对话中实时捕捉复杂想法为图表 - 支持Mermaid的AI思维可视化工具

capture by designnotdrum/brain-jar

1 周安装量

2 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/designnotdrum/brain-jar --skill capture

数据可视化团队协作知识管理

🇨🇳中文介绍

视觉捕捉

在对话过程中将复杂想法捕捉为图表。图表在不同会话间持续保存。

使用时机

在以下情况触发视觉捕捉：

进行涉及多个相互关联概念的头脑风暴时
讨论系统架构或数据流时
解释流程或步骤序列时
映射实体间关系时
记录决策及其依赖关系时

图表类型选择

根据捕捉内容匹配图表类型：

情境	图表类型
头脑风暴、探索想法	`mindmap`
包含决策点的流程	`flowchart`
随时间推移的交互	`sequence`
系统组件与连接	`architecture`（使用流程图语法）

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

联系我们

Mermaid 快速参考

思维导图（用于头脑风暴）：

mindmap
  root((Central Idea))
    Branch 1
      Leaf 1a
      Leaf 1b
    Branch 2
      Leaf 2a

流程图（用于流程）：

flowchart TD
    A[Start] --> B{Decision}
    B -->|Yes| C[Action 1]
    B -->|No| D[Action 2]
    C --> E[End]
    D --> E

序列图（用于交互）：

sequenceDiagram
    participant User
    participant API
    participant DB
    User->>API: Request
    API->>DB: Query
    DB-->>API: Result
    API-->>User: Response

ER 图（用于数据模型）：

erDiagram
    USER ||--o{ ORDER : places
    ORDER ||--|{ LINE_ITEM : contains
    PRODUCT ||--o{ LINE_ITEM : "ordered in"

上下文的重要性

创建图表时始终提供丰富的上下文：

不良上下文：

良好上下文：

"实时通知系统的架构。展示事件如何从用户操作通过事件总线流向连接的客户端。在头脑风暴移动应用项目的通知功能时创建。"

上下文有助于您（和 Claude）在后续回顾时理解图表的用途。

global — 个人思维模式，可在项目间复用
project: — 特定于项目（根据工作目录自动检测）

子代理模式（可选）

对于包含大量上下文的复杂对话，可选择使用 Haiku 子代理进行草稿：

[Task tool with model: "haiku"]
Prompt: "Review the conversation above about [topic]. Draft a [diagram-type]
diagram capturing the key concepts discussed. Return only valid Mermaid syntax."

长时间头脑风暴会议，想法分散在多个消息中
架构自然形成的技术讨论
不确定最终结构应如何时

跳过子代理的情况：

图表结构在脑海中已清晰
节点较少的简单图表
正在迭代现有图表

草稿仅是起点 — 保存前请审查并完善。

图表捕捉后可以：

通过 get_diagram 和 update_diagram 检索和修改
通过 search_diagrams 按内容或上下文搜索
通过 export_diagram 导出为 Mermaid 文件或其他格式
在未来的对话中用作上下文

resume — 继续处理现有图表

🇺🇸English

Visual Capture

Capture complex ideas as diagrams during conversations. Diagrams persist across sessions.

When to Use

Trigger visual capture when:

Brainstorming ideas with many interconnected concepts
Discussing system architecture or data flow
Explaining a process or sequence of steps
Mapping relationships between entities
Documenting decisions and their dependencies

Diagram Type Selection

Match the diagram type to what you're capturing:

Situation	Diagram Type
Brainstorming, exploring ideas	`mindmap`
Process with decision points	`flowchart`
Interactions over time	`sequence`
System components and connections	`architecture` (use flowchart syntax)
Data models and relationships	`erd`
Object relationships	`classDiagram`
State transitions	`stateDiagram`
Project timeline	`gantt`

Creating a Diagram

Identify the core concept — What's the central idea or starting point?
List key relationships — What connects to what?
Choose the right type — Match the diagram type to the thinking pattern
Write Mermaid syntax — Keep it simple; you can always add detail later
Add rich context — Explain what this diagram represents and why

Mermaid Quick Reference

Mindmap (for brainstorming):

mindmap
  root((Central Idea))
    Branch 1
      Leaf 1a
      Leaf 1b
    Branch 2
      Leaf 2a

Flowchart (for processes):

flowchart TD
    A[Start] --> B{Decision}
    B -->|Yes| C[Action 1]
    B -->|No| D[Action 2]
    C --> E[End]
    D --> E

Sequence (for interactions):

sequenceDiagram
    participant User
    participant API
    participant DB
    User->>API: Request
    API->>DB: Query
    DB-->>API: Result
    API-->>User: Response

ERD (for data models):

erDiagram
    USER ||--o{ ORDER : places
    ORDER ||--|{ LINE_ITEM : contains
    PRODUCT ||--o{ LINE_ITEM : "ordered in"

Context Matters

Always provide rich context when creating diagrams:

Bad context:

"Architecture diagram"

Good context:

"Architecture for the real-time notification system. Shows how events flow from user actions through the event bus to connected clients. Created while brainstorming the notification feature for the mobile app project."

Context helps you (and Claude) understand the diagram's purpose when you return to it later.

Scope Selection

global — Personal thinking patterns, reusable across projects
project: — Specific to a project (auto-detect from working directory)

Subagent Pattern (Optional)

For complex conversations with lots of context, optionally use a Haiku subagent to draft:

[Task tool with model: "haiku"]
Prompt: "Review the conversation above about [topic]. Draft a [diagram-type]
diagram capturing the key concepts discussed. Return only valid Mermaid syntax."

When this helps:

Long brainstorming sessions with many ideas scattered across messages
Technical discussions where the architecture emerged organically
When you're unsure what the final structure should be

Skip the subagent when:

The diagram structure is already clear in your head
Simple diagrams with few nodes
You're iterating on an existing diagram

The draft is a starting point—review and refine before saving.

After Capture

Once captured, diagrams can be:

Retrieved and modified with get_diagram and update_diagram
Searched by content or context with search_diagrams
Exported to Mermaid files or other formats with export_diagram
Used as context in future conversations

Related Skills

resume — Continue working on an existing diagram

Weekly Installs

Repository

designnotdrum/brain-jar

GitHub Stars

First Seen

Today

Security Audits

Gen Agent Trust HubPass SocketPass SnykPass

Installed on

zencoder1

amp1

cline1

openclaw1

opencode1

cursor1

统计分析技能指南：描述性统计、趋势分析与异常值检测方法

867 周安装