research-git-repos
仓库创建 2026年7月26日最近提交 19 小时前SkillHot 收录 15 小时前
这个 Skill 做什么
教你用 git clone(shallow)把仓库拉到本地,用文件系统工具看文件和目录,比在 github.com 上翻页面更快也更完整。当你需要理解代码库布局、编码约定或某个功能具体实现时就用,适合做深度代码调研。优点是省资源、不被网页截断或分页限制,能一次性读取真实文件内容。
▸ 展开 SKILL.md 英文原文
How to research a git repository's code, structure, or conventions: clone it shallowly and read it locally with your filesystem tools instead of fetching github.com pages over the web. Load when a task involves understanding a codebase, a repo's layout, its conventions, how a feature is implemented, or anything answerable from the repository's own files.
0
Stars
0
Forks
10
仓库内 Skill
积累中
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/fagerbergj/dotagents/main/skills/research-git-repos/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/fagerbergj/dotagents/main/skills/research-git-repos/SKILL.md"SKILL.MD 节选查看完整文件 ↗
Researching a repository through web_fetch of github.com pages is the wrong tool: each page fetch burns tokens on HTML chrome for a fraction of one file, directory listings paginate, and rendered blobs truncate. The repository itself is cheaper and complete. ## The workflow 1. `git_clone` the repo (shallow is the default - history costs nothing to skip when you're reading code). Clone once; every later step is local. 2. `cd` into the clone. This moves your working directory into the repo (so every later path is repo-relative - pass `README.md`, not `<repo>/README.md`) AND loads the repo's own context: it returns the nearest AGENTS.md/CLAUDE.md (the project's instructions - read and FOLLOW
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有