 4,738 out tokens
100%
67%Figma Design File Audit and Component Review
File inspection with type and payload handling
Search tools first
28%
100%
Connection verified ACTIVE
0%
100%
URL resource discovery
0%
100%
FigJam board unsupported
35%
100%
depth=2 initial overview
0%
100%
Oversized payload mitigation
60%
100%
data_preview response handling
0%
100%
FIGMA_GET_FILE_COMPONENTS
50%
100%
Published components only
100%
100%
Add comment tool
60%
100%
Reply nesting limitation
0%
100%
Without context: $0.3290 · 1m 50s · 15 turns · 20 in / 5,472 out tokens
With context: $0.5080 · 2m 2s · 22 turns · 278 in / 6,560 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.