Scientific Research

A scientific methodology skill that helps formulate testable hypotheses from observations. It conducts literature searches via PubMed and web sources, generates competing hypotheses with evidence, designs experimental tests, and produces professional LaTeX reports with colored boxes and comprehensive appendices.

This skill enables direct access to UniProt, the world's leading protein sequence database. It allows searching for proteins by name, gene, or organism, retrieving sequences in FASTA format, and mapping identifiers between UniProt and other biological databases like PDB, Ensembl, and RefSeq.

This skill enables querying the STRING database for protein-protein interaction networks, functional enrichment analysis (GO, KEGG, Pfam), and homology comparisons. It covers 59 million proteins across 5000+ species and supports workflows like network visualization, pathway analysis, and hub protein discovery.

This skill enables querying the Reactome database for biological pathway analysis. It supports pathway enrichment analysis on gene/protein lists, expression data analysis, gene-to-pathway mapping, and visualization of results in the Reactome Pathway Browser for systems biology research.

This skill enables querying the NCBI Gene database for gene annotation and functional analysis. It provides Python scripts to search genes by symbol or ID, retrieve detailed gene metadata including RefSeqs, GO annotations, chromosomal locations, and phenotypes, and perform efficient batch lookups with built-in rate limiting.

This skill provides comprehensive guidance for accessing the European Nucleotide Archive (ENA), a public repository for nucleotide sequence data. It documents REST APIs for searching samples, studies, and assemblies, retrieving FASTQ files and genome sequences, querying taxonomic information, and bulk downloading datasets via FTP or Aspera for genomics research pipelines.

This skill enables AI-powered web searches using Perplexity models via OpenRouter, providing real-time answers with source citations. It's ideal for finding current information, scientific literature, and facts beyond Claude's training data cutoff, supporting multiple model tiers from cost-effective basic searches to advanced multi-step reasoning.

Hypogenic is a framework for automated scientific hypothesis generation using large language models. It can generate testable hypotheses from data alone (HypoGeniC), combine literature insights with empirical patterns (HypoRefine), or use both approaches together (Union methods). The skill provides configuration templates and documentation for accelerating research discovery across domains like deception detection, content analysis, and predictive modeling.