Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Svg Infra Diagrammer

    1

    Use to produce dark-themed SVG architecture and infrastructure diagrams as self-contained HTML files: hand-written SVG with boxes, groups, arrows, labels, and c

    Free

    3 usesSecurity scanned
    Svg Infra Diagrammer

    Svg Infra Diagrammer

    Example session with this skill installed

    Create an SVG infrastructure diagram in HTML for a three-tier app: a React frontend, a Node.js API in a private subnet, and a PostgreSQL database, all inside an AWS VPC.

    • Read your context and instructions
    • Compiled the svg infra diagrammer
    <!DOCTYPE html>
    <html>
    <style>body { background:#0d1117; } svg { font-family: monospace; }</style>
    <svg width="1200" height="800" viewBox="0 0 1200 800">
    <defs><marker id="arrow" .../></defs>
    <!-- VPC Group -->
    <rect x="50" y="50" width="1100" height="700" fill="none" stroke="#30363d" stroke-dasharray="5,5"/>
    ...
    </svg>
    </html>
    

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Architecture diagrams often rot in siloed design tools or break in READMEs due to missing image assets and broken network fonts. Developers need clean, version-controllable diagrams that render perfectly in any browser without external dependencies.

    What it does

    • Generates self-contained HTML files featuring hand-written, dark-themed SVG infrastructure diagrams.
    • Uses a standardized component library including rounded boxes, clusters, arrows, and cloud symbols.
    • Enforces a consistent GitHub-inspired dark palette for professional, high-contrast visuals.
    • Creates scalable, accessible diagrams with crisp monospace text that maintains clarity at any zoom level.
    • Includes click-to-inspect behavior by wrapping SVG groups in anchor links for interactive documentation.

    Frameworks & tools

    SVG, HTML5, CSS, and Chromium for headless PNG exports.

    Why this beats prompting it yourself

    General LLMs often produce messy, overlapping SVG code or use inconsistent colors that clash with dark mode docs. This skill applies a rigorous draw order and a specific component schema to ensure every arrow connects and every label is legible.

    Use cases

    • Documenting cloud infrastructure in GitHub READMEs using embedded HTML/SVG.
    • Creating high-resolution architecture slides for technical presentations.
    • Visualizing CI/CD pipelines or microservice data flows for onboarding.
    • Generating interactive system maps with clickable components for internal wikis.

    Known limitations

    Not suitable for UML sequence or ER diagrams requiring heavy formal notation. Does not export to editable formats like Figma or Visio.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    Does not support UML sequence/ER diagrams. Output is code-based; not compatible with drag-and-drop editors like Figma. Fixed dark-themed palette.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    It generates a single, self-contained HTML file containing raw SVG code. This ensures the diagram renders perfectly in any browser or GitHub README without needing external image hosting or fonts.

    No. This skill uses a hard-coded dark-themed palette (GitHub-inspired) and a specific component library to ensure professional consistency and high contrast across all outputs.

    Yes. You can use headless Chrome or Chromium to take a screenshot of the generated HTML file. The SKILL.md provides the specific CLI command for this conversion.

    The skill includes a 'cloud' symbol recipe, which is a rounded rectangle with a wavy arc top edge, specifically designed to represent external services or AWS/Azure environments.

    Free