Maintainer of this skill?
by jangtrinh
DESIGN:OS Studio — Native GPU-accelerated interface design & Figma engine built in Rust
# Add to your Claude Code skills
git clone https://github.com/jangtrinh/design-os-studioGuides for using mcp servers skills like design-os-studio.
See how design-os-studio compares with popular alternatives.
design-os-studio is an open-source mcp servers skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by jangtrinh. DESIGN:OS Studio — Native GPU-accelerated interface design & Figma engine built in Rust. It has 51 GitHub stars.
design-os-studio's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/jangtrinh/design-os-studio" and add it to your Claude Code skills directory (see the Installation section above).
design-os-studio is primarily written in Rust. It is open-source under jangtrinh on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other MCP Servers skills you can browse and compare side by side. Open the MCP Servers category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh design-os-studio against similar tools.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
design-os-studio)Native GPU-accelerated interface design studio, enterprise Figma .fig v106 binary read/write engine, Agentic PTY Chat UI, Live Variables & Multi-Edit (Q), and 22-tool Model Context Protocol server written in Rust.
Open and save 723,136-record enterprise Figma .fig v106 binary archives in ~1.5s with 0.0% idle CPU on Metal, DirectX 12, and Vulkan (wgpu + tiny-skia). Execute all 100 / 100 Figma A-to-Z Micro-Interactions (#1..#100) natively on canvas, run Claude Code (claude), OpenAI Codex (codex), Antigravity CLI (agy), Gemini CLI (gemini), and Grok CLI (grok) directly inside the native Agentic PTY Chat UI with zero paid external API keys, switch live Design Variables across Light and Dark modes with Multi-Edit (Q) and Suggest Auto-Layout (⇧A), generate multi-target Dev Mode code (React, Tailwind, CSS, SwiftUI, Jetpack Compose, Flutter, Rust egui), and automate headless GPU visual QA from any terminal or CI pipeline.
Browser-wrapped Electron design tools choke on very large enterprise files, lock .fig binary authoring behind proprietary cloud servers, and force AI coding agents to scrape large, noisy REST JSON payloads without direct canvas write-back. design-os-studio is a local-first GPU studio written in Rust (wgpu + tiny-skia) with native fig-kiwi v106 binary read/write, Figma-style micro-interactions, an embedded Agentic PTY Chat UI for your existing CLI subscriptions (claude, codex, agy, grok), Live Variables Mode Switching & Multi-Edit (Q), and a 22-tool stdio MCP server.
| Dimension | Figma Desktop (Cloud / Electron) | Penpot / Pencil / OpenPencil | DESIGN:OS Studio (design-os-studio) |
|---|---|---|---|
| Runtime & GPU Engine | Electron + Chromium / WebGL | Browser DOM / SVG / Canvas2D or Electron webview wrapper | Rust (wgpu + tiny-skia), no repaints while the view is idle (FrameKey GPU frame reuse) |
Enterprise Scale (723k Records / 112k Nodes) |
Browser tab OOM crashes, multi-second cloud streaming stalls | DOM / SVG layout bottlenecks above 5k–10k nodes |
Uniform 2048x2048 SceneIndex culling + 4-tier semantic zoom LOD, 1.54s cold load, -96.5% disk size (242 MB vs 6.80 GB) |
Figma .fig v106 Binary Read/Write |
Proprietary cloud lock-in; .fig saves require online servers |
Read-only or lossy third-party converters; no native .fig v106 write-back |
Native bidirectional fig-kiwi v106 Read & Write (DEFLATE/Zstd canvas.fig + meta.json + images/, symbolOverrides, parameterConsumptionMap) |
| Tactile Micro-Interactions | Reference UI3 standard, browser-bound latency on huge files | Partial subset; missing CSS Grid track pills, Smart Selection ring swaps, or Scale Tool (K) |
Figma-style micro-interactions on canvas: inspector scrubbing, Auto-Layout handles, CSS Grid track pills, Smart Selection, Scale Tool (K), Eyedropper (I) |
| Agentic Workflow & API Cost | Paid per-seat AI credits or read-only 155K-char REST JSON dumps |
External MCP plugins or paid API key wrappers (ANTHROPIC_API_KEY / OPENAI_API_KEY) |
Native Agentic PTY Chat UI (Claude Code · Codex · Antigravity · Gemini · Grok — zero extra API cost) + 22-tool designos-mcp + 1-click NodeSpec apply |
Variables, Multi-Edit (Q) & Auto-Layout |
Cloud-bound variable collections & manual frame nesting | Partial variable support; no Q Multi-Edit or ⇧A heuristic inference |
Live Variables Mode Switching (Light / Dark), Multi-Edit (Q / ⌘E) & Suggest Auto-Layout (⇧A) (COLOR, FLOAT, STRING, BOOLEAN + = alias picker) |
| Dev Mode Codegen & Visual QA | Paid Dev Mode seats required; cloud-only inspection | Basic CSS/HTML export; no headless GPU diffing CLI | Free built-in Dev Mode (Shift+D) (CSS, Tailwind, React, SwiftUI, UIKit, Jetpack Compose, Android XML) + headless --gpu --screenshot & designos-diff SSIM CLI |
| Privacy, Offline & Licensing | Mandatory cloud sign-in, proprietary license, background telemetry | Self-hosted Docker stack or Electron runtime telemetry | Zero telemetry — 100% local offline execution (PRIVACY.md audited), PolyForm Shield 1.0.0 (source-available) |
Where traditional platforms win, and it is not close: Browser-hosted multiplayer whiteboarding with simultaneous live WebRTC cursors, enterprise cloud org SSO/SCIM admin consoles, and hosted comment email/Slack notifications. If your workflow requires real-time cloud multiplayer without local git or file ownership, use Figma Cloud (paired with our live bridge
design-os-figma-plugin) or a hosted Penpot instance instead.
| Instrument Field | Specification | Verification / Notes |
|---|---|---|
| Repository | jangtrinh/design-os-studio |
11-crate Cargo workspace (crates/designos-*) |
| Engine Stack | Rust + wgpu + tiny-skia |
Metal (verified on macOS) · Direct3D 12 / Vulkan (Windows and Linux, tested by their users) · No Electron |
| Figma Interop | Native .fig v106 read and write |
crates/designos-fig roundtrip tests · more than 2,800 automated tests pass in macOS CI |
| Agent Surface | 22 MCP Tools + Native PTY Chat UI |
Claude Code · Codex · Antigravity · Gemini · Grok |
| Telemetry / Privacy | Zero Tracking (0 network calls) |
100% offline local-first (PRIVACY.md) |
| License | PolyForm Shield 1.0.0 (source-available) |
Release packages: macOS .dmg (verified), Windows .zip, Linux .deb and .tar.gz (tested by their users) |
Install the AI agent skill plugin in Claude Code / Codex, download a release package (.dmg, .zip, .deb, .tar.gz), or build all 4 binaries from source:
# Option A: Claude Code plugin marketplace
/plugin marketplace add jangtrinh/design-os-studio
/plugin install design-os-studio@design-os-studio
# Option B: Clone & launch native Rust/wgpu Studio (or package a .dmg / .zip / .deb)
git clone https://github.com/jangtrinh/design-os-studio
cd design-os-studio
cargo run --release -p designos-app --bin designos-studio
./scripts/build-release.sh 0.5.0 --local-host
First safe use (3 bounded, non-destructive verification steps):