Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsDesign Systems Engineering: Design Context for AI Agents
Make your design system legible to AI agents: choose the context strategy, author DESIGN.md and design.md, structure the knowledge, and verify it.
$9.99
Design Systems Engineering: Design Context for AI Agents
Example session with this skill installed
Review my button component for accessibility and suggest a design token structure for light and dark modes.
- Read your context and instructions
- Compiled the design systems engineering
- Contrast: Current #767676 on white fails WCAG AA. Suggest #595959.
- Tokens: Use color.surface.action.primary and color.text.on-action.
- Target: Ensure 44px min touch area for mobile ergonomics.
Connects securely to your tools. The creator never sees your data.
About this skill
Design Systems Engineering 3.1 teaches an AI agent how to give itself the design context it needs. It covers the four ways design context reaches an agent, a portable DESIGN.md in Google's Stitch format with a template that lints clean, a design.md guidance file in the Vercel genre, an OKF v0.2 knowledge bundle with provenance and trust tiers, and an anti-slop method that never prescribes a palette or a font. It ships a starter eval harness with frozen scenarios and real deterministic checks. Version 3.1.0 hardens the checks (0% false accepts on a 5,000-case fuzz mixture each, plus a 74-case regression suite) on top of the design context engineering layer: DESIGN.md and design.md authoring, OKF v0.2 bundles, and anti-slop creative direction.
- Does not perform pure backend or database optimization.
- Stays tool-agnostic: requires specific plugins for direct Figma/Adobe API automation.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
3 uses
Times used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Requires
Node.js