Token导航 LogoToken导航TokenDH.com
前端设计敏感数据github未标认证来源可访问许可证需确认审计通过

arch-diagrams拱形图

Agent Skill

arch-diagrams 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。

总安装

504

周安装

21

GitHub Stars

4

下载量

168
CodexClaudeCursorGemini CLI

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

unknown

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:arch-diagrams(拱形图)
来源仓库:https://github.com/alphaonedev/openclaw-graph
仓库路径:skills/arch-diagrams
安装命令:
npx skills add https://github.com/alphaonedev/openclaw-graph --skill arch-diagrams
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/alphaonedev/openclaw-graph --skill arch-diagrams

简介

用于生成架构图与流程图,适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

  • 支持 Mermaid 与 PlantUML 语法。
  • 适合系统设计文档与协作沟通。
  • 使用时需提供模块关系描述以生成准确图表。
  • arch-diagrams 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

arch-diagrams

Purpose

This skill allows OpenClaw to generate, edit, and render architecture diagrams using tools like C4 model, PlantUML, Mermaid, sequence diagrams, ERDs, and infrastructure diagrams. It integrates diagram creation into coding workflows for visualizing system designs.

When to Use

Use this skill when documenting software architecture, planning system interactions, or creating visual aids for ERDs and sequence flows. Apply it during design phases, code reviews, or when collaborating on infrastructure setups to quickly prototype diagrams from text descriptions.

Key Capabilities

  • Generate C4 diagrams from high-level descriptions.
  • Render PlantUML code into SVG or PNG outputs.
  • Create Mermaid diagrams for flowcharts, sequences, and ERDs.
  • Support infrastructure diagrams with tools like AWS or generic cloud icons.
  • Edit existing diagrams by parsing and modifying source code (e.g., PlantUML syntax).
  • Export diagrams as code snippets or image files for inclusion in docs.

Usage Patterns

To accomplish tasks, provide a clear text description or partial diagram code to OpenClaw, then specify the diagram type. For example, invoke the skill via CLI or API with inputs like JSON configs. Always include context, such as "Generate a C4 container diagram for a web app with a database." Handle iterations by chaining commands, e.g., generate, review, and refine. Use environment variables for authentication, like setting $OPENCLAW_API_KEY before operations.

Common Commands/API

Use the OpenClaw CLI for direct execution or API for programmatic access. Authenticate with $OPENCLAW_API_KEY in your environment.

  • CLI Command: openclaw arch-diagrams generate --type mermaid --input "sequenceDiagram: A->B: Request" --output diagram.md This generates a Mermaid sequence diagram from the input string and saves it to a file.
  • API Endpoint: POST to /api/v1/arch-diagrams/generate with JSON body: {"type": "plantuml", "description": "@startuml\nAlice -> Bob: Hello\n@enduml", "format": "svg"} Response includes the rendered SVG; handle with HTTP headers for authentication.
  • Config Format: Use YAML for inputs, e.g., type: c4 elements: - name: System type: container Pass this via CLI flag: --config path/to/config.yaml.
  • Code Snippet (Python): import requests response = requests.post('https://api.openclaw.ai/api/v1/arch-diagrams/generate', json={"type": "erd", "input": "User has many Posts"}, headers={'Authorization': f'Bearer {os.environ["OPENCLAW_API_KEY"]}'}) print(response.json()['output'])

Integration Notes

Integrate this skill into your workflow by adding it to IDE extensions (e.g., VS Code plugin for OpenClaw) or CI/CD pipelines. For example, in a GitHub Action, use: run: openclaw arch-diagrams generate --type sequence --input./specs.md && echo '::set-output name=diagram::$(cat diagram.md)'. Set $OPENCLAW_API_KEY as a secret in your environment. When combining with other skills, pipe outputs; e.g., generate a diagram from code analysis results. Ensure compatibility by specifying versions, like OpenClaw CLI v2.5+.

Error Handling

Always check for errors by parsing response codes or CLI exit statuses. For invalid inputs, OpenClaw returns HTTP 400 with details like "Invalid PlantUML syntax: missing @enduml". Handle network issues by retrying with exponential backoff, e.g., in code: if response.status_code == 503: time.sleep(5); retry(). Validate inputs before sending, such as ensuring diagram types are from ["c4", "mermaid", "plantuml", "sequence", "erd"]. Use try-except blocks for API calls, e.g.,

try:
    result = requests.post(url, json=data)
    result.raise_for_status()
except requests.exceptions.HTTPError as e:
    print(f"Error: {e.response.text} - Fix input and retry")

Concrete Usage Examples

  1. Generate a C4 System Diagram: To visualize a simple web application, run: openclaw arch-diagrams generate --type c4 --input "System: WebApp with Database and API" --output c4_diagram.puml. This produces a PlantUML file for a C4 system context diagram. Review and refine by adding: openclaw arch-diagrams edit --file c4_diagram.puml --add "Container: Frontend".
  2. Create an ERD for a Database Schema: For modeling relationships, use: openclaw arch-diagrams generate --type erd --input '{"entities": [{"name": "User", "attributes": ["id", "name"]}, {"name": "Post", "attributes": ["id", "content"]}]}' --output erd.mmd. This outputs a Mermaid ERD code, which you can render in Markdown files.

Graph Relationships

  • In C4 diagrams: "System depends on External System", "Container uses Component".
  • In Sequence diagrams: "Actor sends message to Object", "Object returns response to Actor".
  • In ERDs: "Entity has one-to-many relationship with another Entity", "Attribute belongs to Entity".
  • In Infrastructure diagrams: "Server connects to Database", "Load Balancer routes to Service".

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

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

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

Codex

38.52%
按下载量换算65

Claude

32.43%
按下载量换算54

Cursor

18.1%
按下载量换算30

Gemini CLI

8.85%
按下载量换算15

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

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