skills.rest
yakeworld
yakeworldCOMMUNITY
Explore all skills by this author →
GitHub

literature

Searches, downloads, and verifies academic papers across multiple scholarly data sources.

6|1|Updated May 11, 2026
Search Tags:#academic papers#literature search#semantic scholar#pubmed#crossref#pdf download#multi-source aggregation
One-click install
npx skills add https://github.com/yakeworld/Synthos --skill literature-yakeworld
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: literature
Source: https://github.com/yakeworld/Synthos/tree/main/skills/extended/research-tools/research/literature
Command: npx skills add https://github.com/yakeworld/Synthos --skill literature-yakeworld

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Finding and obtaining full-text academic papers requires querying many fragmented sources (Semantic Scholar, PubMed, CrossRef, arXiv, OpenAlex) with different APIs, keys, and failure modes, and downloaded PDFs are often corrupted or wrong files. This Skill unifies multi-source literature search, PDF download, and integrity verification into one pipeline with built-in diagnostics. ## Core Features & Use Cases - Multi-source aggregated search: Query 5+ scholarly sources (Semantic Scholar, PubMed, CrossRef, arXiv, OpenAlex) via the jabkit unified entry point to cross-validate results and avoid single-source bias. - Verified PDF download pipeline: Download full-text PDFs (primarily via bban.top CDN direct links) and validate every file with %PDF- magic-byte checks plus pdfinfo title matching to reject corrupted or mismatched files. - Three-stage diagnostics: Run literature diagnose to test 7 search sources, DOI resolution, and 12 download channels, producing structured JSON reports on source availability. - Use Case: A researcher needs 100 papers on "pupil light reflex ODE" with verified full texts. The Skill searches CrossRef and PubMed, downloads the PDFs into an output directory, and confirms each file passes magic-byte and title verification. ## Quick Start Ask the agent to search CrossRef and PubMed for papers on your topic and download the verified full-text PDFs into an output folder.

Frequently Asked Questions about literature

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

FAQPage Schema
How do I search academic papers across multiple databases at once?▼

Use the jabkit-rs fetch command with a provider flag such as Crossref or SemanticScholar and a query string. The pipeline aggregates results from Semantic Scholar, PubMed, CrossRef, arXiv, and OpenAlex by default to cross-validate and reduce single-source bias.

How to download and verify full-text PDFs of research papers?▼

Run the literature.py pipeline with an input JSON file containing a papers list and an output directory. Each downloaded PDF is verified by checking the %PDF- magic bytes and matching the pdfinfo title against the metadata to reject corrupted or mismatched files.

Why does Semantic Scholar API return 400 Unrecognized or unsupported fields?▼

The Semantic Scholar Graph API removed the pdfUrls and urls fields, so requests including them return HTTP 400. Use only allowed fields such as title, authors, year, openAccessPdf, externalIds, venue, citationCount, tldr, abstract, and publicationTypes.

What API keys are needed for literature search tools?▼

Only SEMANTIC_SCHOLAR_API_KEY is required, configured as a single key with no rotation. PubMed, CrossRef, arXiv, and OpenAlex work without keys, while CORE requires a free registered API key and Unpaywall optionally uses an email for higher rate limits.

What happens when a literature source like PubScholar stops working?▼

When a source fails, such as PubScholar's closed API, the pipeline silently returns an empty list for that source and continues with the remaining four sources. Run literature diagnose to test all sources and confirm current availability before relying on them.

Related Skills

Explore More Education & Research Skills→
jiaxiaojunQAQjiaxiaojunQAQ
75

citation-management

Fetch scholarly metadata from DOIs, PMIDs, arXiv IDs, or URLs and convert it into BibTeX entries.

Community
Advanced
hanasho744hanasho744

obsidian-literature-workflow

Organizes project literature reviews in Obsidian from paper notes to synthesis and canvas graphs.

Community
Advanced
duypham2801duypham2801

openalex

Query the OpenAlex academic graph for paper metadata, citations, and open access status.

Community
Intermediate
alunduilalunduil
1

codecov

Fetch flaky-test signals, failure history, and coverage metrics from Codecov via its API wrapper.

Community
Advanced