Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计通过

architecture架构

Agent Skill

用于辅助图像生成、图片编辑、视觉素材处理或图像模型工作流。它适合让 Agent 根据文本生成图片、处理背景、整理视觉提示词或调用相关图像工具。使用时需要确认输入图片、版权来源、输出格式和模型限制;涉及人物、品牌、商品或公开展示素材时,应额外核对授权、真实性和内容合规边界。

总安装

349

周安装

15

GitHub Stars

公开资料未说明

下载量

122
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:architecture(架构)
来源仓库:https://github.com/vilin1927/autoflux-landing
仓库路径:skills/architecture
安装命令:
npx skills add https://github.com/vilin1927/autoflux-landing --skill architecture
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/vilin1927/autoflux-landing --skill architecture

简介

用于辅助图像生成和图片编辑的视觉素材处理工作流。

  • 适合生成图片、处理背景或调用图像工具。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。
  • 通过 npx skills add 命令从 GitHub 仓库安装使用。
  • 需确认输入图片版权、输出格式及模型限制条件。
  • architecture 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Architecture Decision Framework

"Requirements drive architecture. Trade-offs inform decisions. ADRs capture rationale."

Selective Reading Rule

Read ONLY files relevant to the request! Check the content map, find what you need.

FileDescriptionWhen to Read
context-discovery.mdQuestions to ask, project classificationStarting architecture design
trade-off-analysis.mdADR templates, trade-off frameworkDocumenting decisions
pattern-selection.mdDecision trees, anti-patternsChoosing patterns
examples.mdMVP, SaaS, Enterprise examplesReference implementations
patterns-reference.mdQuick lookup for patternsPattern comparison

Core Principle

"Simplicity is the ultimate sophistication."

  • Start simple
  • Add complexity ONLY when proven necessary
  • You can always add patterns later
  • Removing complexity is MUCH harder than adding it

Code Style Rules

General Principles

  • Early return pattern: Always use early returns over nested conditions for better readability
  • Avoid code duplication through creation of reusable functions and modules
  • Decompose long (80+ lines) components/functions into smaller ones. Keep in same file if single-use; split if file exceeds 200 lines
  • Keep functions focused and under 50 lines when possible
  • Avoid deep nesting (max 3 levels)
  • Proper error handling with typed catch blocks

Library-First Approach

  • ALWAYS search for existing solutions before writing custom code

- Check package registries for existing libraries - Evaluate existing services/SaaS solutions - Consider third-party APIs for common functionality

  • Custom code IS justified when:

- Specific business logic unique to the domain - Performance-critical paths with special requirements - When external dependencies would be overkill - Security-sensitive code requiring full control

  • Remember: Every line of custom code is a liability that needs maintenance, testing, and documentation

Architecture and Design

  • Clean Architecture & DDD Principles:

- Follow domain-driven design and ubiquitous language - Separate domain entities from infrastructure concerns - Keep business logic independent of frameworks - Define use cases clearly and keep them isolated

  • Naming Conventions:

- AVOID generic names: utils, helpers, common, shared - USE domain-specific names: OrderCalculator, UserAuthenticator, InvoiceGenerator - Follow bounded context naming patterns - Each module should have a single, clear purpose

  • Separation of Concerns:

- Do NOT mix business logic with UI components - Keep database queries out of controllers - Maintain clear boundaries between contexts

Anti-Patterns to Avoid

  • NIH (Not Invented Here) Syndrome: Don't build what already exists (auth, state management, form validation)
  • Generic Naming: No utils.js with 50 unrelated functions, no helpers/misc.js as a dumping ground
  • Poor Boundaries: Mixing business logic with UI, database queries in controllers, unclear separation of concerns

Tech Stack Coverage

Languages: TypeScript, JavaScript, Python, Go, Swift, Kotlin Frontend: React, Next.js, React Native, Flutter Backend: Node.js, Express, GraphQL, REST APIs Database: PostgreSQL, Prisma, NeonDB, Supabase DevOps: Docker, Kubernetes, Terraform, GitHub Actions Cloud: AWS, GCP, Azure


Validation Checklist

Before finalizing architecture:

  • Requirements clearly understood
  • Constraints identified
  • Each decision has trade-off analysis
  • Simpler alternatives considered
  • ADRs written for significant decisions
  • Team expertise matches chosen patterns
  • Code follows Clean Architecture boundaries
  • No premature optimization or over-engineering

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

38.76%
按下载量换算47

Claude

28.99%
按下载量换算35

Cursor

19.63%
按下载量换算24

Gemini CLI

9.19%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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