nature-downloader
A skill from the nature-skills collection that fetches full-text papers and supporting files through what it calls lawful routes.
What the skill teaches
A skill from the nature-skills collection that fetches full-text papers and supporting files through what it calls lawful routes. Chinese papers come only from CNKI through the user's library or CNKI login; English papers come from publisher APIs for Elsevier, Springer Nature or IEEE when the user has a key, then open-access sources such as PMC, Unpaywall and arXiv, then the user's institutional access through CARSI, EZproxy, WebVPN or CAS. For the browser routes it attaches to the user's own logged-in Chrome over the DevTools protocol and reuses that session, without exporting cookies or asking for passwords, and makes at most two attempts at visible checks such as sliders before handing over to the user. It needs Node.js 22 and Python 3.
Capabilities
- Download open-access papers by DOI or title
- Use publisher APIs with the user's own key
- Fetch papers through the user's library login
- Check each file is a real PDF and record its source
About
- Publisher
- yuan1z0825
- Tool
- Research
Install
The project doesn't document install steps that we could confirm. See the project's own instructions
What's inside
- .gitattributes
- .gitignore
- LICENSE
- README.md
- README_EN.md
- agents/openai.yaml
- assets/banner.jpg
- 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
- examples/carsi-retry-template.tsv
- examples/manifest-template.tsv
- examples/publisher-verification-template.tsv
- manifest.yaml
- references/delivery-verification-and-failures.md
- references/institutional-browser-workflow.md
- requirements.txt
- scripts/batch_download.mjs
- scripts/browser_pdf_downloader.mjs
- scripts/cdp_open_url.mjs
- scripts/configure_credentials.py
- scripts/configure_school.py
- scripts/extract_pdf_text.py
MCP servers and skills can run code on your computer and act on your data. Review the source before installing.
This skill includes scripts that your agent may run.
Details
| Fact | Value | Source |
|---|---|---|
| Type | Skill | |
| Tool | Research | |
| Publisher | yuan1z0825 | source |
| Official status | Not stated in its documentation | |
| Status | Beta | source |
| Needs an API key or sign-in | Not stated in its documentation | |
| Includes scripts | Yes | source |
| Platforms | Not stated in its documentation | |
| AI clients | Not stated in its documentation | |
| Licence | Apache-2.0 | source |
| Pricing | Not stated in its documentation | |
| Activity | Last commit Nov 19, 202654,246 GitHub starsDownload data not available (not on npm or PyPI) | source |
| Links | Repository |
More from yuan1z0825
20 skills
- nature-paper2word (Skill)
- nature-experiment-log (Skill)
- nature-figure (Skill)
- nature-literature-pipeline (Skill)
- nature-polishing (Skill)
- nature-ref-verifier (Skill)
Also listed under: Research
Sources
- Skill file (SKILL.md)github.com/yuan1z0825/nature-skills · Backs: Includes scriptsNov 15, 2026
- GitHub repositorygithub.com/yuan1z0825/nature-skills · Backs: Licence, Publisher, Status, ActivityNov 11, 2026
- Skill file (SKILL.md)github.com/Yuan1z0825/nature-skillsNov 10, 2026
- Folder in the repository (nature-downloader)github.com/Yuan1z0825/nature-skills · Backs: Includes scriptsNov 10, 2026