Token导航 LogoToken导航TokenDH.com
效率敏感数据clawhub未标认证来源可访问clear审计通过

excalidraw-proExcalidraw 专业版

Agent Skill

excalidraw-pro 用于补充效率相关能力,适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

5,322

周安装

224

GitHub Stars

公开资料未说明

下载量

1,864
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:excalidraw-pro(Excalidraw 专业版)
来源仓库:https://github.com/jannik689/excalidraw-pro
安装命令:
openclaw skills install excalidraw-pro
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install excalidraw-pro

简介

excalidraw-pro 用于补充效率相关能力,适合提升工作效率。

  • 适用于从自然语言描述生成 Excalidraw 图表(.excalidraw 文件)。
  • 通过 clawhub 安装,需结合来源仓库和 README 核验具体用法。
  • 安装前建议确认权限范围、维护状态及是否触发联网或文件读写。
  • 支持用户创建、绘制或可视化视图的自然语言指令转换。

SKILL.md

name
excalidraw-gen
description
Generate Excalidraw diagrams (.excalidraw files) from natural language descriptions. Use this skill whenever the user asks to create, draw, or visualize a diagram, flowchart, architecture diagram, mind map, sequence diagram, or any kind of visual diagram — even if they don't explicitly mention "Excalidraw". Trigger on phrases like "draw a diagram", "create a flowchart", "visualize the architecture", "make a mind map", "show the flow of", "diagram this", "sketch out", etc.

Excalidraw Diagram Generator

You generate .excalidraw files from natural language descriptions. The user can open these files directly in Excalidraw (File → Open) or drag-and-drop onto the canvas.

Workflow

  1. Understand the description — identify what the user wants to visualize
  2. Auto-select diagram type — choose the best type from the table below
  3. Generate the intermediate JSON — write a structured diagram_input.json
  4. Run the build script — execute build_excalidraw.py to produce the file
  5. Tell the user — report the output file path and how to open it

Diagram Type Selection

What the user describesType to use
Steps, process, decisions, branchingflowchart
Systems, services, components, infrastructurearchitecture
Topics, ideas, concepts radiating from a centermindmap
Two or more parties exchanging messages over timesequence

When in doubt, prefer flowchart — it handles the widest range of content.

Intermediate JSON Formats

Generate one of the following formats as diagram_input.json in the current working directory.

Flowchart

{
  "type": "flowchart",
  "title": "Short descriptive title",
  "nodes": [
    {"id": "unique_id", "label": "Display Text", "shape": "rectangle"},
    {"id": "decision", "label": "Is it valid?", "shape": "diamond"},
    {"id": "start_end", "label": "Start", "shape": "oval"}
  ],
  "edges": [
    {"from": "node_a", "to": "node_b"},
    {"from": "decision", "to": "node_c", "label": "Yes"},
    {"from": "decision", "to": "node_d", "label": "No"}
  ]
}

Shape choices: rectangle (default), diamond (decisions/conditions), oval (start/end points)

Architecture

{
  "type": "architecture",
  "title": "System Architecture",
  "groups": [
    {
      "id": "frontend",
      "label": "Frontend",
      "nodes": [
        {"id": "web", "label": "Web App"},
        {"id": "mobile", "label": "Mobile App"}
      ]
    },
    {
      "id": "backend",
      "label": "Backend",
      "nodes": [
        {"id": "api", "label": "API Gateway"},
        {"id": "auth", "label": "Auth Service"}
      ]
    }
  ],
  "nodes": [],
  "edges": [
    {"from": "web", "to": "api", "label": "HTTPS"},
    {"from": "mobile", "to": "api", "label": "HTTPS"}
  ]
}

Note: groups is optional. Use nodes at the top level for ungrouped components. You can mix both.

Mind Map

{
  "type": "mindmap",
  "title": "Topic Overview",
  "root": "Central Topic",
  "branches": [
    {
      "label": "Branch 1",
      "children": ["Subtopic A", "Subtopic B", "Subtopic C"]
    },
    {
      "label": "Branch 2",
      "children": ["Subtopic D", "Subtopic E"]
    }
  ]
}

Sequence Diagram

{
  "type": "sequence",
  "title": "Interaction Flow",
  "actors": ["User", "Frontend", "API", "Database"],
  "messages": [
    {"from": "User", "to": "Frontend", "label": "Click Login"},
    {"from": "Frontend", "to": "API", "label": "POST /login"},
    {"from": "API", "to": "Database", "label": "Query user"},
    {"from": "Database", "to": "API", "label": "Return record"},
    {"from": "API", "to": "Frontend", "label": "JWT token"},
    {"from": "Frontend", "to": "User", "label": "Redirect"}
  ]
}

Execution Steps

After writing diagram_input.json, run the build script:

python <skill_dir>/scripts/build_excalidraw.py \
  --input diagram_input.json \
  --output <title>.excalidraw

Where <skill_dir> is the directory containing this SKILL.md file, and <title> is a sanitized version of the diagram title.

Output Message to User

After successful generation, tell the user:

✓ Diagram saved to: <filename>.excalidraw

To open in Excalidraw:
1. Go to https://excalidraw.com
2. Click the menu (☰) → Open → select the file
   — or — drag the file onto the canvas

Tips for Good Diagrams

  • Keep labels concise — 1–5 words per node works best
  • Limit nodes — 5–15 nodes per diagram for readability; split complex diagrams into multiple files
  • Use meaningful IDs — snake_case, no spaces (e.g., api_gateway, check_auth)
  • Flowchart edges — always go from a defined node ID to another defined node ID
  • Sequence actors — list them in the order they first appear in the conversation

Error Handling

If the script fails:

  1. Check that diagram_input.json has valid JSON syntax
  2. Ensure all edge from/to values match existing node id values
  3. Verify Python 3.6+ is available (python3 --version)

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

91.79%
按下载量换算1,711

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills