跳到正文
cccskills
免费在 GitHub 公开

diagram-design

Best practices for creating research diagrams with Excalidraw MCP tools

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Diagram Design Guide for Research

When to Create Diagrams

Create a diagram when your research findings involve:

  • Comparing 3+ options — comparison table or matrix diagram
  • Process with 4+ steps — flowchart or sequence diagram
  • System with multiple components — architecture diagram
  • Chronological events — timeline
  • Hierarchical relationships — tree or mind map
  • Data flows — data flow diagram

Excalidraw Workflow

  1. Plan the diagram — decide type, elements, and layout before creating
  2. Create elements — use create_element or batch_create_elements
  3. Arrange — use align_elements and distribute_elements for clean layout
  4. Inspect — use describe_scene to verify the diagram looks right
  5. Adjust — use update_element to fix positioning or text
  6. Group — use group_elements to lock related items together

Note: Do NOT export or share links — the user sees a live embedded canvas that auto-syncs.

Color Palette

Use consistent colors across diagrams:

PurposeColorHex
Primary conceptsBlue#1971c2
Positive / supportedGreen#2f9e44
Negative / limitationsRed#e03131
Warning / caveatsOrange#e8590c
Neutral / contextGray#868e96
Highlight / focusYellow#f08c00

Layout Patterns

  • Top-to-bottom: Process flows, decision trees, timelines
  • Left-to-right: Comparisons, before/after, pipelines
  • Radial / center-out: Concept maps, mind maps
  • Grid: Feature matrices, comparison tables

Element Guidelines

Text

  • Use short labels (2-4 words per element)
  • Title font size: 20-24px
  • Label font size: 14-16px
  • Add detail in sub-labels, not element titles

Shapes

  • Rectangles: Processes, components, entities
  • Diamonds: Decision points
  • Ellipses: Start/end points, concepts
  • Rectangles with rounded corners: Groups, categories

Arrows

  • Solid arrows: Direct relationships, data flow
  • Dashed arrows: Optional paths, indirect relationships
  • Label arrows to clarify the relationship

Spacing

  • 40px minimum between elements
  • 80px between groups
  • Consistent spacing within a group

Diagram Types for Research

Comparison Diagram

[Option A]  [Option B]  [Option C]
   |            |            |
[Pros]      [Pros]      [Pros]
[Cons]      [Cons]      [Cons]
   |            |            |
   └──── [Verdict] ─────────┘

Architecture Diagram

┌─────────────────────────────┐
│        [System Name]         │
│  ┌──────┐  ┌──────┐        │
│  │Comp A│──│Comp B│        │
│  └──────┘  └──┬───┘        │
│               │              │
│          ┌────▼────┐        │
│          │ Comp C  │        │
│          └─────────┘        │
└─────────────────────────────┘

Timeline

[2020]──[2021]──[2022]──[2023]──[2024]──[2025]
  │       │       │       │       │       │
 Event   Event   Event   Event   Event   Event

Tips

  • Always call describe_scene after creating elements to verify layout
  • Use batch_create_elements for efficiency (multiple elements at once)
  • Group related elements before aligning for cleaner organization
  • Do NOT export or share links — the live embedded canvas auto-syncs for the user
  • NEVER use create_from_mermaid — it produces invisible results. Always use batch_create_elements with element JSON instead

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Building, compiling, and resolving dependency issues across languages

中文简介正在准备中。当前显示原文说明。

vstorm-co/pydantic-deepagents11052026年10月21日 更新

Systematic code review for bugs, security, style, and performance

中文简介正在准备中。当前显示原文说明。

vstorm-co/pydantic-deepagents11052026年10月21日 更新

Review Python code for quality, security, and best practices

中文简介正在准备中。当前显示原文说明。

vstorm-co/pydantic-deepagents11052026年10月21日 更新

Comprehensive data analysis skill for CSV files using Python and pandas

中文简介正在准备中。当前显示原文说明。

vstorm-co/pydantic-deepagents11052026年10月21日 更新

Working with diverse data formats: binary, text, structured, and custom

中文简介正在准备中。当前显示原文说明。

vstorm-co/pydantic-deepagents11052026年10月21日 更新

Systematic exploration of unknown environments before starting work

中文简介正在准备中。当前显示原文说明。

vstorm-co/pydantic-deepagents11052026年10月21日 更新

查看 vstorm-co 的全部技能

报告此技能的问题