Install
$ agentstack add skill-quantumbfs-claude-code-skills-download-papers ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Download Papers
Goal: get the PDF onto the local filesystem with minimum friction. The helper script is the default path once you have a DOI, URL, or direct PDF link.
Default workflow
- If the user gives a DOI, URL, or direct PDF link, run:
``bash python ${CLAUDE_SKILL_DIR}/scripts/download_paper.py "" --out-dir papers ``
- Read the JSON output. On
status: "ok", report thelocal_path. Onstatus: "error", summarize the attempted URLs and try the fallback workflow below. - If the user gives only a title or citation, search for a DOI or PDF URL first, then pass that result to the helper script.
The helper resolves DOI or URL inputs, extracts embedded PDF links from HTML pages, prints JSON with status, pdf_url, and local_path, and verifies that the downloaded file starts with the PDF magic bytes.
Fallback workflow
1. Find an open-web source
Search the web for a freely available copy:
- Google Scholar / general web search for the title; look for
[PDF]links - Author's personal homepage / institutional page (often hosts preprints)
- Lab group "Publications" page
- INSPIRE-HEP, NASA ADS, OSTI, ResearchGate (sometimes), university repositories
When a direct PDF URL or article URL turns up, pass it to the helper script.
2. arXiv
Search arXiv by title/author. Useful when the published version is unavailable but a preprint exists:
https://arxiv.org/abs/→ PDF athttps://arxiv.org/pdf/- For papers before ~Aug 1991 (cond-mat launch), arXiv won't have it — stop here and tell the user no PDF was found.
Common publisher PDF locations
- Nature / Springer: "Download PDF"
- Science / AAAS: "PDF" in article tools
- ACS: "PDF" button near title
- Elsevier / ScienceDirect: "Download PDF"
- Wiley: "PDF" in tools section
- APS (Physical Review): "PDF" in article header
- World Scientific (Mod. Phys. Lett., Int. J. Mod. Phys.): "PDF" link
- arXiv: direct PDF link
Tips
- Always verify the downloaded file is a valid PDF; the helper script checks PDF magic bytes.
- Save to a meaningful filename:
_.pdf.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: QuantumBFS
- Source: QuantumBFS/claude-code-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.