figma-automation
Automate Figma Workflows with Rube MCP
Manual Figma inspection, export, and token extraction consume time and invite inconsistent results. This skill guides Claude, Codex, and Claude Code through structured Rube MCP workflows.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "figma-automation" from https://skillstore.io/skills/sickn33-figma-automation.md and its manifest at https://skillstore.io/api/skills/sickn33-figma-automation/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "figma-automation". Summarize the top-level structure of the provided Figma design file.
Expected outcome:
- Found four pages and eighteen published components.
- The main library includes buttons, form controls, navigation, and status indicators.
- Two component sets contain inconsistent variant names.
Using "figma-automation". Extract design tokens and summarize the result before Tailwind conversion.
Expected outcome:
- Extracted color, typography, spacing, and radius groups.
- Local styles and variables were included.
- The complete extraction is ready for Tailwind conversion.
Using "figma-automation". Export the Logo and App Icon nodes as PNG images.
Expected outcome:
Rendered both nodes at the requested scale and returned two temporary download links.
Security Audit
Medium RiskAll 49 shell-execution alerts are false positives caused by Markdown backticks around tool names, parameters, URLs, or workflow examples. The six reconnaissance alerts are also false positives. The external Rube MCP connection and authenticated Figma access create a legitimate third-party data and authorization boundary.
Confirmed security concerns (1)
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (49)
🌐 Network access (1)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/sickn33-figma-automation/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-figma-automation?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-figma-automation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-figma-automation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-figma-automation.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
sickn33. (2026). figma-automation security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-figma-automation/audits/6BibTeX citation
@techreport{sickn33-sickn33-figma-automation-2026,
author = {sickn33},
title = {figma-automation security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/sickn33-figma-automation/audits/6},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "figma-automation security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/sickn33-figma-automation/audits/6"
identifiers:
- type: other
value: "skillstore:sickn33-figma-automation:audit:6"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Inspect Designs for Implementation
Retrieve pages, nodes, and component metadata before building an interface.
Extract a Design System
Collect styles and variables, then prepare complete tokens for Tailwind conversion.
Coordinate Design Reviews
Review comments and versions, then post approved feedback to the Figma file.
Try These Prompts
Connect through Rube MCP and summarize the pages and top-level components in [FIGMA_URL]. Use depth 2 and report access errors.
Find nodes named [NODE_NAMES] in [FIGMA_URL], render them as [FORMAT] at [SCALE], and provide the available download links.
Extract local styles and variables from [FIGMA_URL], summarize token groups, then convert the complete token response into a Tailwind configuration.
Review components, comments, and versions for [FIGMA_URL], identify inconsistencies, and add approved comments only after showing the proposed messages.
Best Practices
- Search Rube tools before each workflow because schemas can change.
- Request only required nodes and use a shallow depth before detailed traversal.
- Ask for approval before posting comments or downloading assets to local storage.
Avoid
- Do not send unreviewed comments or assume write permission.
- Do not request entire deep file trees when specific node identifiers are available.
- Do not reuse expired render URLs or expose them in public channels.