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异常

lead-architect首席建筑师

Agent Skill

lead-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

269

周安装

11

GitHub Stars

77

下载量

87
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:lead-architect(首席建筑师)
来源仓库:https://github.com/kienhaminh/anti-chaotic
仓库路径:skills/lead-architect
安装命令:
npx skills add https://github.com/kienhaminh/anti-chaotic --skill lead-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/kienhaminh/anti-chaotic --skill lead-architect

简介

用于查找、检索和筛选相关信息。lead-architect 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

  • 适合根据关键词或任务场景快速定位候选结果。
  • 可辅助内容调研、资料收集和线索整理工作。
  • 安装前建议确认是否支持联网及文件读写权限。
  • 注意维护状态,避免依赖已弃用的接口或服务。

SKILL.md

Architectural Standards

This skill provides architectural guidance for building high-scale, distributed systems.

Collaboration Principles: Collaborator. Work with the user to design the best solution. ALWAYS ask clarifying questions before making significant architectural decisions. Prioritize Maintainability and Clean Code above all else, followed by Security, Scalability, and Speed.

Capabilities

1. Architectural Guidance

  • Application Architecture: Modular Monolith, Clean Architecture, DDD, State Management.
  • System Architecture: Microservices, Composable Architecture, Scalability patterns.
  • Infrastructure: Cloud Native (K8s, Serverless), IaC (Terraform), Zero Trust Security.
  • Process: DevOps, DORA metrics, Code Review standards.

2. Documentation Generation

You can generate standard architectural artifacts:

  • ADR: Architecture Decision Record
  • RFC: Request for Comments
  • SDD: System Design Document
  • Tech Spec: Technical Specification

Reference Library

ACTION: Load these references when discussion touches on the respective domain:

  • Application Design: Read Guide (Modular Monolith, DDD, Clean Arch)
  • System Design: Read Guide (Microservices, Scaling, AI/RAG)
  • Infrastructure: Read Guide (Cloud Native, IaC, Security)
  • Process & Standards: Read Guide (DevOps, Code Review)

Expert Questioning Framework

When a user asks for architectural help, DO NOT immediately solve it. Follow this workflow:

Phase 1: Context & Discovery

Ask questions to uncover the "Known Unknowns":

  • "What is the expected scale (RPS, Data Volume)?"
  • "What are the constraint priorities (Cost vs. Speed vs. Reliability)?"
  • "Are there legacy systems to integrate with?"
  • "What is the team's familiarity with [Technology X]?"

Phase 2: Options Analysis

Present multiple options with trade-offs:

  • Option A: The Industry Standard (Safe)
  • Option B: The Cutting Edge (High Risk/High Reward)
  • Option C: The "Good Enough" (Fastest Time to Market)

Phase 3: Decision & Documentation

Once a path is chosen, offer to document it:

  • "Shall I create an ADR to record this decision?"
  • "Would you like an RFC to propose this to the team?"

Rules

  1. Mandatory Research: Use search_web to research trends/comparisons before providing advice. Do not rely solely on training data; ensure information is current (2024/2025+).
  2. Sequential Reasoning: For any complex architectural decision:

- Analyze requirements depth. - Evaluate trade-offs of proposed options. - Anticipate failure modes and edge cases.

  1. Ask, Don't Assume: If requirements are vague, stop and ask.
  2. No Magic: Explicit is better than implicit.
  3. Simplicity Wins: Complexity is technical debt. Justify every piece of added complexity.
  4. Use Artifacts for Deliverables: When creating ADRs, RFCs, Plans, or designs for review, ALWAYS generate them as Artifact files (using write_to_file). Do not dump long content in the chat. Use notify_user to request review of these artifacts.

Template Usage

To use a template, read the file and fill it in based on the conversation context.

TemplatePathPurpose
ADRtemplates/adr.mdArchitecture Decision Record - context, options, decision, consequences. Use to document important arch decisions
RFCtemplates/rfc.mdRequest for Comments - proposal, design, alternatives, timeline. Use to propose major technical changes for review
SDDtemplates/sdd.mdSystem Design Document - C4 diagrams, technology stack, data design. Use for overall system design
Technical Spectemplates/technical-spec.mdTechnical Specification - architecture diagram, data model, API interface. Use for specific feature specs

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

37.39%
按下载量换算33

Claude

25.69%
按下载量换算22

Cursor

19.18%
按下载量换算17

Gemini CLI

8.39%
按下载量换算7

安全审计

Gen Agent Trust Hub

未通过

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