Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计提醒

c4-architectc4 建筑师

Agent Skill

c4-architect 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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

374

周安装

15

GitHub Stars

9

下载量

121
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:c4-architect(c4 建筑师)
来源仓库:https://github.com/yuniorglez/gemini-elite-core
仓库路径:skills/c4-architect
安装命令:
npx skills add https://github.com/yuniorglez/gemini-elite-core --skill c4-architect
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/yuniorglez/gemini-elite-core --skill c4-architect

简介

用于生成 C4 模型架构图,支持多级抽象和 Mermaid.js 可视化。

  • 适用于 Codex、Claude、Cursor、Gemini CLI,翻译复杂系统需求。
  • 提供 Context、Container 和 Component 级别指导。
  • 安装方式:github,命令为 npx skills add https://github.com/yuniorglez/gemini-elite-core --skill c4-architect。
  • 建议确认目标受众和代码库结构,确保图表准确性。

SKILL.md

🏗️ Skill: c4-architect (v1.0.0)

Executive Summary

Senior Software Architect for 2026. Specialized in C4 Model visual communication, automated architectural mapping, and Mermaid.js orchestration. Expert in translating complex system requirements into clear, multi-level diagrams (Context, Container, Component) to align engineering and business stakeholders.


📋 The Conductor's Protocol

  1. Level Selection: Determine the required level of abstraction (L1 Context, L2 Container, or L3 Component) based on the target audience.
  2. State Mapping: Use codebase_investigator to extract the current system structure (apps, services, databases).
  3. Sequential Activation: activate_skill(name="c4-architect")activate_skill(name="mermaid-diagram-pro")activate_skill(name="docs-pro").
  4. Verification: Render the Mermaid code and verify that all relationships accurately reflect the current technical state.

🛠️ Mandatory Protocols (2026 Standards)

1. Level-Specific Documentation

As of 2026, C4 diagrams must be treated as "Living Documentation."

  • L1 (System Context): Always start here. Define the system boundary and its external actors (Users, 3rd party APIs).
  • L2 (Container): Decompose the system into deployable units (Next.js apps, NestJS services, PostgreSQL, NATS).
  • L3 (Component): Only create for high-complexity containers (e.g., the core Auth or Payment service).

2. Mermaid C4-Standard Syntax

  • Rule: Use the official C4Context, C4Container, and C4Component types in Mermaid.
  • Protocol: Always include a title and a Legend in every diagram.

3. Diagram-as-Code (DaC)

  • Rule: Never use static image files. Store diagrams as .mermaid files or embedded markdown blocks.
  • Protocol: Link diagram elements to the relevant source code directories using comments or metadata.

🚀 Show, Don't Just Tell (Implementation Patterns)

Level 1: System Context Diagram (L1)

C4Context
  title System Context Diagram for Squaads AI Core

  Person(user, "User", "Interacts with the AI Agents")
  System(squaads_core, "Squaads AI Core", "Orchestrates skills and agents")
  System_Ext(github, "GitHub API", "Provides codebase context")
  System_Ext(vercel, "Vercel", "Deployment target")

  Rel(user, squaads_core, "Uses", "HTTPS")
  Rel(squaads_core, github, "Reads code from", "REST/GraphQL")
  Rel(squaads_core, vercel, "Deploys to", "OIDC/HTTPS")

Level 2: Container Diagram (L2)

C4Container
  title Container Diagram for Squaads AI Core

  Person(user, "User")

  Container_Boundary(core, "AI Core System") {
    Container(cli, "Gemini CLI", "Bun, TypeScript", "Developer interface")
    Container(skill_registry, "Skill Registry", "Markdown, JSON", "Stores tactical knowledge")
    Container(agent_orchestrator, "Agent Orchestrator", "Google GenAI SDK", "Manages delegation")
  }

  Rel(user, cli, "Runs commands")
  Rel(cli, agent_orchestrator, "Invokes")
  Rel(agent_orchestrator, skill_registry, "Fetches expert content")

🛡️ The Do Not List (Anti-Patterns)

  1. DO NOT create Level 4 (Code) diagrams manually. They go stale instantly. Use automated tools if needed.
  2. DO NOT mix levels of abstraction. Don't show a specific React component next to a Person in an L1 diagram.
  3. DO NOT leave relationship arrows unlabeled. "Uses" is better than nothing, but "Authenticates via JWT" is elite.
  4. DO NOT ignore the Legend. Colors and shapes must be explained.
  5. DO NOT over-complicate. If a diagram has more than 15 elements, it should probably be split.

📂 Progressive Disclosure (Deep Dives)


🛠️ Specialized Tools & Scripts

  • scripts/extract-l2-containers.ts: Scans a monorepo's package.json files to generate an initial L2 Mermaid diagram.
  • scripts/lint-mermaid.sh: Validates Mermaid syntax and C4 standards.

🎓 Learning Resources


*Updated: January 23, 2026 - 19:30*

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

36.52%
按下载量换算44

Claude

28.52%
按下载量换算35

Cursor

17.66%
按下载量换算21

Gemini CLI

8.36%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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