Use when converting medical text between academic and patient-friendly tones, translating medical jargon for patients, adapting research papers for public audiences, or rewriting…
Discover novel small molecule binders for protein targets using structure-based and ligand-based approaches.
Provide comprehensive clinical interpretation of somatic mutations in cancer. Given a gene symbol + variant (e.g., EGFR L858R, BRAF V600E) and optional cancer type, performs…
AI-driven patient-to-trial matching for precision medicine and oncology. Given a patient profile (disease, molecular alterations, stage, prior treatments), discovers and ranks…
Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.
Production-ready genomics and epigenomics data processing for BixBench questions. Handles methylation array analysis (CpG filtering, differential methylation, age-related CpG…
Comprehensive immune repertoire analysis for T-cell and B-cell receptor sequencing data. Analyze TCR/BCR repertoires to assess clonality, diversity, V(D)J gene usage, CDR3…
Neuroscience research workflows: neuroanatomy, neural circuits, neurotransmitter biology, neurological/psychiatric disease genetics, neural-protein function.
Production-ready phylogenetics and sequence analysis skill for alignment processing, tree analysis, and evolutionary metrics.
Comprehensive patient stratification for precision medicine by integrating genomic, clinical, and therapeutic data.
Provide actionable treatment recommendations for cancer patients based on molecular profile. Interprets tumor mutations, identifies FDA-approved therapies, finds resistance…
Retrieves protein structure data from RCSB PDB, PDBe, and AlphaFold with protein disambiguation, quality assessment, and comprehensive structural profiles.
Production-ready RNA-seq differential expression analysis using PyDESeq2. Performs DESeq2 normalization, dispersion estimation, Wald testing, LFC shrinkage, and result filtering.
Retrieves biological sequences (DNA, RNA, protein) from NCBI and ENA with gene disambiguation, accession type handling, and comprehensive sequence profiles.
Production-ready single-cell and expression matrix analysis using scanpy, anndata, and scipy. Performs scRNA-seq QC, normalization, PCA, UMAP, Leiden/Louvain clustering,…
Comprehensive systems biology and pathway analysis using multiple pathway databases (Reactome, KEGG, WikiPathways, Pathway Commons, BioModels).
Gather comprehensive biological target intelligence from 9 parallel research paths covering protein info, structure, interactions, pathways, expression, variants, drug…
Production-ready VCF processing, variant annotation, mutation analysis, and structural variant (SV/CNV) interpretation for bioinformatics questions.
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep lear — from…
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep lear — from…
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep lear — from…
PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reaso — from…
PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reaso — from…
PyTorch-native Graph Neural Network framework for molecules and proteins. Suitable for building custom GNN architectures for drug discovery, protein modeling, or knowledge graph…
Use when you have raw or processed arrival-time data from a TWIM-MS instrument and need to convert it to CCS values for comparison across experiments or biomolecular classes.
Use when you have TWIM-MS data (arrival time and m/z values) from a multi-omic sample and need to: (1) establish a CCS calibration curve from known standards, (2) assign…
Query UCSC Genome Browser REST API for DNA sequences, tracks, gene models, and conservation across 100+ assemblies.
Atomic-design guidance for Molecules — functional groups of atoms (SearchBar = input + button + icon; FormField = label + input + error) with a single cohesive purpose.
Use when when you have parallel mass spectra and molecular structure data (e.g., CANOPUS or MassSpecGym datasets) and aim to train a single encoder-decoder model (e.g., BART) that…
Use when when you have a ranked list of GCF-MF (genomic cluster family–molecular feature) link predictions from one or more scoring functions, a curated set of known validated…
Use when when you have scored GCF-MF (gene cluster family–molecular family) links using two or more complementary scoring approaches (e.g., standardised strain correlation and…
变异与区间文件处理 skill。用于 VCF/BCF、BED、GFF/GTF、interval_list、peak、DMR、loop、genomic ranges 的过滤、合并、交集、注释、坐标系转换和 genome build 一致性检查。
Generate R/Python code for volcano plots from DEG (Differentially Expressed Genes) analysis results. Triggered when user needs visualization of gene expression data, p-value vs…
Use when when you have a parsed mass spectrum (precursor m/z, ionization mode, collision energy, and fragment peak list as m/z–intensity pairs) and need to obtain molecular…
Build whole-genome alignments using Progressive Cactus (Armstrong 2020 reference-free clade-level WGA), Minigraph-Cactus (Hickey 2024 pangenome-aware), LASTZ chain/net (U — from…
Use when when you have pre-processed MS/MS spectra and a pre-trained Word2Vec model, and need to compute fast, scalable similarity scores for library matching or molecular…
Use when when comparing large numbers of MS/MS spectra against spectral libraries or in molecular networking, particularly when molecules differ by multiple structural…
Use when when applying a pre-trained Word2Vec model to mass spectra at inference time (e.g., library matching or molecular networking), especially when the query spectra may…
Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.
Use when when you have a multi-step computational chemistry or molecular modeling pipeline (3+ sequential or parallel stages) that must process many molecules, each requiring…
Research and plan a knowledge work task thoroughly before execution. Optimized for pharma/biotech clinical development and consulting.
Execute a knowledge work plan efficiently using specialized agents. Use after the research phase to systematically work through a plan.
Use when interacting with a ZnDraw molecular visualization server — reading frames, navigating trajectories, selecting atoms, bookmarking, creating plots, running extensions, or…
Navigate organizational redesign for AI with a structured 13-skill toolkit that produces persistent artifacts in $HOME/.ai-first-kit/.
Critically review, score, compare, and rank one or more AI scientist outputs for biology, bioinformatics, computational life science, or adjacent research tasks.
Convert between .h5ad (AnnData) files and R single-cell data formats (Seurat, SingleCellExperiment) using anndataR.
Clinical-grade deep analysis of Apple Health export data. Parses the XML from iPhone's Health app export and produces a comprehensive clinical-quality health assessment report…
End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder…
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis.
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis.
Structure prediction using Boltz-1/Boltz-2, an open biomolecular structure predictor. Use this skill when: (1) Predicting protein complex structures, (2) Validating designed…
All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the start, (2) Designing around small molecules or liga — from…
All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the start, (2) Designing around small molecules or liga — from…
Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this skill when: (1) Scoring the regulatory effect of a variant on…
Structure prediction using Chai-1, a foundation model for molecular structure. Use this skill when: (1) Predicting protein-protein complex structures, (2) Validating designed…
Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com/chaidiscovery/chai-lab).
Query ChEMBL database for bioactivity data on drug-like compounds. Use this skill when: (1) Finding compounds active against a protein target (target-based search), (2) Getting…
Clarifies a vague clinical or biomedical research idea into a structured, bounded, searchable, researchable, and testable question.
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]",…
Builds the full component hierarchy from the raw design tree — mapping Figma components to atoms, molecules, and sections.