# github-research

Finds open-source repositories matching research topics, inspects their codebases, and produces an integration blueprint. Useful when tracking down implementations of algorithms.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1800 installs · ★ 433
- Author: lingzhi227
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/lingzhi227/agent-research-skills/tree/HEAD/skills/github-research/SKILL.md
- Updated: 2026-02-27
- HTML: https://affpapa.org/en/nevibecode/skills/github-research

## What it does

The skill takes an output directory from deep-research (such as `paper_db.jsonl` or `code_repos.md`) and processes it through a six-phase pipeline. It begins by extracting URLs, topics, and keywords. Then it runs multi-source queries through `gh api` and Papers With Code to gather between 50 and 200 relevant repositories.

All automation relies on Python 3 standard-library scripts located in `~/.claude/skills/github-research/scripts/`. These scripts rank the candidates, run shallow clones on the top 8 to 15 repositories, parse dependencies, and search for specific patterns in the code. The run ends with a comparison matrix and a catalog of reusable components inside `./github-research-output/{slug}/`.

You need an authenticated GitHub CLI (`gh`) tool ready in your path. Otherwise, discovery scripts fail immediately when calling the API. Running this without an existing deep-research folder will not work either, because phase 1 requires initial research notes to generate search queries.

## Requirements
- Works with: GitHub

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill github-research -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/github-research/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/github-research/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill github-research -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/github-research/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill github-research -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/github-research/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lingzhi227/agent-research-skills github-research
```

2. **Manually: put the files in place**
- File: `.github/skills/github-research/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill github-research -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lingzhi227/agent-research-skills --path skills/github-research
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/github-research/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill github-research -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/lingzhi227/agent-research-skills/tree/HEAD/skills/github-research/SKILL.md

## When to use it
- find open-source implementations of a research paper using its title or arXiv identifier
- rank candidate GitHub repositories by stars, code structure, and dependency footprint
- build a cross-repo comparison matrix for algorithms in a specific domain
- assemble an integration blueprint with a catalog of reusable code modules

## Example prompts
- /github-research ./deep-research-output/llm-agents
- Find GitHub implementations for paper 2401.12345 and compare their code structure
- Which open-source repos implement this consensus algorithm?

## Similar
- [github-deep-research](https://affpapa.org/en/nevibecode/skills/github-deep-research.md) — skill · 2900 installs
- [read-github](https://affpapa.org/en/nevibecode/skills/read-github.md) — skill · 1200 installs
- [github-webhooks](https://affpapa.org/en/nevibecode/skills/github-webhooks.md) — skill · 487 installs
- [python-github-setup-cursorrules-prompt-file](https://affpapa.org/en/nevibecode/rules/python-github-setup-cursorrules-prompt-file.md) — rule · ★ 41011
- [deep-research](https://affpapa.org/en/nevibecode/skills/sanjay3290-deep-research.md) — skill · 672 installs
- [github-issues](https://affpapa.org/en/nevibecode/skills/github-issues.md) — skill · 17431 installs

From the same set: [lingzhi227/agent-research-skills](https://affpapa.org/en/nevibecode/by/lingzhi227/agent-research-skills.md) — 23 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md