Literature Search & Review

SkillDatabases & data

Your AI Research Lab That Never Sleeps. 9 agents, 263 skills, 77 databases — from literature to publication, every discipline, zero boundaries.

Available today. Use it from your connected AI after setup.

No other account needed.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Literature Search & Review skill

What this skill tells your AI

The instructions your AI receives, as published by zaoqu-liu/scienceclaw in skills/literature/SKILL.md and read by ahel’s review.

Comprehensive academic literature search and synthesis across 15+ sources.

Multi-database parallel search (PubMed, arXiv, bioRxiv, medRxiv, OpenAlex, Semantic Scholar, Crossref, DBLP, CORE, DOAJ, Europe PMC)
Web search via Agent-Reach (Exa semantic search, Jina Reader for any URL/PDF)
Social academic search (Twitter/X threads, YouTube talks, GitHub repos)
Structured literature reviews with citation networks
Knowledge gap identification
Hypothesis generation from literature analysis

Query optimization: Short, keyword-based queries (max 7 words). PubMed-friendly syntax.
Multi-source fan-out: Parallel queries across all sources for maximum coverage.
Deduplication: By PMID, DOI, then normalized title.
Reflection loop: Evaluate coverage → identify gaps → generate follow-up queries.

ZERO hallucinated citations. Every reference must come from real search data.
Unified article schema: source_type, title, authors, year, journal, url, doi, pmid, abstract.
Numbered references [1], [2], [3] — built only from retrieved articles.

Start broad, then narrow. First search finds the landscape; follow-up queries fill gaps.
Cross-domain search. The breakthrough paper might be in an unexpected field.
Check preprints AND published papers. Recent findings may only be on bioRxiv/arXiv.
Verify high-impact claims. Use Semantic Scholar's citation count to identify landmark papers.

Advanced