Skip to content
Get packs

Nature Literature Downloader

Fetches legal full-text papers via open access, publisher APIs, and your library's Chrome session

Source Download skill
Repository
Yuan1z0825/nature-skills
Stars
51,827
Licence
Apache-2.0
Files
15 files

What it does

Once installed, the agent can look up academic papers by DOI, title, or topic and try to download their full text (PDF) through lawful routes: open-access copies first, then publisher APIs with your own key, CNKI for Chinese papers, and your institution's library login in your existing Chrome browser. It asks before downloading supplementary files, and it stops at login pages, CAPTCHAs, and paywalls instead of bypassing them.

Great for

  • Researchers or students whose university library already provides access to journals and wants automated PDF retrieval
  • Users with their own Elsevier, Springer Nature, or IEEE API keys who want batch downloads
  • Teams building literature collections that need a record of where each file came from

Skip it if

  • Anyone hoping to get paywalled papers without institutional access; it does not bypass paywalls, logins, or CAPTCHAs, so results will be missing for those papers
  • Users who cannot safely run scripts on their machine, since the skill executes Node.js and Python code and drives a logged-in browser session
  • Sensitive environments where a browser carrying institutional credentials should not be controlled by automation

Try asking

  • “Download the full-text PDF of this paper by DOI: 10.1038/s41586-020-2649-2, no supplementary files”
  • “Find and download open-access PDFs for these 10 papers on perovskite solar cells, skip SI”
  • “Download the CNKI full text of this Chinese paper titled 中文题名 using my library login”
  • “Retry the failed Elsevier API downloads from my last batch via open-access sources”
Step-by-step guide: how to use Nature Literature DownloaderInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the Apache-2.0 licence and an attribution note.

    nature-downloader.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip nature-downloader.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip nature-downloader.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Provide your library's resource portal URL so the skill can infer the correct login route rather than guessing from a school name.
  • Always answer the SI question explicitly (--si or --no-si); the script refuses to run without one, which keeps batches predictable.
  • Review the manifest after a batch; it records each paper's access mode and failures, so you can see which papers still need manual retrieval.

What's inside

  • agents/openai.yaml
  • data/publishers.json
  • data/school.schema.json
  • data/schools.yaml
  • docs/nature-downloader-reference-research-2026-07-15.md
  • docs/superpowers/plans/2026-06-21-nature-downloader-merge.md
  • manifest.yaml
  • README_EN.md
  • README.md
  • references/delivery-verification-and-failures.md
  • references/institutional-browser-workflow.md
  • requirements.txt
  • scripts/batch_download.mjs
  • scripts/browser_pdf_downloader.mjs
  • SKILL.md

Redistributed unmodified from Yuan1z0825/nature-skills under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.