Works with the AI Agents you already use
Flat Svg Diagram Mint
Generate flat, minimal SVG diagrams as standalone HTML: a unified component set, consistent 8px spacing, simple shapes, light/dark awareness, accessible colors,
Free
Flat Svg Diagram Mint
Example session with this skill installed
Create a three-stage system architecture diagram showing an API Gateway, a Lambda function, and a DynamoDB table using a flat SVG style.
- Read your context and instructions
- Compiled the flat svg diagram
A standalone HTML file containing a <svg> with three nodes. It includes a <style> block defining --fill, --stroke, and --text variables, a <defs> for arrowheads, and three <rect> elements snapped to an 8px grid with 'API Gateway', 'Lambda', and 'DynamoDB' labels.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Documenting system architectures or user flows often requires heavy design tools that produce inconsistent results. Developers frequently struggle with diagrams that lack dark mode support, scale poorly, or fail accessibility standards.
What it does
- Generates standalone HTML files containing flat, minimal SVG diagrams.
- Enforces a strict 8px grid system for perfect node alignment and spacing.
- Implements CSS custom properties for automatic light and dark mode awareness.
- Standardizes component geometry for boxes, pills, and decision diamonds.
- Ensures WCAG 4.5:1 contrast ratios and adds appropriate ARIA labels for accessibility.
Why this beats prompting it yourself
General LLM prompts often yield messy SVG code with inconsistent stroke widths and hardcoded colors. This skill enforces a specific design system, ensures grid-snapped coordinates, and structures code for high maintainability and theme-switching.
Use cases
- Create system architecture diagrams for technical documentation.
- Map out complex user flows or state machine transitions.
- Generate organizational charts that stay crisp at any zoom level.
- Build decision trees for internal wikis or slide decks.
Known limitations
Not suitable for data-dense charts with thousands of points or photorealistic visuals. Does not provide drag-and-drop interactivity.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Not for data-heavy charts or 3D visuals. Static output only; no drag-and-drop node editing.
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 buying a skill.
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
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected