Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working with matrices symbolically, physics calculations, number theory problems, geometry computations, and generating executable code from mathematical expressions. Apply this skill when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters.
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.
Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
Search PubMed biomedical literature with natural language queries powered by Valyu semantic search. Full-text access, integrate into your AI projects.
Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.
Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design. Uses RFdiffusion for backbone generation, ProteinMPNN for sequence design, ESMFold/AlphaFold2 for validation. Use when asked to design protein binders, therapeutic proteins, or engineer protein function.
PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.
Query NHGRI-EBI GWAS Catalog for SNP-trait associations. Search variants by rs ID, disease/trait, gene, retrieve p-values and summary statistics, for genetic epidemiology and polygenic risk scores.
Compare GWAS studies, perform meta-analyses, and assess replication across cohorts. Integrates NHGRI-EBI GWAS Catalog and Open Targets Genetics to compare study designs, effect sizes, ancestry diversity, and heterogeneity statistics. Use when comparing GWAS studies for a trait, performing meta-analysis of genetic loci, assessing replication across cohorts, or exploring the genetic architecture of complex diseases.
Interpret genetic variants (SNPs) from GWAS studies by aggregating evidence from multiple databases (GWAS Catalog, Open Targets Genetics, ClinVar). Retrieves variant annotations, GWAS trait associations, fine-mapping evidence, locus-to-gene predictions, and clinical significance. Use when asked to interpret a SNP by rsID, find disease associations for a variant, assess clinical significance, or answer questions like "What diseases is rs429358 associated with?" or "Interpret rs7903146".
Discover genes associated with diseases and traits using GWAS data from the GWAS Catalog (500,000+ associations) and Open Targets Genetics (L2G predictions). Identifies genetic risk factors, prioritizes causal genes via locus-to-gene scoring, and assesses druggability. Use when asked to find genes associated with a disease or trait, discover genetic risk factors, translate GWAS signals to gene targets, or answer questions like "What genes are associated with type 2 diabetes?"
Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
Retrieves biological sequences (DNA, RNA, protein) from NCBI and ENA with gene disambiguation, accession type handling, and comprehensive sequence profiles. Creates detailed reports with sequence metadata, cross-database references, and download options. Use when users need nucleotide sequences, protein sequences, genome data, or mention GenBank, RefSeq, EMBL accessions.
Retrieves protein structure data from RCSB PDB, PDBe, and AlphaFold with protein disambiguation, quality assessment, and comprehensive structural profiles. Creates detailed structure reports with experimental metadata, ligand information, and download links. Use when users need protein structures, 3D models, crystallography data, or mention PDB IDs (4-character codes like 1ABC) or UniProt accessions.
