agentleFS
Sign inStart free
orange4664orange4664/research-skills/paper-downloader/SKILL.md

paper-downloader

Skill41 starsChanged 8 months agoMITView on GitHub

Download paper PDFs and clone source code repositories from paper_info.json output.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    After running paper-finder to get paper_info.json

    line 12
  2. Distinctive:

    Run paper-finder first if needed:

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Paper Downloader Skill

Purpose

Download paper PDFs and clone associated source code repositories. This is the second step in the paper reproduction pipeline, following paper-finder.

When to Use

  • After running paper-finder to get paper_info.json
  • User asks to "download", "get", or "fetch" a paper's PDF
  • User asks to "clone" or "get the code" for a paper
  • User asks to "reproduce" a paper (run paper-finder first, then this)

How to Use

Step 1: Ensure paper_info.json exists

Run paper-finder first if needed:

python skills/paper-finder/scripts/search_paper.py "<query>" --output workspace/paper_info.json

Step 2: Run the Download Script

python skills/paper-downloader/download_paper.py workspace/paper_info.json

Options:

  • --allow-scihub — Enable Sci-Hub as fallback PDF source
  • --clone-depth 0 — Full git clone (default: shallow clone)
  • --skip-code — Only download PDF
  • --skip-pdf — Only clone code
  • -o <dir> — Custom output directory

Step 3: Read the Results

Check workspace/<paper-slug>/download_report.json for:

  • PDF download status and path
  • Code clone status and path
  • Step-by-step log

Step 4: Report to User

Tell the user:

  • Where the PDF was saved
  • Where the code was cloned
  • Which dependency files were found in the repo

Dependencies

  • Python 3.10+
  • requests library
  • git command-line tool

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.

Check your setup, free