Stats
Actions
Tags
From download-papers
Downloads academic paper PDFs given URL, DOI, title, or citation. Searches open-web sources, Sci-Hub mirrors, then arXiv using curl and grep.
How this skill is triggered — by the user, by Claude, or both
Slash command
/download-papers:download-papersThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Goal: get the PDF onto the local filesystem with minimum friction. Try in this order — stop at the first hit.
Goal: get the PDF onto the local filesystem with minimum friction. Try in this order — stop at the first hit.
Search the web for a freely available copy:
[PDF] linksIf a direct PDF URL turns up, fetch it:
curl -L -o paper.pdf "<URL>"
For paywalled DOIs, try Sci-Hub mirrors in order — they rotate availability:
https://sci-hub.se/<DOI>https://sci-hub.st/<DOI>https://sci-hub.ru/<DOI>https://sci-hub.ee/<DOI>The DOI suffix is appended literally (parentheses and slashes included). Example:
https://sci-hub.se/10.1016/0550-3213(92)90424-A
Sci-Hub returns an HTML wrapper with an embedded PDF; the actual file lives at a URL inside an <iframe src="..."> or <embed src="...">. Fetch the page, extract that URL, then download:
curl -sL "https://sci-hub.se/<DOI>" | grep -oE 'src="[^"]*\.pdf[^"]*"' | head -1
Search arXiv by title/author. Useful when the published version is paywalled but a preprint exists:
https://arxiv.org/abs/<id> → PDF at https://arxiv.org/pdf/<id>file paper.pdf should report PDF document); Sci-Hub mirrors sometimes serve CAPTCHA HTML when rate-limited..se/.st/.ru mirror.<firstauthor><year>_<shorttitle>.pdf.npx claudepluginhub quantumbfs/claude-code-skills --plugin download-papersRetrieves scientific paper PDFs from arXiv URLs, DOIs, titles, or other identifiers, saving to papers/ directory. Uses direct arXiv downloads or sci-hub with Chrome for paywalled papers.
Searches Semantic Scholar (200M+ papers), inspects citations, downloads arXiv PDFs, and extracts text via a bundled Python CLI. Use for literature scans, deep reads, impact analysis, or reading lists.
Takes a bibliographic reference citation, searches for a direct full-text URL, downloads and verifies the file matches the reference, then reports outcome (found, paywalled, or not found).