Token导航 LogoToken导航

Agent Skill · 开发

moai-library-mermaid(moai library Mermaid 命令行)

moai-library-mermaid 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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。

moai-library-mermaid 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证为 MIT,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 21,366。

总安装 190周安装 8GitHub Stars 21下载 67核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

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:moai-library-mermaid(moai library Mermaid 命令行)
来源仓库:https://github.com/modu-ai/moai-rank
仓库路径:skills/moai-library-mermaid
安装命令:
npx skills add https://github.com/modu-ai/moai-rank --skill moai-library-mermaid
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/modu-ai/moai-rank --skill moai-library-mermaid

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

moai-library-mermaid 辅助 Mermaid 图表生成和维护。适合流程图、时序图和架构图的代码编写与审查。需结合项目文档规范和渲染引擎版本确保兼容性。避免生成无法正确渲染的语法错误图表定义。moai-library-mermaid 属于开发类 Skill,可作为该场景下的辅助能力补充。

建议通过在线预览工具验证图表的可读性和准确性。

来源仓库内路径:skills/moai-library-mermaid

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/modu-ai/moai-rank --skill moai-library-mermaid;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

moai-library-mermaid 怎么安装?

在终端执行 npx skills add https://github.com/modu-ai/moai-rank --skill moai-library-mermaid。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

moai-library-mermaid 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

moai-library-mermaid 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

moai-library-mermaid 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

moai-library-mermaid 用的人多吗?

公开数据是累计安装 190 次,近一周安装 8 次,下载 67 次,GitHub 21 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

moai-library-mermaid 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
moai-library-mermaid

moai library Mermaid 命令行 · 本页

19021操作浏览器MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Quick Reference

Mermaid Diagram Expert v7.1.0 - Pure skill-based Mermaid rendering for Claude Code with MCP Playwright integration.

This skill provides complete Mermaid 11.12.2 syntax for all 21 diagram types, MCP Playwright integration for rendering SVG and PNG outputs, ready-to-use examples and reference documentation, and enterprise diagram patterns with best practices.

To invoke this skill, use the standard skill invocation pattern with the skill name moai-library-mermaid.

Supported Diagram Types

The skill supports 21 diagram types organized into five categories:

Structural Diagrams include Flowchart for process flows and decision trees, Sequence for interaction sequences and message flows, Class for object-oriented class relationships, ER for entity-relationship databases, Block for block diagram structures, and State for state machines and stateful flows.

Timeline and Tracking diagrams include Timeline for chronological events and milestones, Gantt for project scheduling and timelines, and Gitgraph for Git workflow and branching visualization.

Architecture and Design diagrams include C4 for Context, Container, Component, and Code architecture diagrams, Architecture for system architecture diagrams, and Requirement for requirements and traceability documentation.

Data Visualization diagrams include Pie Chart for pie and donut charts, XY Chart for scatter and line charts, Sankey for flow diagrams with proportional width, and Radar for multi-variable comparison charts.

User and Process diagrams include Mindmap for hierarchical mind mapping, User Journey for user experience flows, Kanban for board state visualization, and Packet for network packet structures.

MCP Playwright Integration

This skill integrates with MCP Playwright for diagram rendering. The MCP configuration in the project mcp.json file enables the Playwright server, which can be configured to use npx with the anthropic-ai playwright-mcp package.

To render diagrams, the MCP Playwright server must be configured in the project MCP settings, Node.js must be installed on the system, and Playwright must be available through npx.


Implementation Guide

Diagram Syntax Patterns

Flowchart diagrams use the flowchart keyword followed by direction indicators such as TD for top-down or LR for left-right. Nodes are defined with brackets for shapes where round brackets create rounded rectangles, square brackets create standard rectangles, curly braces create rhombus decision nodes, and double brackets create stadium-shaped nodes. Connections use arrow syntax with double dashes and angle brackets for arrows, with optional pipe-delimited labels for edge descriptions. Subgraphs group related nodes using the subgraph keyword with a title and end delimiter.

Sequence diagrams define participants first using the participant keyword, then show interactions using arrow notation. Solid arrows with double angle brackets represent synchronous calls, while dashed arrows represent responses or asynchronous messages. Activation rectangles show participant activity duration using activate and deactivate keywords or the plus and minus shorthand on arrows. Notes can be added to the right, left, or over participants.

C4 Context diagrams use the C4Context keyword and define system boundaries using Enterprise_Boundary or System_Boundary functions. Persons are defined with the Person function taking an ID, name, and optional description. Systems are defined with System for internal systems and System_Ext for external systems. Relationships use the Rel function specifying source, target, description, and optional technology.

Class diagrams use the classDiagram keyword and define classes with their attributes and methods. Relationships include inheritance using the angle bracket and pipe symbols, composition using asterisk, aggregation using circle, and association using dashes. Visibility modifiers use plus for public, minus for private, and hash for protected.

State diagrams use the stateDiagram-v2 keyword for the newer syntax. States are defined with the state keyword and brackets. Transitions use arrow notation with optional labels. Composite states contain nested states within the state block.

Diagram Categories

Process and Flow diagrams encompass Flowchart, Sequence, State, Timeline, Gitgraph, and User Journey diagram types. These diagrams represent dynamic processes and temporal sequences.

Structure and Design diagrams include Class, ER, Block, Architecture, and C4 types. These diagrams represent static structures and system compositions.

Data and Analytics diagrams cover Pie Chart, XY Chart, Sankey, and Radar types. These diagrams visualize quantitative data and comparative metrics.

Planning and Organization diagrams include Gantt, Mindmap, Kanban, and Requirement types. These diagrams support project management and requirements tracking.

Network and Technical diagrams currently include the Packet type with additional types reserved for future extensions.

Best Practices

Clarity and Readability guidelines recommend using descriptive labels for all nodes, keeping diagram complexity moderate with a maximum of 20 to 30 nodes, and using consistent styling and color schemes throughout the diagram.

Performance considerations include breaking complex diagrams into multiple smaller diagrams, using subgraphs to organize large flowcharts, and limiting text length within nodes to maintain rendering performance.

Accessibility requirements include providing text alternatives for all diagrams, using both color and shape differentiation rather than color alone, and including descriptive titles and legends for context.

Organization practices recommend grouping related diagrams in directories, using consistent naming conventions for diagram files, and documenting diagram purposes in comments within the source files.


Advanced Patterns

Integration with MoAI-ADK

This skill is designed for use within Claude Code during various development phases:

During the architecture phase with the moai:1-plan command, create system design diagrams to visualize proposed solutions and component relationships.

During the documentation phase with the moai:3-sync command, generate visual documentation including flowcharts, sequence diagrams, and architecture overviews.

During code review phases, use diagrams to communicate system design visually and highlight areas of concern or proposed changes.

During onboarding processes, create diagrams that help new team members understand architecture, data flows, and system boundaries.

Common Architecture Patterns

API Architecture patterns typically use C4 diagrams to show system context with API gateway, backend services, database layer, and cache layer relationships.

Microservices Flow patterns use sequence diagrams to illustrate client requests flowing through API gateway to individual services and their data stores.

Data Pipeline patterns use flowchart diagrams to show data movement through extract, transform, load, validate, and report stages.

Context7 Integration

For the latest Mermaid documentation, use Context7 library resolution and documentation tools. The current stable version is Mermaid 11.12.2 as of December 2025.

Official documentation is available at mermaid.js.org/intro for general documentation and mermaid.js.org/config/setup/modules/mermaidAPI.html for API reference.

Release notes and migration guides are available in the Mermaid GitHub repository releases section.

Learning Resources

The official Mermaid site is located at mermaid.js.org. An interactive live editor for testing diagrams is available at mermaid.live. The complete syntax guide is at mermaid.js.org/syntax/.

For working examples of all 21 diagram types, see the examples.md file in this skill directory. For extended reference documentation, see reference.md. For optimization techniques, see optimization.md. For complex diagram patterns, see advanced-patterns.md.


Works Well With

This skill integrates with several agents and other skills:

Agents that work well with this skill include workflow-docs for documentation with diagrams, workflow-spec for SPEC diagrams and requirements visualization, and design-uiux for architecture visualization and interface documentation.

Skills that complement this skill include moai-docs-generation for comprehensive documentation generation, moai-workflow-docs for diagram validation and documentation workflows, and moai-library-nextra for architecture documentation sites.

Commands that utilize this skill include moai:3-sync for documentation with embedded diagrams and moai:1-plan for SPEC creation with visual architecture diagrams.

Focus: Pure skill-based Mermaid rendering with MCP Playwright integration

平台分布

Claude Code

27.9%
按下载量换算19

OpenCode

21.43%
按下载量换算14

trae

17.54%
按下载量换算12

Antigravity

12.92%
按下载量换算9

windsurf

7.31%
按下载量换算5

Codex

4.01%
按下载量换算3

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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。

继续浏览同类 Skills