Fectivnfy112357/github-explore

Name: Fectivnfy112357/github-explore
Author: Fectivnfy112357

Plugin插件 Native原生 ⭐ 8 MIT Search & Web Access搜索与联网 Approval & Security审批与安全 Dev Workflow开发与代码工作流

基于 gh CLI 的发现与管理封装，专为 AI 编程代理设计。提供仓库查找、多维度探索、趋势分析、仓库摘要、代码搜索、议题/PR 搜索及组织审计功能。

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

github-explore is an agent skill for AI coding agents that wraps the official GitHub CLI gh to deliver structured, deduplicated, relevance-ranked GitHub search results. It fixes three core problems with plain gh search for agents: noisy default star-sorted results, lack of semantic multi-axis exploration, and oversized context-heavy output. It works with over 15 agent CLIs including Claude Code, Codex, Cursor, and DeepSeek Harness (DSH), and can be installed via the npx skills add command for most agents, or via the built-in dsh plugin command for DSH users. Before first use, you must verify that your local gh CLI is properly authenticated.

The skill includes 9 separate scripts that cover different GitHub exploration and management use cases. You can use find_repos.py to search for repos on a specific topic, explore.py to map the full landscape of a technical field, discover.py to auto-expand related topics, and repo_summary.py to get structured metadata for a specific repository. Additional scripts handle trending projects, similar project search, code search, issue/PR search, and organization repository audits. It is designed for AI coding agent developers and researchers who need to explore open source projects on GitHub systematically, while keeping agent context usage low.

github-explore requires two core dependencies to work: a Python 3.10+ installation on your local machine, and a properly authenticated installation of the official GitHub CLI. It is released under the permissive MIT open source license, so there is no cost for personal or commercial use. By default, the skill filters out forked and archived repositories, sets a minimum star threshold for results, and saves full results to a temporary file on your system, leaving only a ~3KB layered summary in standard output to reduce context consumption. No unit test suite is included, as the scripts themselves are tested via real-world use.

github-explore 是一个面向 AI 编码代理的 GitHub 搜索技能，对 GitHub CLI（gh）的搜索命令做了封装，解决了原生搜索结果噪声大、无语义分面、输出占用过多上下文的问题，可输出结构化、去重、按相关性排序的搜索结果。该技能支持 Claude Code、Codex、Cursor 等十余个代理 CLI，也可作为原生插件安装到 DeepSeek Harness（DSH）。

典型使用场景包括搜索特定主题的 GitHub 仓库、绘制某技术领域的全景图谱、自动扩展相关主题、查看趋势项目、汇总单个仓库信息、寻找同类项目、搜索代码/Issue/PR 以及审计组织仓库。它适合 AI 编码代理开发者、需要调研特定技术领域开源项目的开发者使用，也能帮助代理减少上下文占用，提升搜索效率。

该技能依赖 Python 3.10+ 以及已完成身份认证的 GitHub CLI（gh），采用 MIT 许可证开源，无使用成本。默认会过滤分叉和已归档的仓库，设置最低星标门槛，完整结果输出到临时文件，标准输出只保留约 3KB 的分层摘要，降低上下文消耗。安装可通过 npx skills 或 DSH 自带的插件命令完成。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：github-explore（Fectivnfy112357/github-explore）
仓库：https://github.com/Fectivnfy112357/github-explore
本站详情页：https://www.yhbd.top/plugins/fectivnfy112357-github-explore/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 8 · 最近提交 2026-09-18 · 主语言 Python

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

Only 8 stars - very few users, little community feedback星标只有 8，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add github-explore

把 Fectivnfy112357/github-explore 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

15.1 KB · 缓存于 2026-08-25 04:53:41 · 15.1 KB

github-explore

Discovery + management wrappers around the gh CLI for AI coding agents.

English · 简体中文

What is this

github-explore is an agent skill that turns "search GitHub for X" into structured, deduplicated, relevance-scored output. It wraps gh search and gh repo view with smart filters, semantic multi-axis exploration, and layered output designed to keep an agent's context window small.

When you ask an agent "find multi-agent collaboration repos", you don't want a star-sorted dump of ollama, langchain, and a bunch of unrelated generic LLM frameworks. You want the canonical anchors (crewAI, autogen, MetaGPT, langgraph, camel, ChatDev, AutoGPT) surfaced first, with the protocol layer (A2A, ANP, ag-ui) as a separate axis, and awesome-* lists pushed to the bottom. That's what this skill does.

Why it exists

Plain gh search has three structural problems for agent-driven research:

Star-sorted default = giant noise. A query for "multi-agent" returns ollama (180k★) and langchain (140k★) on top because GitHub sorts by popularity, not topical fit.
No semantic axes. "Search repos about Y" is a one-dimensional query. Real topics have multiple semantic facets (frameworks vs. protocols vs. patterns) that should be explored in parallel and then unioned.
Output floods context. gh search repos --json returns full bodies, dates, and license objects per repo. Piping 50 of these into an LLM wastes thousands of tokens.

github-explore addresses all three with a thin layer of Python around gh.

Key features

Multi-axis exploration — explore.py lets the agent define 2-4 semantic axes per topic, runs them in parallel, and unions results with a relevance score that combines cross-axis hits, canonical anchor recall, and awesome-list signals.
Smart defaults — every discovery script filters forks and archived repos by default, enforces a minimum star floor, dedupes by fullName, and renders in a layered markdown summary (~3KB stdout).
Layered output — full reports go to %TEMP%/gh-explore-{topic}-{ts}.md automatically; the agent reads the summary, and pulls the file only when it needs more detail. Default exploration drops your context from ~18KB to ~2KB.
Field-level contract — python scripts/<script>.py --schema prints the output JSON structure for the three scripts that support it (find_repos, explore, repo_summary), backed by the schema files in skills/github-explore/scripts/schemas/. The other scripts' JSON mirrors gh search's native camelCase fields (documented in skills/github-explore/references/commands-search-format.md).
No new CLI surface — every script is a wrapper over gh search or gh repo view. You can drop the skill and run the same gh commands by hand; the value is in the filter, dedup, and relevance scoring.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 Fectivnfy112357/github-explore 的 README.md。在 GitHub 查看原文 →