astroai-research — Claude Code skill: what it does, how to install
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.
CC0-1.0 ★ 409 updated 2026-11-17
npx skills add Xin-YuXiao/Awesome-AI-for-Astronomy --skill astroai-research -a claude-codeWhat astroai-research 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.
What it helps with
- 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 for the agent
- 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
How to install astroai-research
1Skills CLI (Vercel)
npx skills add Xin-YuXiao/Awesome-AI-for-Astronomy --skill astroai-research -a claude-code2Manually: put the files in place
~/.claude/skills/astroai-research/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/astroai-research/
1Skills CLI (Vercel)
npx skills add Xin-YuXiao/Awesome-AI-for-Astronomy --skill astroai-research -a codex2Manually: put the files in place
.agents/skills/astroai-research/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Xin-YuXiao/Awesome-AI-for-Astronomy --skill astroai-research -a cursor2Manually: put the files in place
.cursor/skills/astroai-research/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Xin-YuXiao/Awesome-AI-for-Astronomy .agents/skills/astroai-research2Manually: put the files in place
.github/skills/astroai-research/SKILL.md1Skills CLI (Vercel)
npx skills add Xin-YuXiao/Awesome-AI-for-Astronomy --skill astroai-research -a gemini-cli2Platform CLI
gemini skills install https://github.com/Xin-YuXiao/Awesome-AI-for-Astronomy --path .agents/skills/astroai-researchManually: put the files in place
.devin/skills/astroai-research/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about astroai-research
How to install astroai-research in Claude Code?
Run npx skills add Xin-YuXiao/Awesome-AI-for-Astronomy --skill astroai-research -a claude-code. The file will be placed at ~/.claude/skills/astroai-research/SKILL.md.
What does astroai-research do?
It queries the Awesome AI for Astronomy catalog and fetches recent arXiv papers, datasets, benchmarks, and code.
What is required to run astroai-research?
It requires Python 3.9+ and internet access to the public website. No API keys are required.
Source text
SKILL.md · CC0-1.0
--- 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 For a shortlist, include the paper title, primary link, research task, and relevant public code, data, or model links. Identify whether each candidate came from the curated catalogue or Today, and deduplicate by arXiv ID or DOI when combining them. Treat source summaries as discovery aids. Verify methods, data, metrics, numerical results, and publication status against the primary paper or publisher before making claims. Say when the answer is based on an abstract or catalogue entry. If asked to propose a catalogue change, follow the repository's [contribution guide](https://github.com/Xin-YuXiao/Awesome-AI-for-Astronomy/blob/main/CONTRIBUTING.md). Check for duplicates before proposing an entry.
© Xin-YuXiao · CC0-1.0 · Xin-YuXiao/Awesome-AI-for-Astronomy