github-researcher

作者: google-gemini

指导智能体如何阅读和搜索GitHub问题,以了解仓库中的问题。

npx skills add https://github.com/google-gemini/gemini-managed-agents-templates --skill github-researcher

GitHub Researcher Skill

This skill helps the agent find and understand issues in a specified GitHub repository, and gain a deep understanding of the codebase.

[!WARNING] GitHub CLI (gh) is NOT installed in this environment. Do NOT attempt to run gh commands. Always use the provided fetch_issues.py script to batch fetch open issues, and use curl with the GitHub REST API to fetch specific issue details or comments.

Workflow

1. Fetching Issues

You can fetch issues using the provided Python script (works without auth for public repos):

python skills/github-researcher/scripts/fetch_issues.py --repo <owner>/<repo> --workspace ./workspace

Output: {workspace}/data/github-issues.md

If you need to fetch specific issue details or comments, you can query the GitHub REST API directly using curl (since api.github.com is in the network allowlist):

Fetch Specific Issue Details:

curl -s -H "User-Agent: Repo-Maintainer/1.0" https://api.github.com/repos/<owner>/<repo>/issues/<issue_number>

Fetch Comments on a Specific Issue:

curl -s -H "User-Agent: Repo-Maintainer/1.0" https://api.github.com/repos/<owner>/<repo>/issues/<issue_number>/comments

3. Understanding the Repo

To answer questions like "What are my biggest issues?" or understand the project deeply:

  1. Read the README: Check the top-level README.md in the cloned repo.
  2. Scan the directory tree: Use find . -maxdepth 2 to understand the structure.
  3. Summarize issues: Read the fetched issues and identify themes, recurring complaints, or critical bugs.

Output

Produce a summary of the top issues and codebase structure to answer the user's high-level questions.

来自 google-gemini 的更多技能

agent-tui
google-gemini
Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications…
gemini-api-cli
google-gemini
使用Gemini API CLI工具的指南。当你需要通过命令行与Gemini API交互、管理代理或生成媒体(图像、……)时使用。
behavioral-evals
google-gemini
创建、运行、修复和推广行为评估的指南。用于验证代理决策逻辑、调试故障、调试提示…
gemini-live-api-dev
google-gemini
通过WebSocket与Gemini进行实时双向流式传输,支持音频、视频和文本对话。具备音频输入/输出(16 kHz PCM)、视频帧、文本以及带语音活动检测的自动转录功能,可实现中断处理。包含原生音频特性:情感对话、主动音频和思考模式;支持同步和异步工具调用的函数调用;以及Google搜索接地功能。提供会话管理,包括上下文压缩、恢复等。
gemini-omni-flash-api
google-gemini
使用此技能进行生成式视频编辑、文本转视频、图像参考视频生成以及首帧到视频的过渡动画,基于…
gemini-api-dev
google-gemini
使用Google的Gemini模型构建应用程序,支持多模态内容、函数调用和结构化输出,覆盖Python、JavaScript、Go和Java语言。可访问当前Gemini 3模型(Pro、Flash、Pro Image),具备100万token上下文;旧版Gemini 2.x和1.5模型已弃用。支持文本生成、图像/音频/视频理解、函数调用、结构化JSON输出、代码执行、上下文缓存和嵌入功能。提供官方SDK:google-genai(Python)...
gemini-interactions-api
google-gemini
Gemini模型与代理的统一接口,支持服务端状态、流式传输和工具编排。兼容当前多款模型(gemini-3-flash-preview、gemini-3-pro-preview、gemini-2.5-flash/pro)及Deep Research代理;自动将已弃用的模型ID替换为当前替代方案。通过previous_interaction_id将对话历史卸载至服务端,实现有状态的多轮交互,无需手动管理历史记录。内置工具编排功能包括...
deliver
google-gemini
将简报的浓缩版发布到 Google Chat 或 Slack 的传入 webhook,使每日运行自行投递——当没有 webhook 时静默跳过……