
Literature Search
This is a unified search across PubMed, arXiv, bioRxiv, and medRxiv that takes natural language queries and returns full article text, not just abstracts. It uses Valyu's semantic search API, so you're not wrestling with database-specific query syntax or chaining multiple API calls. The standout bit is getting actual content and figures in one request instead of bouncing between sources. You'll want this for literature reviews where comprehensive coverage matters more than the quirks of individual databases. Setup needs a Valyu API key, but they give you $10 in credits to start. The bash wrapper handles path resolution, which saves you from hunting down script locations in Claude's plugin cache.
- skills.sh installs
- 603
- GitHub stars
- 64
- last updated
- Aug 21, 2026
Install
$ npx -y skills add yorkeccak/scientific-skills --skill literature-search --agent claude-codeInstalls into .claude/skills of the current project.
Files
Literature Search
Search across all major scientific literature databases (PubMed, arXiv, bioRxiv, medRxiv) simultaneously using natural language queries powered by Valyu's semantic search API.
Why This Skill is Powerful
- No API Parameter Parsing: Just pass natural language queries directly - no need to construct complex search parameters
- Semantic Search: Understands the meaning of your query, not just keyword matching
- Full-Text Access: Returns complete article content, not just abstracts
- Image Links: Includes figures and images from papers
- Comprehensive Coverage: Search across PubMed, arXiv, bioRxiv, and medRxiv simultaneously
- Unified Results: Get results from all sources in a single query
Requirements
- Node.js 18+ (uses built-in fetch)
- Valyu API key from https://platform.valyu.ai ($10 free credits)
CRITICAL: Script Path Resolution
The scripts/search commands in this documentation are relative to this skill's installation directory.
Before running any command, locate the script using:
Sponsors
Details
- Repository
- github.com/yorkeccak/scientific-skills
- Category
- Data Science & ML
- First seen
- Jun 3, 2026