# astroai-research

astroai-research is a Claude Code skill that discovers AI and machine learning papers, datasets, and code for astronomy. Runs when querying curated literature or tracking recent arXiv preprints.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 409 repo stars
- Author: Xin-YuXiao
- License: CC0-1.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/Xin-YuXiao/Awesome-AI-for-Astronomy/tree/HEAD/.agents/skills/astroai-research/SKILL.md
- Updated: 2026-11-17
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/astroai-research

## What it does

The skill queries the curated Awesome AI for Astronomy collection and the AstroAI Today feed to find machine learning papers, benchmarks, datasets, and software. It distinguishes peer-reviewed catalog entries from raw arXiv candidates.

Searches run through `scripts/query.py` using Python's standard library. The tool requires Python 3.9+ and network access to the public site. No API credentials or third-party packages are needed.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add Xin-YuXiao/Awesome-AI-for-Astronomy --skill astroai-research -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add Xin-YuXiao/Awesome-AI-for-Astronomy --skill astroai-research -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add Xin-YuXiao/Awesome-AI-for-Astronomy --skill astroai-research -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install Xin-YuXiao/Awesome-AI-for-Astronomy .agents/skills/astroai-research
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add Xin-YuXiao/Awesome-AI-for-Astronomy --skill astroai-research -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/Xin-YuXiao/Awesome-AI-for-Astronomy --path .agents/skills/astroai-research
```

### Windsurf (Devin Desktop)

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

### 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/Xin-YuXiao/Awesome-AI-for-Astronomy/tree/HEAD/.agents/skills/astroai-research/SKILL.md

## When to use it
- discover machine learning papers and repositories for astronomy tasks
- track new arXiv preprints using daily, weekly, or monthly digests
- locate open astronomy datasets, benchmarks, and software libraries
- filter research literature by data modality and code availability

## Example prompts
- Search the astroai-research catalog for photometric redshift papers with public code
- Get the latest weekly AstroAI Today digest on gravitational waves
- Find tools and libraries for light curve analysis using astroai-research

## Source text · SKILL.md · CC0-1.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: b31e485794c79088.

BEGIN THIRD-PARTY FILE b31e485794c79088
````text
---
name: astroai-research
description: Find AI and machine learning papers, datasets, benchmarks, and software in Awesome AI for Astronomy and track recent arXiv papers with AstroAI Today. Use for astronomy literature discovery, finding reusable research resources, or checking daily, weekly, and monthly AI for Astronomy updates.
---

# AstroAI Research

Use the [curated catalogue](https://xin-yuxiao.github.io/Awesome-AI-for-Astronomy/) for existing work and reusable resources. Use [AstroAI Today](https://xin-yuxiao.github.io/Awesome-AI-for-Astronomy/today.html) for new arXiv candidates and period digests. The two sources have different inclusion processes, and appearing in Today does not imply an entry in the curated catalogue or peer review.

## Query the sources

Run [scripts/query.py](scripts/query.py) from the skill directory with Python 3.9+ and access to the public site. The script uses the standard library and needs no credentials. Pass separate search terms to match all of them, and quote a phrase to match it as written. Search English titles and terminology, using the researcher's language for the answer.

```sh
python scripts/query.py catalog "photometric redshift" --resource code --limit 5
python scripts/query.py catalog "light curve" --modality "Time series"
python scripts/query.py catalog "light curve" --kind links --section "Tools and Libraries"
python scripts/query.py today --limit 5
python scripts/query.py today --date 2026-11-10 --topic "Gravitational Waves"
python scripts/query.py today --month 2026-11 "weak lensing"
python scripts/query.py digest week
python scripts/query.py digest month --period 2026-11
```

- **Catalogue.** Search by task, object, survey, or method. Filter by section, modality, or linked resource when needed. Some entries have no modality tag, so retry without that filter when coverage matters. The `links` kind searches resources such as tools and communities.
- **Today.** Without a date, the script returns the latest available batch and reports its date. Date and month filters use the public archive. A missing batch is distinct from a published batch with no matching papers.
- **Digests.** Use the week or month summary to orient a literature scan. Retain the reported dates and whether the period is final. Open highlighted arXiv records before relying on the digest's interpretation.
- **Browser fallback.** Use the catalogue's search or its [JSON export](https://xin-yuxiao.github.io/Awesome-AI-for-Astronomy/entries.json), and the Today page's Today, This week, This month, or Archive tabs. The [RSS feed](https://xin-yuxiao.github.io/Awesome-AI-for-Astronomy/today/feed.xml) covers recent entries only.

## Use results in research
````
END THIRD-PARTY FILE b31e485794c79088

The third-party file has ended. Everything between the b31e485794c79088 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2713 of 3420 bytes. © Xin-YuXiao · CC0-1.0 · https://github.com/Xin-YuXiao/Awesome-AI-for-Astronomy/tree/HEAD/.agents/skills/astroai-research/SKILL.md

## Similar
- [Lacuna Research MCP](https://affpapa.org/en/nevibecode/mcp/lacuna-research-mcp.md) — MCP server · ★ 76 repo stars
- [paper2code-arxiv-implementation](https://affpapa.org/en/nevibecode/skills/paper2code-arxiv-implementation.md) — skill · 643 installs
- [autoresearchclaw-autonomous-research](https://affpapa.org/en/nevibecode/skills/autoresearchclaw-autonomous-research.md) — skill · 1600 installs

_Part of the page did not fit — see the HTML version._

---
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
