agentleFS
luizomfluizomf/omskills/skills/productivity/excalidraw/SKILL.md

excalidraw

Skill3 starsChanged 2 months agoMITView on GitHub

Create or edit an Excalidraw scene while preserving editability and the requested visual style. When no target or base is supplied, use assets/diagram-base.excalidraw. A supplied target always wins over the base. Never merge the base into an existing target or overwrite the bundled base. Input is complete when the scene source and requested transformation are unambiguous. 1. Read the scene. Parse the full Excalidraw JSON. For wrapped formats, locate the scene without treating wrapper text as drawing content. Preserve unknown…

69 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use heartmula, webhook-subscriptions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • math-incSkill

    heartmula

    Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

    Also in 9 projects that use this

  • Tommy-ywSkill

    webhook-subscriptions

    Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.

    Also in 5 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 7 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

  • AlekseiULSkill

    TubeScribe

    YouTube video summarizer with speaker detection, formatted documents, and audio output. Works out of the box with macOS built-in TTS. Optional recommended tools (pandoc, ffmpeg, mlx-audio) enhance quality. Requires internet for YouTube access. No paid APIs or subscriptions. Use when user sends a YouTube URL or asks to summarize/transcribe a YouTube video.

    Also in 3 projects that use this

  • mae616Skill

    p5js

    p5.js(クリエイティブコーディング)のProcessing由来「コードでスケッチ」思想を軸に、setup/drawループ・座標系・インタラクション・パフォーマンス最適化を整理する。p5.js、Processing、クリエイティブコーディング、ジェネラティブアート、インタラクティブ表現、ビジュアルプログラミング、Canvas描画、パーティクル、フラクタル、ノイズ表現に関する相談で必ず使うこと。ユーザーが「コードでアート」「動くビジュアル」「インタラクティブな描画」と言った場合にも適用する。

    Also in 10 projects that use this

  • +5 more from math-inc

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 64 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Create or edit an Excalidraw scene while preserving editability and the requested visual style.

    line 11
  2. Very specific:

    When no target or base is supplied, use assets/diagram-base.excalidraw.

    line 23
  3. Very specific:

    Build or edit elements: Read REFERENCE.md before creating elements.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 64 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Excalidraw

Create or edit an Excalidraw scene while preserving editability and the requested visual style.

Input

Identify:

  • the diagram content and destination path;
  • an existing target diagram, when the request edits one;
  • a base scene used only when creating a new diagram;
  • any required layout, labels, colors, or output format.

When no target or base is supplied, use assets/diagram-base.excalidraw. A supplied target always wins over the base. Never merge the base into an existing target or overwrite the bundled base. Input is complete when the scene source and requested transformation are unambiguous.

Workflow

  1. Read the scene. Parse the full Excalidraw JSON. For wrapped formats, locate the scene without treating wrapper text as drawing content. Preserve unknown top-level data, appState, files, and elements outside the requested edit. The source is ready when all retained scene data is accounted for.
  2. Plan the diagram. Convert the request into a small set of nodes, relationships, groups, and reading order. Reuse the target's spacing and element styles; otherwise derive new-element defaults from the base scene's appState.currentItem* values. Prefer fewer, larger elements and direct labels. The plan is ready when every requested concept and relationship has one visual representation.
  3. Build or edit elements. Read REFERENCE.md before creating elements. Use unique stable IDs and preserve existing IDs for elements that retain their identity. Keep labels as text elements, not custom label properties. Bind every shape label to its shape and every arrow label to its arrow: set the text's containerId and add the text ID to the container's boundElements. Do not place an arrow's label as independent text near the arrow. For connected arrows, set startBinding and endBinding and add the arrow ID to both endpoint shapes. Every new element must satisfy the reference schema, and every binding must be reciprocal and reference an existing, non-deleted element.
  4. Lay out the scene. Prevent overlaps, leave clear gaps, keep labels inside their containers, and route arrows so direction is obvious. Order elements back-to-front: regions, shapes, bound text, connectors, connector labels, then annotations. The layout is complete when every element is legible and every relationship can be followed without ambiguity.
  5. Write the requested destination. Preserve the target format when editing; for a new scene, use the requested Excalidraw-compatible format. Keep the result editable rather than rasterizing it. Writing is complete when the destination contains the transformed scene and the bundled base is unchanged.
  6. Verify. Parse the produced scene and check every element ID for uniqueness, every reference for a live target, every reciprocal binding in both directions, every arrow label for a live arrow containerId and the reciprocal text entry in that arrow's boundElements, and every requested concept for coverage. Render and inspect visually when that capability is available. Otherwise state that verification was structural only. Completion requires all structural checks to pass and the inspection level to be reported.

Example

Request: Create a new left-to-right diagram showing Script -> Recording -> Edit, using the bundled visual base.

Result: a new editable scene with three labeled shapes, two bound arrows, the base canvas settings, unique IDs, valid reciprocal bindings, and no changes to the bundled base.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.