Borrowing it
Nothing to install: this file belongs to hadi21k/figma-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hadi21k/figma-mcp/main/.claude/skills/figma-design-system/SKILL.mdgit clone --depth 1 https://github.com/hadi21k/figma-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hadi21k/figma-mcp/figma-design-system)<a href="https://agentmods.dev/skills/hadi21k/figma-mcp/figma-design-system"><img src="https://agentmods.dev/badge/skills/hadi21k/figma-mcp/figma-design-system/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hadi21k/figma-mcp/figma-design-system"><img src="https://agentmods.dev/badge/skills/hadi21k/figma-mcp/figma-design-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00137 | $0.03747 |
| Opus 5 | $0.00068 | $0.01873 |
| Sonnet 5 | $0.00027 | $0.00749 |
| Haiku 4.5 | $0.00014 | $0.00375 |
Grade A, and why
figma-design-system scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Design System Skill
Build professional, well-structured UI designs through the Figma MCP server. This skill ensures Claude approaches Figma design work systematically — thinking like a designer, not just an API caller.
Core Philosophy
The Figma MCP gives you 67 tools to manipulate a Figma file. But tools without design thinking produce messy files. This skill teaches you how to think about structure, then use the tools to execute that structure.
The golden rule: Plan the layout tree in your head first. Then build from the inside out.
1. Design Workflow
Every design task follows this sequence. Do not skip steps.
Step 1: Understand Context
- Use
get_document_infoto see existing pages, frames, and structure - Use
get_local_componentsto know what components already exist - Use
get_local_stylesto see established color/text/effect styles - Use
get_variablesto check for existing variable collections - Ask the user about target screen size, brand, and content if not specified
Step 2: Set Up Foundation
- Navigate to the correct page with
set_current_page, or create one withcreate_page - If no design system exists yet, establish styles and variables first (see Section 4)
- Determine the frame dimensions (common: 1440×900 desktop, 390×844 mobile, 768×1024 tablet)
Step 3: Plan the Layout Tree
Before creating anything, map out the hierarchy. Example for a landing page hero:
hero-section (frame, 1440×900, vertical auto layout)
├── nav-bar (frame, horizontal auto layout, fill width)
│ ├── logo (frame or image)
│ ├── nav-links (frame, horizontal auto layout, gap 32)
│ │ ├── link-1 (text)
│ │ ├── link-2 (text)
│ │ └── link-3 (text)
│ └── cta-button (frame, horizontal auto layout, padding 12/24)
│ └── button-label (text)
├── hero-content (frame, vertical auto layout, centered, gap 24)
│ ├── headline (text, H1)
│ ├── subtitle (text, body large)
│ └── action-row (frame, horizontal auto layout, gap 16)
│ ├── primary-button (frame)
│ └── secondary-button (frame)
└── hero-image (rectangle or image fill)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 427 lines · 137 tokens per session scan A 90433c452590
figma-design-system is a skill published in the GitHub repository hadi21k/figma-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 137 tokens to every session and 3,747 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.