scientific-literature-search
Systematic strategies for searching scientific literature across PubMed, arXiv, Google Scholar, and AI-assisted tools. Covers PICO framework for clinical questions, three-tiered search (database-specific, AI-assisted, content extraction), PubMed field tags and MeSH, boolean query construction, and full-text extraction. Use when planning a literature search or choosing a search tier.
npx skills add BioTender-max/awesome-bio-agent-skills --skill scientific-literature-search --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Directs the agent to use a three-tiered search strategy (Tier 1: database-specific searches; Tier 2: AI-assisted web search; Tier 3: direct content extraction) across PubMed, arXiv, and Google Scholar, with PubMed field tags and MeSH, and to apply the PICO framework for clinical queries. It includes steps for constructing and refining queries, leveraging tools for AI-assisted and web searches, and performing content extraction for deep dives.
How it works
- Step 1: Define a clinical or research question using the PICO framework.
- Step 2: Construct Tier 1 queries for each database (PubMed via MeSH/field tags, arXiv via category/keyword, Google Scholar via general search access) and run them with a broad core term set, then refine with MeSH terms and filters.
- Step 3: Supplement with Tier 2 AI-assisted web search and a general web search for protocols and documentation, using the cited tools (e.g., web_search_20250305) to surface landscape and trends.
- Step 4: Evaluate results, screen titles/abstracts, and prioritize by recency, quality, and study design; decide when to proceed to Tier 3.
- Step 5: Use Tier 3 to extract full text and supplementary materials from high-priority papers, then inspect references for additional sources.
When to use it
Use when planning a literature search or choosing a search tier.
What it can touch
- Tools and code references for performing searches include: Bio.Entrez (PubMed), arxiv package, scholarly, and web_search_20250305 via Claude-like API; trafilatura for HTML extraction; pypdf for PDFs; Crossref API for DOIs.
- Example scripts show interactions with Entrez, arxiv, scholarly, and a web search client, as well as content extraction steps.
Caveats
- The license listed is CC-BY-4.0; no explicit risk notes beyond typical usage of the included tools.
- Absent explicit guarantees about results quality or reproducibility beyond the described workflow.
# Scientific Literature Search ## Overview Scientific literature search is the foundation of evidence-based research. A well-executed search maximizes recall (finding all relevant papers) while maintaining precision (avoiding irrelevant results). This guide provides a systematic approach that combines database-specific query strategies, AI-assisted synthesis, and direct content extraction, organized into a three-tiered framework that scales from targeted lookups to comprehensive landscape reviews. ## Key Concepts ### The PICO Framework For clinical and biomedical questions, structure queries using the PICO framework: - **P** (Population): Who are you studying? (e.g., "Diabetes Mellitus"[MeSH]) - **I** (Intervention): What treatment or exposure? (e.g., "Metformin"[MeSH]) - **C** (Comparison): What is the alternative? (e.g., placebo, standard care) - **O** (Outcome): What result are you measuring? (e.g., "Cardiovascular Diseases"[MeSH]) PICO queries can be combined with publication type filters to target specific evidence levels: ``` "Diabetes Mellitus"[MeSH] AND "Metformin"[MeSH] AND "Cardiovascular Diseases"[MeSH] AND ("clinical trial"[Publication Type] OR "meta-analysis"[Publicati
- Overview
- Key Concepts
- The PICO Framework
- Three-Tiered Search Strategy
- PubMed Field Tags
- Boolean Operators
- arXiv Subject Categories
- Decision Framework
- Best Practices
- Common Pitfalls
- Workflow
- Common Search Scenarios
- Finding Methods and Protocols
- Understanding Disease Mechanisms
What does the scientific-literature-search skill do?
Systematic strategies for searching scientific literature across PubMed, arXiv, Google Scholar, and AI-assisted tools. Covers PICO framework for clinical questions, three-tiered search (database-specific, AI-assisted, content extraction), PubMed field tags and MeSH, boolean query construction, and full-text extraction. Use when planning a literature search or choosing a search tier.
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill scientific-literature-search --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.