Search and retrieve scientific literature. Use when asked to find papers, research a topic, find citations, get paper abstracts, or conduct literature reviews. Accesses Semantic Scholar, arXiv, and other academic databases.
Installation
Details
Usage
After installing, this skill will be available to your AI coding assistant.
Verify installation:
npx agent-skills-cli listSkill Instructions
name: literature-search description: Search and retrieve scientific literature. Use when asked to find papers, research a topic, find citations, get paper abstracts, or conduct literature reviews. Accesses Semantic Scholar, arXiv, and other academic databases. allowed-tools:
- Read
- Write
- Bash
- WebSearch
- WebFetch
Scientific Literature Search
You are conducting scientific literature searches and reviews.
Available Resources
Semantic Scholar (Primary)
- 225M+ papers indexed
- Rich citation network
- AI-powered relevance ranking
- API access via MCP server
arXiv
- Preprints in physics, materials science, chemistry
- Open access
- Latest research before peer review
PubMed
- Biomedical and life sciences
- Peer-reviewed publications
CrossRef
- DOI resolution
- Publication metadata
Search Strategies
Topic Search
When researching a topic:
- Start with broad search terms
- Refine based on initial results
- Follow citation networks (cited by, references)
- Look for review articles first
Specific Paper Search
When looking for a specific paper:
- Search by title (exact or partial)
- Search by author + keywords
- Search by DOI if known
Citation Analysis
- Find highly cited papers in the field
- Look at recent papers citing foundational work
- Identify key authors and groups
Using Semantic Scholar MCP
The Semantic Scholar MCP server provides:
- Paper search
- Author search
- Citation information
- Paper recommendations
Example queries:
Search for papers on "CO2 adsorption in MOFs"
Find recent papers by Author Name about topic
Get citations for paper with ID xxx
Using Web Search
For broader searches:
Search for "metal-organic framework CO2 capture" site:nature.com
Search for "LAMMPS force field" filetype:pdf
Manual API Access (Fallback)
Semantic Scholar API
curl "https://api.semanticscholar.org/graph/v1/paper/search?query=machine+learning+materials&limit=10"
arXiv API
curl "http://export.arxiv.org/api/query?search_query=all:materials+science&max_results=10"
Literature Review Workflow
-
Define Scope
- What specific question are you answering?
- What time period? (last 5 years typical)
- What subfields?
-
Initial Search
- Use 3-5 different keyword combinations
- Note total results to gauge field size
-
Screen Results
- Read titles and abstracts
- Flag relevant papers
- Note key authors and journals
-
Deep Dive
- Read full text of key papers
- Extract methods, parameters, findings
- Build citation network
-
Synthesize
- Identify consensus and controversies
- Note gaps in literature
- Summarize for user
Extracting Information
From papers, extract:
- Methods: Simulation software, parameters, conditions
- Force fields: Which potentials used, parameters
- Results: Key numerical values, trends
- Limitations: What authors acknowledge
Citation Format
Use consistent format:
Author1, Author2, et al. "Title." Journal Volume, Pages (Year). DOI: xxx
Saving Results
Save literature search results to:
workspaces/project-name/literature/
├── search-results.md # Summary of search
├── key-papers.md # Annotated bibliography
├── extracted-parameters.md # Force field params, etc.
└── pdfs/ # Downloaded papers (if permitted)
Web Download (via Playwright)
For downloading papers or supplementary info:
Use playwright to navigate to [URL] and download the PDF
Note: Respect copyright and access restrictions.
Best Practices
- Document Everything: Record search terms, dates, result counts
- Check Recency: Prefer recent papers unless seeking foundational work
- Verify Citations: Cross-check important claims
- Look for Reviews: Start with review articles for new topics
- Follow Authors: Key researchers often have related work
- Check Preprints: arXiv may have newer versions
Common Queries
Materials Science
- Force field parameters for [material]
- DFT study of [property] in [material]
- Molecular dynamics of [process]
Computational Methods
- Best practices for [simulation type]
- Convergence testing for [property]
- Comparison of [method A] vs [method B]
Specific Materials
- [Material] synthesis and characterization
- [Material] applications in [field]
- [Material] properties: [specific property]
More by fl-sean03
View allRun jobs on CU Boulder CURC HPC cluster (Alpine). Use when simulations need more compute than the local workstation, for large-scale parallel jobs, or when GPU resources are needed beyond local availability. You have full SSH access - work like a researcher.
Run LAMMPS molecular dynamics simulations. Use when asked to run MD simulations, energy minimization, equilibration, production runs, or calculate properties like diffusion, RDF, MSD. Supports both CPU and GPU execution.
Run Quantum ESPRESSO DFT calculations. Use when asked to perform first-principles calculations, SCF, structural relaxation, band structure, DOS, phonons, or any ab initio quantum mechanical calculation.
Query materials databases for structures and properties. Use when asked to get crystal structures, material properties, phase diagrams, or thermodynamic data. Primary source is Materials Project, with NIST, PubChem as secondary.
