agentleFS
OsmosyOsmosy/vector-gene/skills/science/literature_search_arxiv/SKILL.md

literature-search-arxiv

Skill0 starsChanged 29 days agoApache-2.0View on GitHub

Search for scientific papers, preprints, and publications on arXiv. Extract metadata, abstracts, and download full-text PDFs or HTML versions of papers. Use when the user asks to find research papers, literature, or specific arXiv IDs.

3 other projects use a version of this, 3 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 4 are common, 0 are distinctive, and 4 are very specific to this project.

  • 4

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.

    line 14
  2. Very specific:

    User Notification: If .licenses/literature_search_arxiv_LICENSE.txt does not already exist in the workspace root directory then (1) …

    line 16
  3. Common:

    If this skill is used, ensure this is mentioned in the output AND list the URLs of all papers that were used in producing the output.

    line 29
  4. Common:

    Search arXiv and return a clean JSON array of matching papers.

    line 36
  5. Very specific:

    Search for papers using search_arxiv.py.

    line 117
  6. Very specific:

    If full text is needed, use download_paper.py to fetch the PDF or HTML.

    line 118
  7. Common:

    If downloading a PDF, verify the PDF is not empty or corrupted.

    line 119
  8. Common:

    Read the downloaded file using standard file reading tools.

    line 120

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

arXiv Search and Retrieval

Prerequisites

  1. uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.
  2. User Notification: If .licenses/literature_search_arxiv_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://info.arxiv.org/help/api/index.html and to always check the license of the papers retrieved by the skill for any restrictions, then (2) create the file recording the notification text and timestamp.

Core Rules

  • Terms of Use: You MUST respect arXiv's Terms of Use.
    • Maximum 1 request every 3 seconds.
    • The provided utility scripts handle rate limiting automatically. Always use these scripts rather than writing your own curl/python requests.
  • If this skill is used, ensure this is mentioned in the output AND list the URLs of all papers that were used in producing the output.

Utility Scripts

1. Search and Extract Metadata

Search arXiv and return a clean JSON array of matching papers.

uv run scripts/search_arxiv.py --query "au:einstein AND ti:relativity" \
  --max_results 5 2>/dev/null > /tmp/arxiv_search_results.json

Important: The tool outputs a large JSON result to stdout. Requesting 100+ results will produce a massive JSON that might exceed your context length. Limit --max_results (e.g., 5-10) or paginate carefully using --start. Always redirect output to a file and parse it separately, otherwise terminal output will be truncated.

Returned Metadata: JSON results include id, title, summary, published, authors, pdf_url, primary_category, doi, journal_ref, and comment. Note: the doi field only contains DOI information in case the paper has an external DOI and if only an arXiv-issued DOI exists, this is DOI is not returned.

Options:

  • --query: Search string. See references/query_syntax.md for advanced syntax.
  • --id_list: Comma-separated list of arXiv IDs to fetch directly (e.g., 1706.03762v5).
  • --start: Pagination offset (default 0).
  • --max_results: Number of results to return (default 10).
  • --sort_by: relevance, lastUpdatedDate, or submittedDate. (Use --sort_by submittedDate --sort_order descending for the most recent papers).
  • --sort_order: ascending or descending.

2. Download Paper (PDF or HTML)

Download the full text of a paper to your local workspace for reading.

uv run scripts/download_paper.py --id 1706.03762 --format pdf --output attention.pdf

Options:

  • --id: The arXiv ID (e.g., 1706.03762 or 1706.03762v5).
  • --format: pdf or html. Note: HTML is only available for newer papers.
  • --output: Filepath to save the downloaded document.

Important: when downloading papers, make sure you download them to a location where you do not overwrite other files and do not clutter existing directory structure.

3. Download Paper Source (tar.gz)

Download the LaTeX source files of a paper to your local workspace. Note that not all papers have source available.

uv run scripts/download_paper_source.py --id 2010.11645 --output source.tar.gz

Options:

  • --id: The arXiv ID (e.g., 2010.11645).
  • --output: Filepath to save the downloaded tar.gz file.

Caution: Care should be exercised when untar'ing the downloaded file for security and to avoid cluttering your filesystem, as archives may contain many files or unexpected directory structures.

Safe Extraction Requirements: NEVER extract directly into your working directory! Always extract into a dedicated new directory: bash mkdir paper_source && tar -xzf source.tar.gz -C paper_source

Reference

  • Advanced Query Syntax: See references/query_syntax.md for prefixes (au, ti, abs), booleans, and date filtering.

Workflow

  1. Search for papers using search_arxiv.py. Review the JSON summaries.
  2. If full text is needed, use download_paper.py to fetch the PDF or HTML.
  3. If downloading a PDF, verify the PDF is not empty or corrupted.
  4. Read the downloaded file using standard file reading tools.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.