What problem does it solve? Locating the right research papers for a query is hard: a single keyword search misses sibling methods, citing works, and papers whose abstracts don't state the property you care about. This Skill searches Firecrawl's research paper index — a corpus dominated by PubMed, bioRxiv, and medRxiv biomedical literature plus arXiv preprints in CS, physics, and math — and expands strong hits into complete, verified paper sets. ## Core Features & Use Cases - Semantic paper search: Query paper abstracts with HyDE-based semantic search via firecrawl_research_search_papers, the natural first move for almost any query. - Semantic and structural expansion: Turn one good hit into a full set with firecrawl_research_related_papers using similar, citers, or references modes. - Metadata and in-body verification: Confirm citations with firecrawl_research_inspect_paper and verify load-bearing claims (methods used, scores reported, affiliations) with firecrawl_research_read_paper. - Use Case: A researcher asks for alternatives to the Adam optimizer. The Skill runs a semantic search, expands several strong anchors with mode=similar, re-seeds from new hits, and returns the full family of relevant papers rather than a single best match. ## Quick Start Ask the assistant to find papers on your research question using the firecrawl research tools, for example: find papers about training-free detection of AI-generated text and include closely related methods.
