The Forge: Execution Engine

PubMed Evidence Pipeline

Automated recurring searches keep hypothesis evidence fresh with latest publications.

Runs every 6 hours via systemd · API Status

Tool Registry Statistics

Real Inventory: 282 tools currently available. This is our honest, working tool library — not aspirational vaporware.

Tool Execution Analytics

Data endpoint: /api/forge/analytics

Activity Timeline

Tool calls by hour (UTC) — success / errors

Usage by Category

Actual tool call volume grouped by tool type

Calls by Tool

Recent Tool Calls

Search PubMed for scientific papers. Returns PMIDs, titles, authors, abstracts.

Search ClinicalTrials.gov for trials: NCT ID, status, phase, conditions, interventions.

Search Semantic Scholar for papers with citation counts and abstracts.

Get gene annotation from MyGene.info: symbol, name, summary, aliases, GO terms.

Fetch full abstract for a PubMed article by PMID.

Convenience function combining PubMed, Semantic Scholar, and trials for comprehensive topic research.

Search OpenAlex (250M+ works) for scholarly articles with citation counts, topics, open access status. Broader coverage than PubMed with better bibliometrics.

Query Reactome pathway database for biological pathways involving a gene.

Query protein-protein interaction network from STRING DB with confidence scores and evidence types.

Extract figures from a scientific paper by PMID. Returns figure captions, image URLs, and descriptions via PMC BioC API, Europe PMC full-text XML, or open-access PDF extraction. Use when you need to see visual evidence (pathway diagrams, heatmaps, microscopy) from a cited paper.

Get comprehensive protein annotation from UniProt: function, domains, PTMs, subcellular location.

Retrieve clinical genetic variants from ClinVar with clinical significance and review status.

Query Allen Brain Atlas for brain region-specific gene expression data.

Get disease associations for a gene from Open Targets platform.

Run pathway/GO enrichment analysis on gene lists via Enrichr API.

Get genes associated with a disease from DisGeNET with association scores.

Query Human Protein Atlas for tissue and cell-specific expression and subcellular localization.

Query Allen Brain Cell Atlas for cell-type specific gene expression (SEA-AD, ABC Atlas)

Get disease associations for a gene from DisGeNET with scores and supporting evidence.

Query NHGRI-EBI GWAS Catalog for genetic associations with traits or genes.

Functional enrichment analysis for gene lists via STRING DB (GO terms, pathways, diseases).

Query KEGG pathway database for biological pathways involving a gene with pathway diagrams.

Find drugs targeting a specific gene/protein from ChEMBL database with activity data.

Get gene expression levels across tissues from GTEx portal.

Fetch AlphaFold protein structure predictions with confidence scores and 3D coordinates.

Get disease annotation from MyDisease.info: ontology, CTD data.

Get comprehensive gene annotation from Ensembl: coordinates, biotype, cross-references, mouse orthologs

Query PubChem compound database for molecular structures and properties.

Query OMIM for genetic diseases and phenotypes associated with a gene.

Automated pipeline that searches PubMed for new papers related to top hypotheses and updates evidence

Get developmental brain gene expression from BrainSpan Atlas across human brain development (8 weeks post-conception to 40 years).

Query DGIdb for drug-gene interactions and druggability categories. Aggregates DrugBank, PharmGKB, TTD, ChEMBL, and clinical guideline data.

Query DrugBank for comprehensive drug information including targets, indications, and pharmacology.

Search Europe PMC for biomedical literature with MeSH terms and citation counts

Search NCBI GEO for gene expression and genomics datasets.

Query CZI CellxGene Discovery API for single-cell datasets. Returns brain/neurodegeneration datasets with cell type annotations, tissue info, and disease context.

Search disease-associated methylation changes

Query EBI QuickGO for Gene Ontology annotations — biological process, molecular function, and cellular component terms for a gene.

Query BioGRID database for experimentally verified protein-protein interactions with evidence types.

Query gnomAD for population variant frequency and gene constraint metrics (pLI, o/e ratios). Returns LoF/missense variants with allele frequencies and ClinVar pathogenic counts.

Search Human Phenotype Ontology (HPO) for phenotype terms and gene/disease associations. Standardizes clinical phenotype vocabulary for neurodegeneration research.

Query InterPro for protein domain and family annotations (Pfam, SMART, PANTHER)

Query Bgee for gene expression across anatomical structures and developmental stages. Integrates RNA-seq data with developmental stage and cell type context — more granular than GTEx for brain regions.

Query EBI Proteins API for disease-associated protein variants with clinical annotations

Query Mouse Genome Informatics for mouse models, phenotypes, and gene homologs.

Search Pathway Commons for pathways across Reactome, KEGG, PANTHER, NCI-PID

Query STITCH database for chemical-protein interactions. Aggregates data from experiments, databases, text mining, and predictions.

Query BindingDB for protein-ligand binding affinity measurements (Ki, Kd, IC50, EC50) from the primary literature. Accepts gene symbol or UniProt accession. Returns compound names, affinities, SMILES, PubMed IDs, and BindingDB URLs. Supports optional max_ic50_nm filter for potent binders. Essential for drug target prioritization (BACE1, LRRK2, GSK3B, CDK5).

Query ClinGen for curated gene-disease validity classifications. Expert panels rate evidence from Definitive to Refuted. Gold-standard resource for determining whether a gene causes a specific disease.

Query COSMIC (via Open Targets) for somatic cancer mutations. Returns cancer associations with somatic mutation evidence scores from Cancer Gene Census and IntOGen.

Query EBI IntAct for experimentally validated molecular interactions. Aggregates data from BioGRID, MINT, DIP. Returns interactors with detection methods and publication evidence.

Query JASPAR database for transcription factor binding motifs and regulatory elements.

Query PharmGKB for pharmacogenomics drug-gene relationships. Returns clinical annotations linking genetic variants to drug response (efficacy, toxicity, dosage), level of evidence (1A–4), and CPIC guidelines.

Query HUGO Gene Nomenclature Committee (HGNC) for authoritative gene names, aliases, previous symbols, gene family membership, locus type (protein-coding/lncRNA/pseudogene), chromosomal location, and cross-references to Ensembl/UniProt/OMIM/RefSeq/MGI. Gold-standard for gene symbol disambiguation and family classification.

Query Monarch Initiative for disease-gene-phenotype associations. Integrates OMIM, ClinVar, HPO, MGI, ZFIN data. Supports disease→gene and gene→disease queries.

Query Agora (AMP-AD Knowledge Portal, Sage Bionetworks) for Alzheimer's Disease multi-omic gene target scoring. Integrates RNA-seq, proteomics, metabolomics, network centrality, and genetic risk evidence across AD brain datasets. Returns nomination status, expression changes in AD brain (RNA + protein), genetic risk association (IGAP), and evidence across modalities. Essential for AD target prioritization.

Query Alliance of Genome Resources (AGR) for cross-species gene orthologs using 8 integrated algorithms (OrthoFinder, PANTHER, Ensembl Compara, OMA, InParanoid, Phylome, OrthoMCL, HGNC). Returns orthologs in mouse, rat, zebrafish, fly, worm, and yeast with prediction method count and best-score flag. Critical for identifying model organism experiments that validate neurodegeneration mechanisms.

Search EBI BioStudies and ArrayExpress for transcriptomics, proteomics, and functional genomics datasets. Returns accession numbers, organism, study type. Complements NCBI GEO with European datasets and ArrayExpress studies.

Query EBI Complex Portal for experimentally validated protein complexes. Returns complex membership, subunit lists, and molecular functions. Essential for mechanistic interpretation of disease-associated proteins.

Search EBI Ontology Lookup Service (OLS4) across 300+ biomedical ontologies for disease, phenotype, molecular function, or chemical terms. Resolves free-text names to canonical ontology IDs: HPO (HP:), Disease Ontology (DOID:), MONDO, EFO, Gene Ontology (GO:), ChEBI. Essential for analyses that need standard identifiers for diseases or biological processes. Supports filtering by ontology and exact-match queries. Returns IDs, labels, descriptions, and synonyms.

Search ENCODE for epigenomics experiments (ChIP-seq, ATAC-seq, Hi-C) targeting a gene. Returns released experiments with biosample, assay type, and accession IDs. Critical for interpreting non-coding GWAS variants by finding TF binding sites and chromatin accessibility near neurodegeneration risk loci.

Query Ensembl Regulatory Build for regulatory elements in the genomic neighborhood of a gene. Returns promoters, enhancers, CTCF binding sites, and open chromatin regions derived from ENCODE/Roadmap data. Critical for interpreting non-coding GWAS variants near neurodegeneration loci (BIN1, CLU, PICALM, APOE). Reveals the regulatory landscape that controls gene expression.

Query EMBL-EBI Expression Atlas for differential expression experiments. Returns experiments where a gene is differentially expressed across conditions, tissues, and diseases.

Query GTEx v8 for cis-eQTLs in brain tissues: genetic variants that regulate gene expression in frontal cortex, hippocampus, substantia nigra and 6 other brain regions. Connects GWAS hits to causal gene regulation.

Query IMPC (International Mouse Phenotyping Consortium) for statistically significant phenotypes observed in knockout mice (p<0.0001). Covers 20+ biological systems including neurological, cardiovascular, metabolic, and immune phenotypes. Provides direct in vivo evidence of gene function — essential for validating disease hypotheses about neurodegeneration genes like TREM2, GBA, LRRK2, and PSEN1.

Query JensenLab DISEASES (STRING group) for text-mining gene-disease confidence scores derived from 500M+ MEDLINE abstracts. Provides independent evidence scores complementary to DisGeNET and ClinGen. Covers rare and common diseases with automated mining of scientific literature. High-confidence associations reflect strong co-mention signals across publications.

Query MSigDB gene set membership for a gene via Enrichr genemap. Returns which Hallmark, KEGG, Reactome, WikiPathways, and GO gene sets directly contain the query gene. Complements enrichr_analyze (which runs enrichment on a gene list) by answering 'which named pathways include this gene?' — useful for contextualizing a single candidate gene.

Fetch official NCBI gene summary, aliases, chromosomal location, and MIM IDs via the NCBI Datasets v2 API. Returns a concise functional overview from RefSeq curators — useful as a first-pass description of gene function before querying pathway or disease databases. Covers all human genes including rare neurodegeneration-associated genes.

Search NIH RePORTER for funded research grants on a topic. Returns project titles, PIs, institutions, award amounts, and abstract excerpts. Useful for mapping the funding landscape for neurodegeneration research areas, identifying active investigators, and understanding NIH research priorities. Covers all NIH institutes including NIA, NINDS, and NIMH.

Query OmniPath for directed signaling interactions and post-translational modifications (PTMs). Integrates 100+ databases (BioGRID, HPRD, PhosphoSitePlus, SignaLink, Reactome, CellTalkDB) with stimulation/inhibition directionality. Unlike STRING, focuses on regulatory direction — which kinase activates which receptor. Includes ligand-receptor interactions for cell-cell communication.

Query Open Targets Platform for drugs targeting a gene, with clinical phases, mechanisms of action, and disease indications. Focuses on clinical evidence and approved drugs — complements ChEMBL bioactivity data for drug repurposing.

Query Open Targets Genetics for GWAS loci linked to a gene via Locus-to-Gene (L2G) ML scoring. Maps genetic variants to probable causal genes using eQTLs, chromatin accessibility, and functional genomics. Essential for interpreting AD/PD GWAS hits.

Query Open Targets for baseline RNA expression across 100+ tissues for a gene, aggregated from GTEx and Expression Atlas. Returns TPM-like values and z-scores per tissue. Includes a brain_only flag to filter to CNS/neuronal tissues, making it directly useful for neurodegeneration context: microglia (TREM2), neurons (SNCA/MAPT), oligodendrocytes. Complements gtex_eqtl (genetic effects) and bgee_expression (developmental) with baseline expression profiles.

Query Open Targets Platform for drug tractability and modality assessments. Returns tractability buckets for small molecules (clinical/preclinical precedent, structural features), antibodies (membrane protein evidence), and other modalities. Critical for prioritizing therapeutic targets — especially relevant for neurodegeneration targets like LRRK2 (kinase), TREM2 (receptor), and GBA (enzyme).

Get canonical cell type marker genes from PanglaoDB scRNA-seq database. Covers microglia, astrocytes, neurons, OPCs, DAM, oligodendrocytes, endothelial, pericytes.

Search RCSB Protein Data Bank for experimental protein structures (X-ray, cryo-EM, NMR). Complements AlphaFold predictions with experimentally validated structural data including drug binding sites.

Query NIH Pharos TCRD for drug target development level (TDL): Tclin (approved drugs), Tchem (bioactive molecules), Tbio (biological knowledge only), Tdark (poorly characterized). Returns target family, disease associations, drugs and bioactive compounds. Essential for drug target prioritization in neurodegeneration.

Query WikiPathways community pathway database for biological pathways containing a gene. Complements Reactome and KEGG with community-curated pathways including disease-specific and rare pathway annotations. Returns pathway IDs, names, species, and visualization URLs.

Search ChEMBL (EBI) for small molecules, drugs, and chemical probes by name. Returns structural information, clinical development phase, ATC pharmacological classification, molecular properties (MW, LogP, HBD/HBA), and InChI key. Compound-centric complement to chembl_drug_targets (gene-centric). Useful for looking up a drug candidate's ChEMBL ID and clinical phase, or finding related compound series.

Retrieve publication metadata from CrossRef by DOI. Returns title, authors, journal, year, citation count, publisher, open access PDF link, subject areas, and funders. CrossRef indexes 150M+ scholarly works across all publishers — covers papers from any journal (not just biomedical), including clinical trials, meta-analyses, and specialized neuro-chemistry publications not in PubMed. Essential for DOI-based paper lookup when PMID is unavailable.

Query GTEx v8 for splicing QTLs (sQTLs) in brain: genetic variants that alter RNA splicing patterns across 9 brain regions. Complementary to eQTLs — many disease risk variants act by changing splice junction usage rather than expression level. Key examples: MAPT H1/H2 haplotype sQTLs (tau isoform switching), BIN1 hippocampal sQTLs. Returns per-tissue splice junction associations with variant IDs.

Query Harmonizome for gene-associated datasets across 114 gene-set libraries (KEGG, Reactome, OMIM, GO, GTEx, GWAS, ChEMBL, etc.). Enables rapid cross-database characterization of any gene.

Get age-related methylation changes

Query Open Targets for mouse model phenotypes associated with a gene. Returns experimentally observed phenotypes from knockout/transgenic mouse models aggregated from IMPC, MGI, and other sources. Provides phenotype class summaries (neurological, behavioral, metabolic, etc.) and biological model details (allelic composition, genetic background, literature). Useful for assessing whether modifying a gene has neurological or disease-relevant consequences in preclinical models.

Retrieve UniProt/Swiss-Prot curated protein feature annotations for a gene: post-translational modifications (phosphorylation, ubiquitination, acetylation, methylation), active sites, binding sites, glycosylation, disulfide bonds, signal peptides, and natural variants. Especially valuable for neurodegeneration research: tau (MAPT) phosphorylation landscape, alpha-synuclein (SNCA) PTMs, APP cleavage sites. Returns structured feature list with positions and evidence counts.

Annotate genetic variants using Ensembl Variant Effect Predictor (VEP). Accepts dbSNP rsIDs or HGVS notation and returns predicted molecular consequences (missense, splice, frameshift), SIFT/PolyPhen-2 pathogenicity scores, amino acid changes, and impact classification (HIGH/MODERATE/LOW/MODIFIER). Essential for interpreting neurodegeneration GWAS variants: APOE4=rs429358, LRRK2 G2019S=rs34637584, GBA N370S=rs76763715.

Get articles that cite a specific paper via Europe PMC

Query ProteomicsDB (TUM/Kuster lab) for mass spectrometry-based protein abundance across human tissues. Measures actual protein levels (iBAQ normalized intensity) across 60+ tissues/fluids. Complements RNA expression atlases (GTEx, HPA) with protein-level data — critical because mRNA and protein levels often diverge. Accepts gene symbol or UniProt accession.

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

Query Allen Brain Atlas for ISH expression data across brain regions.

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

Query CZ CELLxGENE Discover 'Where is My Gene' (WMG v2) API for quantitative single-cell gene expression across human cell types. Returns mean log2(CPM+1) expression, percent expressing cells, and total cell count per cell-type per tissue. Brain-relevant cell types (microglia, neurons, astrocytes, oligodendrocytes, pericytes) are prioritized. Distinct from cellxgene_gene_expression which only lists datasets. Critical for neurodegeneration: understanding which brain cell types express TREM2/APOE/APP/SNCA/MAPT at the single-cell level.

Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.

Drug compounds and bioactivity data for a gene target from the ChEMBL database of bioactive molecules.

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

Get CIViC (Clinical Interpretation of Variants in Cancer) expert-curated clinical variant interpretations for a gene. Returns variant names, HGVS expressions, variant types, and CIViC URLs. Useful for variant effect classification, functional evidence in overlapping cancer/neurodegeneration genes (IDH1, PTEN, ATM, BRCA2, TP53), and mechanistic evidence for rare disease variant interpretation.

Query ClinGen for curated gene-disease validity classifications.

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.

Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools.

Search ClinicalTrials.gov for clinical trials related to genes, diseases, or interventions. Returns NCT IDs, status, phase, conditions, interventions, enrollment, and sponsor info.

Fetch clinical genetic variants from NCBI ClinVar. Returns pathogenicity, review status, and associated conditions.

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints, needs help making a tough decision, asks for a council/panel/board discussion, wants to explore a problem from multiple angles, requests devil's advocate analysis, or says things like "what would different experts think about this", "help me think through this from all sides", "council mode", "mind council", or "deliberate on this". Also trigger when the user faces a dilemma, trade-off, or complex choice with no obvious answer.

Search for bioRxiv/medRxiv preprints via CrossRef API. Returns preprints indexed by CrossRef with title, authors, DOI, posted date, and abstract snippet. Useful for finding the latest findings before peer review, especially for fast-moving topics like tau pathology, neuroinflammation, TREM2 biology, Parkinson's alpha-synuclein research, and ALS/FTD mechanisms.

Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.

Search 78 public scientific, biomedical, materials science, and economic databases via REST APIs. Covers physics/astronomy (NASA, NIST, SDSS, SIMBAD), earth/environment (USGS, NOAA, EPA), chemistry/drugs (PubChem, ChEMBL, DrugBank, FDA, KEGG, ZINC, BindingDB), materials (Materials Project, COD), biology/genomics (Reactome, UniProt, STRING, Ensembl, NCBI Gene, GEO, GTEx, PDB, AlphaFold, InterPro, BioGRID, Gene Ontology, dbSNP, gnomAD, ENCODE, Human Protein Atlas, Human Cell Atlas), disease/clinical (COSMIC, Open Targets, ClinicalTrials.gov, OMIM, ClinVar, GDC/TCGA, cBioPortal, DisGeNET, GWAS Catalog), regulatory (FDA, USPTO, SEC EDGAR), economics/finance (FRED, World Bank, US Treasury), demographics (US Census, Eurostat, WHO). Use when looking up compounds, genes, proteins, pathways, variants, clinical trials, patents, economic indicators, or any public database API query.

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.

NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use for identifying cancer-specific vulnerabilities, synthetic lethal interactions, and validating oncology drug targets.

Query DGIdb for drug-gene interactions and druggability categories. Aggregates DrugBank, PharmGKB, TTD, ChEMBL, and clinical guideline data.

Extract cognitive patterns and thinking fingerprints from any text. Use this skill when the user wants to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, compare thinking styles between people, asks "what's my thinking style", "analyze how this person reasons", "cognitive profile", "thinking pattern", "DHDNA", "digital DNA", or wants to understand the mind behind any text. Also trigger when the user provides text and wants deeper insight into the author's reasoning patterns, decision-making style, or cognitive signature.

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

Get genes associated with a disease from DisGeNET with association scores.

Find diseases related to a query disease based on shared gene-disease associations in DisGeNET. Uses top-scoring genes for the query disease to identify comorbid or mechanistically related conditions. Helps map shared molecular substrates across neurodegeneration (e.g. diseases sharing APOE, LRRK2, or GBA pathways). Requires DISGENET_API_KEY for full results.

Get disease associations for a gene from DisGeNET with scores and supporting PMIDs.

DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Query EBI eQTL Catalog v2 for tissue/cell-type-specific expression QTLs. Covers 100+ studies beyond GTEx including microglia, iPSC-derived neurons, brain organoids, and disease cohorts. Returns rsid, variant, p-value, beta, SE, MAF, tissue_label, and qtl_group. Supports optional tissue_keyword filter (e.g. 'microglia', 'brain', 'iPSC').

Gene set enrichment against GO Biological Process. Enter a gene list to find enriched pathways.

Retrieve multi-source phenotype and disease associations for a gene via Ensembl REST API. Aggregates disease-gene links from Orphanet, OMIM/MIM morbid, NHGRI-EBI GWAS Catalog, DECIPHER, ClinVar, and UniProtKB into a unified view with MONDO/HP/Orphanet ontology accessions and data source provenance. Distinct from omim_gene_phenotypes (OMIM only), clinvar_variants (variant-level), and monarch_disease_genes (Monarch KG). Useful for comprehensive disease context, rare disease associations via Orphanet, and multi-source phenotype validation.

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

Query FinnGen R10 (N=520,000 Finns, 2,408 endpoints) for fine-mapped genetic loci. Returns SuSiE credible sets with lead SNP, gene, p-value, beta, and cross-trait annotations.

Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.

Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.

Look up any human gene — returns full name, summary, aliases, and gene type from MyGene.info.

Generate or edit images using AI models (FLUX, Nano Banana 2). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

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.

Query Genomics England PanelApp for disease gene panel memberships. Used by NHS Genomic Medicine Service for rare disease diagnosis. Returns panel name, disease group, confidence level (green/amber/red), mode of inheritance, penetrance, phenotypes, and gene evidence. Covers hereditary dementias, Parkinson, motor neuron disease, ataxias, and leukodystrophies.

Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), vector and raster data operations, spatial statistics, point cloud processing, network analysis, cloud-native workflows (STAC, COG, Planetary Computer), and 8 programming languages (Python, R, Julia, JavaScript, C++, Java, Go, Rust) with 500+ code examples. Use for remote sensing workflows, GIS analysis, spatial ML, Earth observation data processing, terrain analysis, hydrological modeling, marine spatial analysis, atmospheric science, and any geospatial computation task.

Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.

Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.

Submit and manage protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio), a web-based interface for autonomous lab execution on Reconfigurable Automation Carts (RACs). Use when the user wants to run cell-free protein expression (validation or optimization), generate fluorescent pixel art, or interact with Ginkgo Cloud Lab services. Covers protocol selection, input preparation, pricing, and ordering workflows.

Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.

Functional enrichment analysis via g:Profiler (ELIXIR bioinformatics platform). Tests a gene list against GO Biological Process, GO Molecular Function, GO Cellular Component, KEGG, Reactome, WikiPathways, Human Phenotype Ontology, and TRANSFAC databases. Complements Enrichr with different statistical correction (g:SCS method), independent database versions, and broader ontology coverage including HP phenotypes and miRTarBase targets.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Genome-wide association study hits from the NHGRI-EBI GWAS Catalog. Query by gene or trait.

Query EBI GWAS Catalog for all phenotypic associations reported for a specific genetic variant (rsID). Returns distinct traits grouped by study count and best p-value. Complements gwas_genetic_associations (gene-centric): this tool lets you see the full phenotypic spectrum of a known variant. Essential for major neurodegeneration variants: APOE4=rs429358 (Alzheimer, lipids, cognition), LRRK2 G2019S=rs34637584 (Parkinson), GBA N370S=rs76763715.

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Protein expression across human tissues and cell types from the Human Protein Atlas. Includes subcellular localisation.

Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.

Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.

Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work instructions, (4) preparing Medical Device Files, (5) understanding ISO 13485 requirements, or (6) identifying missing documentation for medical device certification. Also use when users mention medical device regulations, QMS certification, FDA QMSR, EU MDR, or need help with quality system documentation.

Query the KEGG Disease database for curated disease entries and their causal/associated genes. Returns KEGG disease IDs, gene lists with subtypes (e.g. AD1/APP, AD17/TREM2), approved drugs, and linked pathways. Disease-centric view distinct from kegg_pathways (gene-to-pathway). Valuable for getting the official KEGG gene list for neurodegeneration diseases with clinical subtypes.

Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.

This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

Search LIPID MAPS for lipid structures, classifications, and biological roles via KEGG cross-reference. Returns LMID, formula, exact mass, main/sub class, InChIKey, HMDB/ChEBI IDs, and LIPID MAPS URL. Covers glycerophospholipids, sphingolipids, gangliosides, ceramides, oxysterols, and plasmalogens — all implicated in neurodegeneration (NPC, Alzheimer, Parkinson, ALS).

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.).

Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.

Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.

Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores (cosine, modified cosine), and identifying unknown compounds from spectral libraries. Best for metabolite identification, spectral matching, library searching. For full LC-MS/MS proteomics pipelines use pyopenms.

MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.

Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.

Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.

Search the NIH Metabolomics Workbench for public metabolomics datasets. Returns study IDs, titles, species, analysis type (LC-MS, GC-MS, NMR), sample counts, and URLs. Useful for finding published CSF, brain region, or plasma metabolomics datasets for neurodegeneration diseases. Complements RNA/protein atlases with metabolite-level evidence.

Query cross-species methylation conservation

Get CpG island information for gene regions

Query developmental stage methylation dynamics

Search differential methylation between conditions

Query DNA methylation studies for specific genes

Compare methylation patterns across tissues

Get tissue-specific methylation patterns

Cloud computing platform for running Python on GPUs and serverless infrastructure. Use when deploying AI/ML models, running GPU-accelerated workloads, serving web endpoints, scheduling batch jobs, or scaling Python code to the cloud. Use this skill whenever the user mentions Modal, serverless GPU compute, deploying ML models to the cloud, serving inference endpoints, running batch processing in the cloud, or needs to scale Python workloads beyond their local machine. Also use when the user wants to run code on H100s, A100s, or other cloud GPUs, or needs to create a web API for a model.

Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, run energy minimization and production MD, analyze trajectories (RMSD, RMSF, contact maps, free energy surfaces). For structural biology, drug binding, and biophysics.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Query Monarch Initiative for disease-gene-phenotype associations from OMIM, ClinVar, HPO

Look up a variant in NCBI dbSNP for chromosomal position (GRCh38), reference/alternate alleles, functional class, gene context, and population allele frequencies from studies including 1000 Genomes, ALFA, and TOPMED. Complements Ensembl VEP (consequence prediction) and gnomAD (constraint) with official dbSNP registration metadata. Essential for characterizing a specific variant rsID.

Retrieve NCBI Gene Reference Into Function (GeneRIF) linked publications for a gene. GeneRIF is a curated set of brief functional annotations each backed by a PubMed paper. Returns titles, journals, and URLs for the top-cited papers supporting gene function annotations — a fast path to high-quality mechanistic evidence for any neurodegeneration gene.

Look up official NCBI Medical Subject Headings (MeSH) descriptors for diseases, pathways, and biological concepts. Returns the preferred descriptor name, hierarchical tree codes (e.g. C10.228.140.380 for Alzheimer Disease), scope note definition, and entry terms (all synonyms accepted by PubMed). Essential for standardizing terminology, discovering correct PubMed search terms, and navigating the MeSH vocabulary hierarchy from broad to specific.

Search the NCBI Sequence Read Archive (SRA) for public high-throughput sequencing datasets. Returns run accessions, titles, organisms, library strategy (RNA-Seq, ATAC-seq, ChIP-seq, scRNA-seq), and center names. Essential for finding publicly available neurodegeneration patient or model datasets for reanalysis.

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.

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.

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

Query OmniPath for post-translational modification (PTM) interactions integrating PhosphoSitePlus, PhosphoELM, SIGNOR, DEPOD, dbPTM, HPRD and 30+ other sources. Returns enzymes modifying the query gene AND substrates the gene modifies — phosphorylation, ubiquitination, acetylation, SUMOylation, methylation. Critical for tau kinase/phosphatase networks, alpha-synuclein ubiquitination (PINK1/Parkin), LRRK2 substrates, TDP-43/FUS in ALS.

Query FDA Adverse Event Reporting System (FAERS) via openFDA API for drug safety signals. Returns ranked adverse reactions with report counts and percentages from post-market surveillance. Useful for identifying neurological adverse events, CNS toxicity, ARIA risk, and safety liabilities for drugs being repurposed in neurodegeneration (donepezil, memantine, lecanemab, aducanumab, levodopa, riluzole).

Query the MRC IEU OpenGWAS platform for phenome-wide association study (PheWAS) data. Returns all GWAS traits where a given variant reaches genome-wide significance across 10K+ studies including UK Biobank, FinnGen, and many GWAS consortia. Complements GWAS Catalog by covering unpublished and OpenGWAS-native summary statistics. Useful for characterizing pleiotropic variants like rs429358 (APOE4).

Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports 16+ AI providers including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral with complete data privacy through self-hosting.

Get top-scored target genes for a disease from Open Targets Platform, integrating 14+ evidence types (GWAS, rare genetics, expression, pathways, animal models, literature). Disease-centric: given a disease name, returns ranked gene list with overall association score and per-evidence-type breakdown. Essential for target prioritization debates. Distinct from open_targets_associations (gene→diseases).

Disease associations and therapeutic evidence for a gene from Open Targets Platform, scored across multiple evidence sources.

Query Open Targets for target safety liability evidence curated from literature, clinical genetics, and animal toxicology. Returns safety events, affected tissues, inhibition effects, and supporting PMIDs. Critical for neurodegeneration drug discovery: CNS off-target effects, gene essentiality, tissue-specific toxicity, and high-risk indications for targets like LRRK2, BACE1, MAPT, CDK5, GSK3B.

Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants to speed up NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads. Covers physics simulation, differentiable rendering, mesh ray casting, particle systems (DEM/SPH/fluids), vector/similarity search, GPUDirect Storage file IO, interactive dashboards, geospatial analysis, medical imaging, and sparse eigensolvers. Also use when you see CPU-bound Python code (loops, large arrays, ML pipelines, graph analytics, image processing) that would benefit from GPU acceleration, even if not explicitly requested.

Get canonical cell type marker genes from PanglaoDB scRNA-seq database. Covers microglia, astrocytes, neurons, OPCs, DAM, oligodendrocytes.

Search Paperclip MCP for biomedical papers (8M+ across arXiv, bioRxiv, PMC, OpenAlex, OSF). Uses hybrid BM25+embedding search with TL;DR summaries.

Ingest a list of paper dicts into the local PaperCorpus cache for persistent storage. Each paper needs at least one ID (pmid, doi, or paper_id).

Search across PubMed, Semantic Scholar, OpenAlex, and CrossRef with unified results and local caching. Use providers param to filter to specific sources.

Start a stateful multi-page search session. Call again with incremented page param to fetch subsequent pages.

Search 10 academic paper databases via REST APIs for research papers, preprints, and scholarly articles. Covers PubMed, PMC (full text), bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall. Use when searching for papers, citations, DOI/PMID lookups, abstracts, full text, open access, preprints, citation graphs, author search, or any scholarly literature query. Triggers on mentions of any supported database or requests like "find papers on X" or "look up this DOI".

Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs.

All-in-one web toolkit powered by parallel-cli, with a strong emphasis on academic and scientific sources. Use this skill whenever the user needs to search the web, fetch/extract URL content, enrich data with web-sourced fields, or run deep research reports. Covers: web search (fast lookups, research, current info — prioritizing peer-reviewed papers, preprints, and scholarly databases), URL extraction (fetching pages, articles, academic PDFs), bulk data enrichment (adding fields to CSV/lists from the web), and deep research (exhaustive multi-source reports grounded in academic literature). Also handles setup, status checks, and result retrieval. Use this skill for ANY web-related task — even if the user doesn't mention 'parallel' or 'web' explicitly. If they want to look something up, fetch a page, enrich a dataset, investigate a topic, find academic papers, check citations, or review scientific literature, this is the skill to use.

Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

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.

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.

Search PGS Catalog (EMBL-EBI) for published polygenic risk score (PRS) models for a disease. Returns multi-SNP scoring models with variant counts, effect weight methods, publication DOI/year, and FTP download links. Covers 47+ Alzheimer disease PRS, 11+ Parkinson disease PRS, and hundreds of cognitive/brain trait models. Complements GWAS tools (single variants) with complete polygenic models ready for individual risk stratification. Essential for precision medicine analyses in neurodegeneration.

Query PharmGKB for pharmacogenomics drug-gene relationships. Returns clinical annotations linking genetic variants to drug response.

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.

High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual integration.

Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more.

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

Find bioassay-confirmed active compounds against a protein target in PubChem BioAssay. Returns assay IDs linked to the gene and CIDs of active compounds. Useful for identifying chemical probes, drug leads, validated inhibitors, and tool compounds for neurodegeneration target validation (BACE1, CDK5, GSK3B, LRRK2, GBA, HDAC6, PARP1).

Search PubMed for papers by keyword. Returns titles, authors, journals, PMIDs.

Extract standardized gene, disease, chemical, and variant mentions from PubMed literature using NCBI PubTator3 AI annotation. Resolves synonyms to canonical IDs (NCBI Gene IDs, MeSH disease IDs). Useful for finding papers where specific genes and diseases co-occur, building evidence chains for hypotheses, and disambiguating biomedical entity names.

High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.

Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API, opentrons-integration may be simpler.

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.

Complete mass spectrometry analysis platform. Use for proteomics workflows feature detection, peptide identification, protein quantification, and complex LC-MS/MS pipelines. Supports extensive file formats and algorithms. Best for proteomics, comprehensive MS data processing. For simple spectral comparison and metabolite ID use matchms.

Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.

Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.

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.

Interact with Zotero reference management libraries using the pyzotero Python client. Retrieve, create, update, and delete items, collections, tags, and attachments via the Zotero Web API v3. Use this skill when working with Zotero libraries programmatically, managing bibliographic references, exporting citations, searching library contents, uploading PDF attachments, or building research automation workflows that integrate with Zotero.

IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.

Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution.

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

Look up biological pathways a gene participates in, from Reactome.

Search Reactome for pathways by concept name and return constituent genes for each pathway. Complements the gene→pathway direction by going pathway-name→genes. Essential for building mechanistic gene sets for neurodegeneration analyses: mitophagy, tau clearance, NLRP3 inflammasome, amyloid processing, autophagy, endosomal sorting, complement activation, mTOR signaling.

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.

Look up current research information using parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.

Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related small-molecule or protein modeling tasks. Ideal for programmatic batch screening, multi-step chemistry pipelines, and workflows that would otherwise require maintaining local HPC/GPU infrastructure.

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.

Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.

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.

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.

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.

Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.

RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.

Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.

Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems, service operations, network traffic, logistics, or any system where entities interact with shared resources over time.

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.

Query STRING DB for a multi-gene functional interaction network with per-channel evidence scores: coexpression (escore), experimental binding/co-IP (ascore), text-mining (tscore), curated database (dscore), neighborhood (nscore), and gene fusion (fscore). Unlike the basic STRING protein interactions tool, this returns the complete evidence breakdown for every pairwise link so you can distinguish mechanistic (experimental) from correlative (coexpression/text-mining) evidence. Essential for assessing gene module cohesion in AD (TREM2/TYROBP/SYK/PLCG2), PD (PINK1/PARK2/LRRK2/SNCA), and ALS/FTD (TDP-43/FUS/C9orf72) networks.

Find physical protein-protein interactions from the STRING database. Enter 2+ gene symbols.

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.

Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

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.

Guide for building Graph Neural Networks with PyTorch Geometric (PyG). Use this skill whenever the user asks about graph neural networks, GNNs, node classification, link prediction, graph classification, message passing networks, heterogeneous graphs, neighbor sampling, or any task involving torch_geometric / PyG. Also trigger when you see imports from torch_geometric, or the user mentions graph convolutions (GCN, GAT, GraphSAGE, GIN), graph data structures, or working with relational/network data. Even if the user just says 'graph learning' or 'geometric deep learning', use this skill.

Fine-tune a model artifact on a dataset artifact via GPU sandbox. Produces a new model version with parent lineage, code commit SHA, and eval metrics captured. Use dry_run=True to validate and estimate cost before launching.

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

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.

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Cross-reference a compound across 40+ chemistry and pharmacology databases via EBI UniChem. Given a compound name or InChI key, returns the compound's IDs in ChEMBL, DrugBank, PubChem, BindingDB, DrugCentral, KEGG, ChEBI, and more. Essential for integrating multi-database drug evidence and resolving compound identity across sources.

Comprehensive protein annotation from UniProt/Swiss-Prot: function, domains, subcellular location, disease associations.

Query the U.S. Treasury Fiscal Data API for federal financial data including national debt, government spending, revenue, interest rates, exchange rates, and savings bonds. Access 54 datasets and 182 data tables with no API key required. Use when working with U.S. federal fiscal data, national debt tracking (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates on Treasury securities, foreign exchange rates, savings bonds, or any U.S. government financial statistics.

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.

Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like "what if...", "what would happen if...", "what are the possibilities", "explore scenarios", "scenario analysis", "possibility space", "what could go wrong", "best case / worst case", "risk analysis", "contingency planning", "strategic options", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.