skills.rest
GliteTech
GliteTechOFFICIAL
Explore all skills by this author →
GitHub

download_paper

Resolve partial paper identifiers to a canonical record and download the best available version.

16|8|Updated Apr 15, 2026
Search Tags:#metadata-extraction#pdf-download#open-access#paper-identification#doi-resolution#scholarly-resolver
One-click install
npx skills add https://github.com/GliteTech/glite-arf --skill download-paper-glitetech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: download_paper
Source: https://github.com/GliteTech/glite-arf/tree/main/meta/asset_types/paper/skills/download_paper
Command: npx skills add https://github.com/GliteTech/glite-arf --skill download-paper-glitetech

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Resolves the challenge of locating a specific scholarly work when only partial identifiers are available, and ensures you obtain the correct version and complete metadata for downstream processing.

Core Features & Use Cases

  • Canonical identification: aggregates CrossRef, OpenAlex, Semantic Scholar, and other sources to build a canonical paper record.
  • Open access discovery: locates the best available OA version across multiple providers to maximize accessibility.
  • Version-aware retrieval: prioritizes published versions, accepted manuscripts, or preprints according to availability.
  • Use Case: When given a title and year but no DOI, automatically locate and download the best-text format for integration into asset pipelines.

Quick Start

To download a paper, provide partial identifiers (title, DOI, arXiv, or PMID) and an output_dir.

Frequently Asked Questions about download_paper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I download an open access PDF using only a paper title?▼

To download an open access PDF using only a paper title, provide the title as a partial identifier to resolve the canonical record and fetch the best available PDF version across multiple scholarly sources.

What is the best way to resolve a DOI to a downloaded PDF and metadata?▼

The best way to resolve a DOI to a downloaded PDF is to submit the DOI as input, which aggregates records from CrossRef, OpenAlex, and Semantic Scholar to validate metadata and retrieve the file to your output directory.

Can I find open access preprints if the published PDF is paywalled?▼

Yes, you can find open access preprints if the published version is paywalled by utilizing version-aware retrieval, which prioritizes accepted manuscripts or preprints according to availability across multiple providers.

Does this scholarly resolver work with arXiv and PubMed IDs?▼

Yes, this scholarly resolver works with arXiv and PubMed IDs by gathering all known identifiers from partial inputs and resolving them across arXiv, CrossRef, OpenAlex, and Semantic Scholar to return a validated record.

What happens if a paper cannot be found across any metadata sources?▼

If a paper cannot be found across any metadata sources, the system exhausts all available lookup options across CrossRef, OpenAlex, Semantic Scholar, and publishers, then reports a not_found status instead of returning a file.

Related Skills

Explore More Education & Research Skills→
ovachieverovachiever
52

citation-management

Convert DOIs, PMIDs, and arXiv IDs to validated BibTeX citations.

Community
Advanced
greghavensgreghavens
8

pdf

Extract text and metadata from PDF files using pdf-parse.

Community
Intermediate
TeoSlayerTeoSlayer
7

pilot-service-agents-academic

Fetch scholarly metadata from bibliographic databases via OpenAlex, Crossref, and PubMed.

Community
Intermediate
kthornkthorn
118

Finding Open Access Papers

Query the Unpaywall REST API by DOI to return the best open-access PDF URL.

Community
Basic