Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    Excalidraw Sketcher

    1

    Use to produce hand-drawn style Excalidraw JSON diagrams for architectures, flows and sequences. Covers library elements, positioning, arrows, styling and PNG/S

    Free

    0 installsSecurity scanned
    Excalidraw Sketcher

    Excalidraw Sketcher

    Example session with this skill installed

    Create an Excalidraw diagram for a serverless API flow: Gateway to Lambda to DynamoDB. Use hachure fill for the DB and blue arrows.

    • Read your context and instructions
    • Compiled the excalidraw sketcher
    {
      "type": "excalidraw",
      "version": 2,
      "elements": [
        {"type": "rectangle", "id": "gw", "x": 100, "y": 100, "width": 140, "height": 60, "strokeColor": "#1e1e1e"},
        {"type": "arrow", "x": 240, "y": 130, "points": [[0,0], [100,0]], "strokeColor": "#1971c2", "startBinding": {"elementId": "gw"}}
      ]
    }
    

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

    About this skill

    The problem

    Standard architectural diagrams often look too rigid for early-stage docs, while manual whiteboarding is time-consuming to align and update. Generating structured, editable "hand-drawn" diagrams programmatically is difficult due to coordinate math and element binding requirements.

    What it does

    • Generates valid Excalidraw JSON files for system architectures, sequence diagrams, and UI wireframes.
    • Calculates grid-based positioning and gutters to prevent overlapping elements automatically.
    • Binds arrows to shapes using element IDs so connections persist when you move boxes in the editor.
    • Applies customizable visual styles including hachure fills, roughness levels, and stroke weights.
    • Includes headless export instructions for converting JSON to PNG or SVG via CLI.

    Frameworks & tools

    Excalidraw, JSON, jq, and excalidraw-cli for headless rendering.

    Why this beats prompting it yourself

    Generic LLM prompts often produce invalid JSON or messy, overlapping shapes without proper z-index or coordinate logic. This skill enforces specific grid math, label centering, and element binding, ensuring the output is actually usable in a whiteboard editor immediately.

    Use cases

    • Visualizing microservices architecture for engineering design docs.
    • Creating sequence diagrams for complex authentication or data flows.
    • Drafting low-fidelity UI wireframes for rapid prototyping feedback.
    • Generating mind maps for brainstorming sessions that stay editable.

    Known limitations

    Not suitable for strict UML with exact class relations or statistical charts. Requires a JSON-compatible editor or the Excalidraw CLI for viewing and export.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scanned

    Verified clean 1 month ago

    • Free to download with an account

    Listed1 month ago
    Updated29 days ago

    Frequently Asked Questions