se-patterns — community se-patterns, se-agent-builder, community, ide skills

v1.0.0
GitHub

关于此技能

非常适合需要为生产就绪的构建提供结构化软件工程原则的架构代理 SE design philosophy, architecture patterns, and decision guides for production-grade Relevance AI builds

RelevanceAI RelevanceAI
[0]
[1]
更新于: 3/10/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 4/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Concrete use-case guidance Explicit limitations and caution
Review Score
4/11
Quality Score
44
Canonical Locale
en
Detected Body Locale
en

非常适合需要为生产就绪的构建提供结构化软件工程原则的架构代理 SE design philosophy, architecture patterns, and decision guides for production-grade Relevance AI builds

核心价值

赋予代理应用 6 个关键模式来设计和审查 AI 系统，包括操作单元，使他们能够确保生产就绪并使用 SE 原则和架构模式调试故障

适用 Agent 类型

非常适合需要为生产就绪的构建提供结构化软件工程原则的架构代理

↓ 赋予的主要能力 · se-patterns

使用可扩展的架构设计新的 AI 代理
使用软件工程原则审查现有的构建以确保生产就绪性
使用操作单元模式调试生产故障

! 使用限制与门槛

  • 需要了解软件工程原则
  • 仅限于 6 个预定义模式

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The page lacks a strong recommendation layer.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作，再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”，而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核，以及是否已经进入工作流落地阶段。

安装路径

先进入安装与验证

如果这项技能值得继续，下一步应该先确认安装命令、CLI 写入路径与环境验证。
可信复核

回到可信合集再做一次复核

如果你还在比较不同技能或供应方，先回到可信合集做二次判断，而不是继续放大仓库噪音。
工作流

如果要进团队流转，转到工作流集合

当你的目标已经不是单个技能，而是团队协作、审批和交接，就应该转到工作流合集继续决策。
实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致，便于搜索引擎理解页面内容。

? FAQ

se-patterns 是什么？

非常适合需要为生产就绪的构建提供结构化软件工程原则的架构代理 SE design philosophy, architecture patterns, and decision guides for production-grade Relevance AI builds

如何安装 se-patterns？

运行命令：npx killer-skills add RelevanceAI/se-agent-builder/se-patterns。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

se-patterns 适用于哪些场景？

典型场景包括：使用可扩展的架构设计新的 AI 代理、使用软件工程原则审查现有的构建以确保生产就绪性、使用操作单元模式调试生产故障。

se-patterns 支持哪些 IDE 或 Agent？

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

se-patterns 有哪些限制？

需要了解软件工程原则；仅限于 6 个预定义模式。

↓ 安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行：npx killer-skills add RelevanceAI/se-agent-builder/se-patterns。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    se-patterns 已启用，可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考，但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论，再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

se-patterns

安装 se-patterns，这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

When to Use

  • Designing a new agent, tool, or workforce system
  • Reviewing an existing build for production readiness
  • Choosing which architecture pattern to apply
  • Pushing back on client requests that violate SE principles
  • Debugging production failures (start with Unit of Action)

Quick Reference: 6 Patterns + Decision Sequence

Check patterns in this order. The first "no" tells you which pattern to apply:

  1. Unit of Action — Is each task scoped to one entity? Fix this first.
  2. Note Step — Does every 3+ step tool have documentation?
  3. Centralize Rules — Are business rules in one place?
  4. Code Over LLM — Are deterministic decisions in code steps?
  5. Parameterize — Any duplicated tools or agents?
  6. Compute at Right Level — Is logic in the right layer?
  7. Data Over Routing — Do agents pass data, not instructions?
  8. Audit Enrichment — Do writes include who/when/why?

Pattern Summary

PatternProblem It SolvesKey Question
Compute at Right LevelLogic in wrong layer"Where does this data naturally live?"
ParameterizeTool/agent duplication"Am I copy-pasting to change one value?"
Centralize RulesScattered business logic"How many places define this rule?"
Code Over LLMWasted credits on deterministic logic"Can this be if/else?"
Data Over RoutingInvisible control flow"Am I passing data or instructions?"
Audit EnrichmentUntraceable agent actions"Can I explain WHY from data alone?"

Reference Files

FileContent
design-philosophy.mdSE lens for build decisions, 3-layer architecture, push-back scripts
unit-of-action.mdThe foundational pattern — one entity per task
system-design-patterns.mdAll 6 architecture patterns with anti-patterns and examples
note-step.mdDocumentation-as-first-step pattern for tools
decision-guide.mdMeta-guide: which pattern to apply when

相关技能

寻找 se-patterns 的替代方案 (Alternative) 或可搭配使用的同类 community Skill？探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

React 框架

★ 138.4k
⑂ 0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

★ 98.6k
⑂ 0
开发者工具