# deep-research

Runs a systematic academic literature review on a topic: finds papers, reads them, builds a database and writes a final report. Useful when you need the state of a field, not a few search hits.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1900 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/deep-research/SKILL.md
- Updated: 2026-02-27
- HTML: https://affpapa.org/en/nevibecode/skills/lingzhi227-deep-research

## What it does

The skill works through six phases in strict order: latest conference material, a broad survey of the topic, deep reading of selected papers, a hunt for code and tools, synthesis with research gaps, and the final report. Skipping ahead is not allowed. Before each next phase the agent checks that the previous phase's files exist on disk and prints a completion checkpoint.

A set of scripts does the heavy lifting. `paper_finder.py` searches published conference papers with venue and year filters, `search_semantic_scholar.py` and `search_arxiv.py` add citation data and recent preprints, `paper_db.py` merges results into one database, `extract_pdf.py` pulls text out of PDFs, and `compile_report.py` assembles the report. Semantic Scholar needs an API key. Without Bash the skill falls back to `WebSearch` and `WebFetch`.

Peer-reviewed conference papers come first; preprints are supplementary and get marked as such in citations. So on a very fresh topic your pool will be thinner. Output lands in a topic folder split by phase, which means you can edit the intermediate notes by hand between runs.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

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

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill deep-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/deep-research/SKILL.md

## When to use it
- map the state of a field from recent conference papers
- build a paper database with BibTeX and citation counts
- read the shortlisted papers and write notes on each
- find open-source implementations and tools for the topic
- spell out research gaps and write the final report

## Example prompts
- do a literature review on long horizon reasoning agents
- /research retrieval augmented generation
- deep dive into memory for LLM agents

## Similar
- [literature-review](https://affpapa.org/en/nevibecode/skills/collaborative-deep-research-literature-review.md) — skill · 732 installs
- [research-lit](https://affpapa.org/en/nevibecode/skills/research-lit.md) — skill · 614 installs
- [academic-deep-research](https://affpapa.org/en/nevibecode/skills/academic-deep-research.md) — skill · 560 installs
- [tooluniverse-literature-deep-research](https://affpapa.org/en/nevibecode/skills/tooluniverse-literature-deep-research.md) — skill · 664 installs
- [research-ideation](https://affpapa.org/en/nevibecode/skills/galaxy-dawn-research-ideation.md) — skill · 566 installs
- [systematic-literature-review](https://affpapa.org/en/nevibecode/skills/systematic-literature-review.md) — skill · 2500 installs

## Other versions with the same name
- [deep-research · affaan-m](https://affpapa.org/en/nevibecode/skills/affaan-m-deep-research.md) — 5100 installs
- [deep-research · bytedance](https://affpapa.org/en/nevibecode/skills/bytedance-deep-research.md) — 2800 installs
- [deep-research · 199-biotechnologies](https://affpapa.org/en/nevibecode/skills/199-biotechnologies-deep-research.md) — 10200 installs
- [deep-research · ruvnet](https://affpapa.org/en/nevibecode/skills/ruvnet-deep-research.md) — 893 installs
- [deep-research · hkustdial](https://affpapa.org/en/nevibecode/skills/hkustdial-deep-research.md) — 496 installs

From the same set: [lingzhi227/agent-research-skills](https://affpapa.org/en/nevibecode/by/lingzhi227/agent-research-skills.md) — 30 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