重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
diagramming-expert by erichowens/some_claude_skills
npx skills add https://github.com/erichowens/some_claude_skills --skill diagramming-expert精通基于文本的可视化沟通。主动创建图表以增强对复杂概念、系统、流程和关系的理解。
"最重要的是,展示数据。" — Edward Tufte
图表应当:
适用于:
不适用于:
问自己: "用图片会更清晰吗?" 如果是 → 就画图。
完整分类请参见
/references/diagram-types.md
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 类型 | 用途 | 关键模式 |
|---|---|---|
| 流程图 | 流程、决策 | 方框 + 箭头 |
| 层次图 | 组织结构、分类法 | 树状结构 |
| 分层图 | 系统架构 | 堆叠方框 |
| 关系图 | 连接、网络 | 节点 + 边 |
| 序列图 | 时间顺序事件 | 垂直流 |
| 对比图 | 并排分析 | 平行列 |
| 循环图 | 反馈循环 | 圆形箭头 |
| 矩阵图 | 二维分类 | 网格结构 |
完整字符集请参见
/references/unicode-characters.md
BOXES: ARROWS: CONNECTORS:
┌─┬─┐ ╔═╦═╗ → ← ↑ ↓ ├ ┤ ┬ ┴
│ │ │ ║ ║ ║ ◄ ► ▲ ▼ ╠ ╣ ╦ ╩
├─┼─┤ ╠═╬═╣ ⟶ ⟵ ⟷ ┼ ╋ ╬
│ │ │ ║ ║ ║ ⇒ ⇐ ⇔
└─┴─┘ ╚═╩═╝ ──► ◄── EMPHASIS:
═══ ━━━
ROUNDED: BULLETS: ═══ ━━━
╭───╮ • ○ ●
│ │ ├── └── DASHED:
╰───╯ ■ □ ▪ ┄ ┅ ┆ ┇
MAXIMIZE: MINIMIZE:
┌─────────────────┐ ╔══════════════════╗
│ Essential info │ ║ ╭──────────────╮ ║
│ Clear structure │ ║ │ Same info │ ║
│ Direct labeling │ ║ │ + decoration │ ║
└─────────────────┘ ║ ╰──────────────╯ ║
╚══════════════════╝
✓ Good ✗ Chartjunk
CHUNKING: Group related elements
BAD: GOOD:
┌─┬─┬─┬─┬─┬─┬─┬─┐ ┌─────┐ ┌─────┐ ┌─────┐
│A│B│C│D│E│F│G│H│ │ A B │ │ C D │ │ E F │
└─┴─┴─┴─┴─┴─┴─┴─┘ │ (1) │ │ (2) │ │ (3) │
└─────┘ └─────┘ └─────┘
PROXIMITY: SIMILARITY: ENCLOSURE:
○ ○ ● ● ○ ● ○ ● ○ ┌───────────┐
○ ○ ● ● ● ○ ● ○ ● │ ○ ○ ○ ○ ○ │
Groups by Groups by │ (grouped) │
nearness appearance └───────────┘
EMPHASIS LEVELS:
═══════════════════════ Level 1: Double/Heavy
─────────────────────── Level 2: Single
- - - - - - - - - - - - Level 3: Dashed
. . . . . . . . . . . . Level 4: Dotted
SIZE HIERARCHY:
╔═══════════════════════════╗
║ PRIMARY ELEMENT ║
╠═══════════════════════════╣
│ Secondary Element │
├───────────────────────────┤
│ tertiary element │
└───────────────────────────┘
完整模式库请参见
/references/patterns-library.md
┌─────────┐ ┌─────────┐ ┌─────────┐
│ 开始 │───►│ 流程 │───►│ 结束 │
└─────────┘ └─────────┘ └─────────┘
┌──────────┐
│ 决策 │
└────┬─────┘
┌─────────┴────────┐
▼ ▼
┌────────┐ ┌────────┐
│ 是 │ │ 否 │
└────────┘ └────────┘
┌─────────────────────────────────────┐
│ 表示层 │
├─────────────────────────────────────┤
│ 业务逻辑 │
├─────────────────────────────────────┤
│ 数据访问 │
├─────────────────────────────────────┤
│ 数据库 │
└─────────────────────────────────────┘
┌──────────────────┐
│ │
▼ │
┌───────┐ ┌───┴───┐
│ 输入 │─────────►│ 输出 │
└───────┘ └───────┘
▲ │
│ │
└──────────────────┘
✗ BAD: Excessive decoration
╔══════════════════════════════════╗
║ ╭━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╮ ║
║ ┃ ★ ★ ★ IMPORTANT INFO ★ ★ ★ ┃ ║
║ ╰━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╯ ║
╚══════════════════════════════════╝
✓ GOOD: Clean and direct
┌──────────────────┐
│ 重要信息 │
└──────────────────┘
✗ BAD: Crossing lines, unclear flow
┌───┐ ┌───┐
│ A │──┬──│ B │
└───┘ │ └───┘
│ ╳ │
┌─┴─┐ │ ┌─┴─┐
│ C │──┴──│ D │
└───┘ └───┘
✓ GOOD: Clear hierarchy, minimal crossings
┌───┐ ┌───┐
│ A │ │ B │
└─┬─┘ └─┬─┘
│ │
▼ ▼
┌───┐ ┌───┐
│ C │ │ D │
└───┘ └───┘
✗ BAD: Too much in one diagram
[Cramming 15 concepts with 30 arrows]
✓ GOOD: Break into focused diagrams
"Overview Diagram" + "Detail Diagram A" + "Detail Diagram B"
可与以下技能协同工作:
心理学特定模式请参见
/references/jungian-diagrams.md
此技能与 jungian-psychologist 紧密集成,用于:
在适当时,为受益于渲染的图表提供 Mermaid 符号:
graph TD
A[Conscious] --> B[Personal Unconscious]
B --> C[Collective Unconscious]
B --> D[Complexes]
C --> E[Archetypes]
记住:一张好图胜过千言万语。每当出现复杂概念时,主动创建它们。
每周安装
68
仓库
GitHub 星标
80
首次出现
Jan 24, 2026
安全审计
安装于
gemini-cli58
opencode58
codex57
cursor56
github-copilot54
cline48
Master of text-based visual communication. Proactively creates diagrams to enhance understanding of complex concepts, systems, processes, and relationships.
"Above all else, show the data." — Edward Tufte
Diagrams should:
Use for:
NOT for:
Ask yourself: "Would this be clearer with a picture?" If yes → diagram it.
See
/references/diagram-types.mdfor complete taxonomy
| Type | Use For | Key Pattern |
|---|---|---|
| Flowchart | Processes, decisions | Boxes + arrows |
| Hierarchy | Org structures, taxonomies | Tree structure |
| Layers | System architecture | Stacked boxes |
| Relationship | Connections, networks | Nodes + edges |
| Sequence | Time-ordered events | Vertical flow |
| Comparison | Side-by-side analysis | Parallel columns |
| Cycle | Feedback loops | Circular arrows |
| Matrix | 2D categorization | Grid structure |
See
/references/unicode-characters.mdfor complete character set
BOXES: ARROWS: CONNECTORS:
┌─┬─┐ ╔═╦═╗ → ← ↑ ↓ ├ ┤ ┬ ┴
│ │ │ ║ ║ ║ ◄ ► ▲ ▼ ╠ ╣ ╦ ╩
├─┼─┤ ╠═╬═╣ ⟶ ⟵ ⟷ ┼ ╋ ╬
│ │ │ ║ ║ ║ ⇒ ⇐ ⇔
└─┴─┘ ╚═╩═╝ ──► ◄── EMPHASIS:
═══ ━━━
ROUNDED: BULLETS: ═══ ━━━
╭───╮ • ○ ●
│ │ ├── └── DASHED:
╰───╯ ■ □ ▪ ┄ ┅ ┆ ┇
MAXIMIZE: MINIMIZE:
┌─────────────────┐ ╔══════════════════╗
│ Essential info │ ║ ╭──────────────╮ ║
│ Clear structure │ ║ │ Same info │ ║
│ Direct labeling │ ║ │ + decoration │ ║
└─────────────────┘ ║ ╰──────────────╯ ║
╚══════════════════╝
✓ Good ✗ Chartjunk
CHUNKING: Group related elements
BAD: GOOD:
┌─┬─┬─┬─┬─┬─┬─┬─┐ ┌─────┐ ┌─────┐ ┌─────┐
│A│B│C│D│E│F│G│H│ │ A B │ │ C D │ │ E F │
└─┴─┴─┴─┴─┴─┴─┴─┘ │ (1) │ │ (2) │ │ (3) │
└─────┘ └─────┘ └─────┘
PROXIMITY: SIMILARITY: ENCLOSURE:
○ ○ ● ● ○ ● ○ ● ○ ┌───────────┐
○ ○ ● ● ● ○ ● ○ ● │ ○ ○ ○ ○ ○ │
Groups by Groups by │ (grouped) │
nearness appearance └───────────┘
EMPHASIS LEVELS:
═══════════════════════ Level 1: Double/Heavy
─────────────────────── Level 2: Single
- - - - - - - - - - - - Level 3: Dashed
. . . . . . . . . . . . Level 4: Dotted
SIZE HIERARCHY:
╔═══════════════════════════╗
║ PRIMARY ELEMENT ║
╠═══════════════════════════╣
│ Secondary Element │
├───────────────────────────┤
│ tertiary element │
└───────────────────────────┘
See
/references/patterns-library.mdfor comprehensive patterns
┌─────────┐ ┌─────────┐ ┌─────────┐
│ Start │───►│ Process │───►│ End │
└─────────┘ └─────────┘ └─────────┘
┌──────────┐
│ Decision │
└────┬─────┘
┌─────────┴────────┐
▼ ▼
┌────────┐ ┌────────┐
│ Yes │ │ No │
└────────┘ └────────┘
┌─────────────────────────────────────┐
│ PRESENTATION LAYER │
├─────────────────────────────────────┤
│ BUSINESS LOGIC │
├─────────────────────────────────────┤
│ DATA ACCESS │
├─────────────────────────────────────┤
│ DATABASE │
└─────────────────────────────────────┘
┌──────────────────┐
│ │
▼ │
┌───────┐ ┌───┴───┐
│ Input │─────────►│Output │
└───────┘ └───────┘
▲ │
│ │
└──────────────────┘
✗ BAD: Excessive decoration
╔══════════════════════════════════╗
║ ╭━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╮ ║
║ ┃ ★ ★ ★ IMPORTANT INFO ★ ★ ★ ┃ ║
║ ╰━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╯ ║
╚══════════════════════════════════╝
✓ GOOD: Clean and direct
┌──────────────────┐
│ Important Info │
└──────────────────┘
✗ BAD: Crossing lines, unclear flow
┌───┐ ┌───┐
│ A │──┬──│ B │
└───┘ │ └───┘
│ ╳ │
┌─┴─┐ │ ┌─┴─┐
│ C │──┴──│ D │
└───┘ └───┘
✓ GOOD: Clear hierarchy, minimal crossings
┌───┐ ┌───┐
│ A │ │ B │
└─┬─┘ └─┬─┘
│ │
▼ ▼
┌───┐ ┌───┐
│ C │ │ D │
└───┘ └───┘
✗ BAD: Too much in one diagram
[Cramming 15 concepts with 30 arrows]
✓ GOOD: Break into focused diagrams
"Overview Diagram" + "Detail Diagram A" + "Detail Diagram B"
Works with:
See
/references/jungian-diagrams.mdfor psychology-specific patterns
This skill integrates closely with jungian-psychologist for:
When appropriate, provide Mermaid notation for diagrams that benefit from rendering:
graph TD
A[Conscious] --> B[Personal Unconscious]
B --> C[Collective Unconscious]
B --> D[Complexes]
C --> E[Archetypes]
Remember : A good diagram is worth a thousand words. Create them proactively whenever complex concepts arise.
Weekly Installs
68
Repository
GitHub Stars
80
First Seen
Jan 24, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
gemini-cli58
opencode58
codex57
cursor56
github-copilot54
cline48
Python PDF处理教程:合并拆分、提取文本表格、创建PDF文件
66,200 周安装
JSON 转 React Email 渲染器:用 JSON 规范生成 HTML/纯文本邮件 | @json-render/react-email
8 周安装
runtime-context技能:AI智能体运行时环境检测与工具适配,实现跨平台兼容性
9 周安装
JSON 转 SVG/PNG 图像渲染器 - 使用 Satori 将 JSON 规范快速生成图片
9 周安装
学术论文写作智能体工具:12个AI智能体流水线,支持LaTeX/PDF输出,涵盖所有学科
63 周安装
check-version插件:70毫秒快速检查Claude插件版本,自动提示更新
9 周安装
对抗性代码审查工作流:Hunter/Skeptic/Referee 消除偏见,提升缺陷检测准确率
10 周安装