agentleFS
Binbin-miaoBinbin-miao/workbuddy-expert-team/skills/prior-art-research/SKILL.md

prior-art-research

Skill1 starsChanged 10 days agoMITView on GitHub

Proactively searches GitHub repositories, open-source ecosystems, and reference products to extract proven architectures, native components, and pitfalls before building from scratch.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

/prior-art-research — 开源优秀项目与现成方案对标检索(拒绝闭门造车)

融合 FoundationAgents/MetaGPT 的竞品/先例分析与 gsd-build/get-shit-done 的四维前置调研(Stack / Features / Architecture / Pitfalls):

一、 触发规则(1A + 2A 标准)

  1. 必触发场景:凡是从零开发新功能/新插件/新工具/新网页、技术选型、跨模块存储/架构改造、对接第三方框架/SDK、或产品横向对比,必须在写代码前先执行本检索!
  2. 免触发场景:纯修复本地既有代码的明确内部小 Bug,或单文件 ≤20 行的简单配置微调,直接查本地代码即可,无需浪费时间搜外部网页。

二、 四维深潜检索法(Search → Inspect Source → Extract Pattern → Adapt)

1. 多源精准检索(超越表面网页摘要)

  • GitHub 仓库与源码检索:
    • 使用搜索工具查询 <技术栈/框架> <功能关键词> github、site:github.com "<核心接口或事件名>"。
    • 通过 GitHub REST API 或网页抓取直接检视高星开源项目的目录结构、核心源码文件、最新 Release Notes 与高赞 Issues:
      • https://api.github.com/search/repositories?q=<keywords>&sort=stars&order=desc
      • https://api.github.com/repos/<owner>/<repo>/contents/<path>
  • 当前框架/生态原生能力排查:
    • 检索目标框架或宿主环境是否已经内置了现成组件、工具类或已安装的依赖库(遵循 Ponytail 阶梯:有原生组件绝不手搓劣质替代品)。

2. 四维提炼产出(GSD 4-Dimension Synthesis)

将检索结果浓缩为 20 行以内的《开源对标简报》,直接供《开工方案卡》与架构设计使用:

  • Stack & Native Components(现成组件/库):有哪些开箱即用的原生组件或成熟库?
  • Features & UX Patterns(交互与功能标杆):优秀同类项目有哪些贴心的交互细节?
  • Architecture & Data Flow(架构与数据结构借鉴):它们如何组织状态、存储与扩展接口?
  • Pitfalls & Edge Cases(前人踩过的坑):Issues 或源码注释里揭示了哪些容易踩中的平台限制或兼容性陷阱?

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.