Back to resources

SKILL

paper-lookup

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/paper-lookup
Use with an agent

SUMMARY

What it does

This Agent Skill provides a workflow for searching academic literature across 11 APIs (PubMed, PMC, Europe PMC, bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall). It instructs an agent to select authoritative databases, make bounded and rate-limited API calls via curl, handle known silent failure modes (e.g., HTTP 200 with error bodies), and return auditable results with provenance. The skill includes bundled Python scripts for pagination, JATS XML parsing, arXiv Atom parsing, and OpenAlex abstract reconstruction. It requires network access, curl, and Python 3.11+; no credentials are required, but optional API keys can raise rate limits. The skill is designed for reproducible literature retrieval and emphasizes reporting gaps and failures honestly.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

literature.searchweight 100 · confidence 90literature.retrieveweight 90 · confidence 90literature.citationweight 80 · confidence 80literature.fulltextweight 80 · confidence 80literature.openaccessweight 70 · confidence 70

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.