Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 870 files from 1 769 authors, of which 62 217 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Extracts and assigns COSMIC v3.4 mutational signatures (84 SBS / 11 DBS / 18 ID / 24 CN / 16 SV) from somatic VCFs using SigProfilerSuite, MutationalPatterns, MuSiCal mvNMF, SigNet, or HRDetect. Use when characterizing DNA-damage etiology (BRCA1/2 HRD, MMR-D, POLE, APOBEC3A, UV, tobacco, aflatoxin, 5-FU/SBS17b, platinum, colibactin SBS88), routing PARP inhibitor decisions, or auditing de novo extraction vs refit choice for cohort size.
End-to-end somatic variant calling from tumor-normal paired samples using Mutect2 or Strelka2. Covers preprocessing, variant calling, filtering, and annotation for cancer genomics. Use when calling somatic mutations from tumor-normal pairs.
Work with sparse matrices for memory-efficient storage of count data. Use when dealing with single-cell data or large bulk RNA-seq datasets where most values are zero.
Spatial analysis of cell neighborhoods and interactions in IMC data. Covers neighbor graphs, spatial statistics, and interaction testing. Use when analyzing spatial relationships between cell types, testing for neighborhood enrichment, or identifying cell-cell interaction patterns in imaging mass cytometry data.
Analyze cell-cell communication in spatial transcriptomics data using ligand-receptor analysis with Squidpy. Infer intercellular signaling, identify communication pathways, and visualize interaction networks. Use when analyzing cell-cell communication in spatial context.
Load spatial transcriptomics data from Visium, Xenium, MERFISH, Slide-seq, and other platforms using Squidpy and SpatialData. Read Space Ranger outputs, convert formats, and access spatial coordinates. Use when loading Visium, Xenium, MERFISH, or other spatial data.
Estimate cell type composition in spatial transcriptomics spots using reference-based deconvolution. Use cell2location, RCTD, SPOTlight, or Tangram to infer cell type proportions from scRNA-seq references. Use when estimating cell type composition in spatial spots.
Identify spatial domains and tissue regions in spatial transcriptomics data using Squidpy and Scanpy. Cluster spots considering both expression and spatial context to define anatomical regions. Use when identifying tissue domains or spatial regions.
Analyze high-resolution spatial platforms like Slide-seq, Stereo-seq, and Visium HD. Use when working with subcellular resolution or high-density spatial data.
Build spatial neighbor graphs for spatial transcriptomics data using Squidpy. Compute k-nearest neighbors, Delaunay triangulation, and radius-based connectivity for downstream spatial analyses. Use when building spatial neighborhood graphs.
End-to-end spatial transcriptomics workflow for Visium/Xenium data. Covers data loading, preprocessing, spatial analysis, domain detection, and visualization with Squidpy. Use when analyzing spatial transcriptomics data.
Quality control, filtering, normalization, and feature selection for spatial transcriptomics data. Calculate QC metrics, filter spots/cells, normalize counts, and identify highly variable genes. Use when filtering and normalizing spatial transcriptomics data.
Analyzes spatial proteomics data from CODEX, IMC, and MIBI platforms including cell segmentation and protein colocalization. Use when working with multiplexed imaging data, analyzing protein spatial patterns, or integrating spatial proteomics with transcriptomics.
Compute spatial statistics for spatial transcriptomics data using Squidpy. Calculate Moran's I, Geary's C, spatial autocorrelation, co-occurrence analysis, and neighborhood enrichment. Use when computing spatial autocorrelation or co-occurrence statistics.
Visualize spatial transcriptomics data using Squidpy and Scanpy. Create tissue plots with gene expression, clusters, and annotations overlaid on histology images. Use when visualizing spatial expression patterns.
Delimits species boundaries from molecular data using distance-based (ASAP), tree-based (bPTP, GMYC), and coalescent (BPP) methods. Compares multiple delimitation results with delimtools. Use when delineating putative species from DNA barcoding data, resolving cryptic species complexes, or validating taxonomic assignments. Emphasizes multi-method consensus following integrative taxonomy best practice.
Estimate species trees using coalescent methods including ASTRAL-III, wASTRAL, ASTRAL-Pro, SVDQuartets, and BPP. Use when multi-locus data shows gene tree discordance from incomplete lineage sorting, when in the anomaly zone where concatenation is misleading, or when computing concordance factors to assess topological support.
Build, manage, and search spectral libraries for proteomics. Use when creating or working with spectral libraries for DIA analysis. Covers DDA-based library generation, predicted libraries (Prosit, DeepLC), and library formats.
Normalizes ChIP-seq data using exogenous spike-in (ChIP-Rx with Drosophila chromatin per Orlando 2014 / Egan 2016; E. coli carryover for CUT&RUN/CUT&Tag). Distinguishes RRPM from Rx-Input scaling, integrates with DiffBind / DESeq2 / edgeR / csaw via sizeFactors and DiffBind library-size vectors, and applies the Patel et al 2024 *Nat Biotechnol* review's failure-mode framework to validate that normalization is correctly applied at the read level (not peak counts). Use when global signal shifts are expected (HDACi, BETi, EZH2i, dosage, target knockdown), when ChIPseqSpikeInFree detects post-hoc shifts, or when validating internal-control regions before publication.
Predicts whether a DNA variant alters mRNA splicing using sequence-based deep-learning tools — SpliceAI (10kb context dilated CNN, clinical default), Pangolin (multi-tissue), MMSplice (modular per-region CNN with calibrated ΔPSI), SpliceTransformer/TrASPr (tissue-aware transformers), SpliceVault (empirical 300K-RNA lookup of likely mis-splicing outcomes), CADD-Splice (composite score). Applies the ClinGen SVI 2023 framework for ACMG/AMP variant interpretation (PVS1, PP3, BP4 evidence codes), HGVS splicing nomenclature (c.123+1G>A, c.123-3T>G, r.spl?), extended-window scoring for deep-intronic pseudoexons, tissue-specific predictions, branchpoint variant detection (BPHunter, LaBranchoR), and splice-switching ASO design. Use when interpreting splice impact of clinical variants, prioritizing VUS, identifying deep-intronic pathogenic variants, or designing ASOs.
End-to-end alternative splicing analysis from FASTQ to differential splicing results for short-read bulk RNA-seq. Aligns with STAR 2-pass cohort-style, performs junction QC (RSeQC, MaxEntScan, SpliceAI), runs rMATS-turbo and leafcutter for concordant differential analysis, optionally MAJIQ V3 for complex events / heterogeneous cohorts, isoform-switching with NMD/ORF/domain consequences (IsoformSwitchAnalyzeR v2 + DRIMSeq+DEXSeq+stageR DTU), and sashimi visualizations. Use when performing comprehensive splicing analysis from raw bulk RNA-seq data; for variant-driven splice prediction see splice-variant-prediction; for rare-disease single-patient outlier detection see outlier-splicing-detection; for full-isoform PacBio/ONT analysis see long-read-splicing.
Assesses RNA-seq data quality specifically for alternative splicing analysis. QC layers include experimental design audit (library prep, read length, depth, replicates), STAR 2-pass cohort-style alignment, junction saturation curves and discovery plateau detection, novel-vs-known junction ratio diagnostics, junction-overhang distribution, splice-site strength scoring (MaxEntScan intrinsic + SpliceAI context-aware), strandedness verification, GENCODE basic vs comprehensive choice, and rRNA contamination screening. Splicing analysis is more demanding than DGE on read length, depth, library prep, alignment strategy, and annotation choice — failures silently bias PSI estimates and inflate novel-junction false positives. Use when evaluating data suitability for splicing analysis, troubleshooting low event detection, or designing sequencing experiments where AS is a primary endpoint.
Quantifies alternative splicing as PSI (percent spliced in) from RNA-seq using rMATS-turbo (BAM-based event), SUPPA2 (TPM-based event), MAJIQ V3 (LSV-based Bayesian), leafcutter (annotation-free intron clusters), VAST-TOOLS (cross-species with microexon support), Shiba (junction-imbalance-corrected, 2025 SOTA at low coverage), or IRFinder-S (intron retention coverage-aware). Distinguishes the five canonical event classes (SE, A5SS, A3SS, MXE, RI), special classes (microexons, exitrons, AFE/ALE), intron retention subtypes (canonical RI vs detained introns), and applies effective-length normalization. Use when measuring splice-site usage or isoform inclusion ratios from short-read RNA-seq.
Download raw sequencing reads from NCBI SRA using sra-tools (prefetch, fasterq-dump, vdb-validate) or the ENA mirror. Use when pulling FASTQ for SRR/ERR/DRR accessions, deciding between SRA-direct, ENA mirror, or AWS/GCP cloud mirror (STRIDES), handling --include-technical for 10x and other single-cell records, validating with MD5/vdb-validate, navigating SRR/SRX/SRS/SRP/PRJNA hierarchy, or finding accessions via pysradb. Encodes SRA cloud-egress economics, the fasterq-dump uncompressed-scratch trap, and the --max-size default that silently truncates large prefetches.
Profiles RNA-binding protein targets without antibody or UV crosslinking using STAMP (APOBEC1-RBP fusion, C-to-U editing), scSTAMP (single-cell), TRIBE/HyperTRIBE (ADAR-RBP, A-to-I editing), DART-seq (APOBEC1-YTH for m6A), or Bullseye/SAILOR edit-site detection pipelines. Use when antibody is unavailable or specificity is doubtful, when single-cell RBP profiling is needed (scSTAMP), or when in vivo RBP profiling without UV is preferred.
Align RNA-seq reads with STAR (Spliced Transcripts Alignment to a Reference). Supports two-pass mode for novel splice junction discovery. Use when aligning RNA-seq data requiring splice-aware alignment.
Statistical analysis for metabolomics data. Covers preprocessing (log2 transformation, normalization), limma moderated testing with empirical Bayes, Welch's t-tests with BH correction, fold change estimation, and multivariate methods (PCA, PLS-DA, OPLS-DA). Use when identifying differentially abundant metabolites or building classification models.
Add p-value brackets, significance asterisks, and effect-size annotations to distribution plots using ggpubr, ggsignif, and statannotations with correct test selection (parametric vs non-parametric vs paired), multiple-testing adjustment, and rendering of negative results. Use when a boxplot/violin/raincloud needs in-figure statistical comparisons between groups.
Track bacterial strains using MASH, sourmash, fastANI, and inStrain. Compare genomes, detect contamination, and monitor strain-level variation. Use when needing sub-species resolution for outbreak tracking, transmission analysis, or within-host strain dynamics.
Align protein structures using Foldseek 3Di, TM-align, US-align, DALI, or Foldmason for structural MSA. Predict, score, and superpose backbone coordinates when sequence identity is below the twilight zone or remote-homology detection is required. Use when sequence MSA fails (<25% identity), when the dark proteome is the target, when AlphaFoldDB / ESM Atlas search is needed, or when structural superposition is the goal.
Call structural variants (SVs) from sequencing data using Manta, Delly, GRIDSS, and LUMPY. Detects deletions, insertions, inversions, duplications, and translocations too large for standard SNV callers. Use when detecting structural variants from short-read or long-read data and building consensus callsets.
Detect structural variants from long-read alignments using Sniffles, cuteSV, and SVIM. Use when detecting deletions, insertions, inversions, translocations, or complex rearrangements from ONT or PacBio data, especially those missed by short-read methods.
Parse and write protein structure files using Biopython Bio.PDB. Use when reading PDB, mmCIF, and MMTF files, downloading structures from RCSB PDB, or writing structures to various formats.
Modify protein structures using Biopython Bio.PDB. Use when transforming coordinates, removing atoms or residues, adding new entities, modifying B-factors and occupancies, or building structures programmatically.
Navigate protein structure hierarchy using Biopython Bio.PDB SMCRA model. Use when accessing models, chains, residues, and atoms, iterating over structure levels, or extracting sequences from PDB files.
Analyzes experimental RNA structure probing data from SHAPE-MaP and DMS-MaPseq experiments using ShapeMapper2. Converts mutation rates to per-nucleotide reactivity profiles that constrain structure prediction. Use when processing SHAPE-MaP or DMS-MaPseq sequencing data to obtain experimental RNA structure information.
Resolve subclonal copy number, whole-genome doubling, and copy-number tumor evolution from bulk sequencing with Battenberg, TITAN, and MEDICC2. Covers clonal versus subclonal copy-number states, haplotype phasing for subclonal resolution, cancer cell fraction, whole-genome-doubling detection and timing relative to mutations, mirrored subclonal allelic imbalance, and copy-number phylogenies. Use when a tumor is heterogeneous and bulk data shows non-integer copy number, when calling subclonal CNAs, detecting or timing whole-genome doubling, reconstructing copy-number evolution, or deciding between Battenberg and TITAN.
Performs subgroup and heterogeneous treatment effect (HTE) analyses for clinical trials. Covers Mantel-Haenszel pooling, Breslow-Day, interaction tests in regression, RERI for additive interaction, modern data-adaptive HTE methods (STEPP, SIDES, causal forests, X/R-learners), Bayesian shrinkage (Dixon-Simon, MAP, EXNEX), graphical multiplicity (Bretz-Maurer), and credibility frameworks (Sun BMJ, EMA 2019). Use when analyzing treatment effects across patient subgroups for regulatory submissions or precision-medicine claims.
Searches molecular libraries for substructure matches using SMARTS patterns with explicit handling of recursive SMARTS, ring membership, aromaticity dialect, vector binding, atom map indices, and reactive/PAINS/REOS/Brenk/Aldridge filter catalogs. Use when filtering compounds by pharmacophore features, functional groups, scaffold matches, or screening for assay-interference / structural alerts.
Identifies super-enhancers from H3K27ac, MED1, or BRD4 ChIP-seq using ROSE, ROSE2, LILY, HOMER -style super, and ENCODE dELS cross-referencing. Handles peak stitching parameters, ranking choices, hockey-stick inflection, marker choice (H3K27ac vs MED1/BRD4), and cross-condition comparison with spike-in normalization. Constructs core regulatory circuitry (Saint-Andre 2016) from SE-encoded TFs. Use when identifying cell-identity / cancer-associated regulatory domains, comparing super-enhancers between conditions, identifying master transcription factor networks, or predicting BET-inhibitor responsiveness.
Detect syntenic blocks and structural rearrangements between genomes using MCScanX (Wang 2012), JCVI/MCScan (Tang 2008 Python), GENESPACE (Lovell 2022) for orthology-anchored riparian visualization, SyRI for structural variation, AnchorWave for sequence-level synteny, i-ADHoRe 3.0 for highly diverged species, SynNet for synteny networks, and ntSynt for multi-genome macrosynteny. Use when identifying collinear gene blocks across species, distinguishing macrosynteny from microsynteny, detecting inversions/translocations/duplications, anchoring orthology in WGD lineages, producing publication riparian plots, computing synteny block age via Ks (cross-references whole-genome-duplication), or running synteny-aware ortholog inference in polyploids.
Call topologically associating domains (TADs) from Hi-C data using insulation score, HiCExplorer, and other methods. Identify domain boundaries and hierarchical domain structure. Use when calling TADs from Hi-C insulation scores.
Predict miRNA target genes using sequence-based algorithms and database lookups. Use when identifying potential mRNA targets of differentially expressed or functionally important miRNAs.
Targeted metabolomics analysis using MRM/SRM with standard curves. Covers absolute quantification, method validation, and quality assessment. Use when quantifying specific metabolites using calibration curves and internal standards.
Taxonomic classification of ASVs using reference databases like SILVA, GTDB, or UNITE. Covers naive Bayes classifiers (DADA2, IDTAXA) and exact matching approaches. Use when assigning taxonomy to ASVs after DADA2 amplicon processing.
Predict TCR-epitope specificity using ERGO-II and deep learning models for T-cell receptor antigen recognition. Match TCRs to their cognate epitopes or predict TCR targets. Use when analyzing TCR repertoire specificity or identifying antigen-reactive T-cells.
End-to-end TCR/BCR repertoire analysis from FASTQ to clonotype diversity metrics. Use when analyzing immune repertoire sequencing data from bulk or single-cell experiments.
Clusters genes by temporal expression profile shape using Mfuzz soft clustering, TCseq, and DEGreport degPatterns. Groups co-regulated genes into shared trajectory patterns via fuzzy c-means or hierarchical approaches. Use when categorizing temporally dynamic genes into response groups or identifying co-expression modules across time points. Requires temporally variable genes identified first (see differential-expression/timeseries-de).
Infers dynamic gene regulatory networks from bulk time-series expression data using Granger causality (statsmodels), dynGENIE3 (Extra-Trees on ODE-derived expression derivatives), and dynamic Bayesian networks (bnlearn). Identifies time-delayed regulatory relationships and tracks network rewiring across conditions. Use when inferring causal regulatory relationships from bulk temporal expression data or detecting TF influence propagation over time. Not for static co-expression networks (see gene-regulatory-networks/coexpression-networks).
End-to-end time-course analysis from expression matrix to temporal patterns and enrichment. Covers temporal DE, Mfuzz soft clustering, optional rhythm detection, GAM trajectory fitting, and per-cluster pathway enrichment. Use when analyzing bulk time-series expression experiments from any omics platform.
Analyze time-series RNA-seq data using limma voom with splines, maSigPro, and ImpulseDE2. Identify genes with dynamic expression patterns. Use when analyzing time-series or longitudinal expression data.
Infer developmental trajectories and pseudotime from single-cell RNA-seq data using Monocle3, Slingshot, and scVelo for RNA velocity analysis. Use when inferring developmental trajectories or pseudotime.
Models continuous temporal trajectories from bulk or time-resolved omics data using generalized additive models (mgcv), spline regression, and changepoint detection (segmented, ruptures). Fits smooth gene expression curves and tests trajectory differences between conditions. Use when fitting non-linear temporal models to bulk time-series data or comparing developmental trajectories across conditions. Not for single-cell pseudotime (see single-cell/trajectory-inference).
Transcribe DNA to RNA and translate to protein using Biopython. Use when converting between DNA, RNA, and protein sequences, finding ORFs, or using alternative codon tables.
Performs gene-level association from GWAS summary statistics via genetically predicted tissue expression using FUSION, PrediXcan, S-PrediXcan, S-MultiXcan, UTMOST, MOSTWAS, kTWAS, EpiXcan, TIGAR-V2, and probabilistic fine-mapping with FOCUS and MA-FOCUS. Use when running TWAS from GWAS sumstats, prioritising candidate causal genes from a GWAS lead locus, picking single-tissue vs cross-tissue models, identifying LD-induced TWAS false positives, choosing ancestry-matched prediction weights, fine-mapping co-regulated TWAS hits, or triangulating TWAS with cis-eQTL Mendelian randomization and colocalization to nominate a causal gene.
Calculate translation efficiency (TE) as the ratio of ribosome occupancy to mRNA abundance. Use when comparing translational regulation between conditions or identifying genes with altered translation independent of transcription.
Infer pathogen transmission networks and identify likely transmission pairs using TransPhylo and outbreak reconstruction algorithms. Estimate who-infected-whom from genomic and epidemiological data. Use when investigating outbreak transmission chains or identifying superspreaders.
Read, write, and convert phylogenetic tree files using Biopython Bio.Phylo. Use when parsing Newick, Nexus, PhyloXML, or NeXML tree formats, converting between formats, or handling multiple trees.
Modify phylogenetic tree structure using Biopython Bio.Phylo. Use when rooting trees with outgroups, midpoint, or MAD methods, pruning taxa, collapsing clades, ladderizing branches, or extracting subtrees. Includes rooting method decision guidance.
Draw and export phylogenetic trees using Biopython Bio.Phylo with matplotlib and modern alternatives. Use when creating tree figures, customizing colors and labels, exporting to image formats, or choosing between Bio.Phylo, ggtree, ETE4, and iTOL for publication.
Claude Skills — questions
Answers built from the skills we actually parsed.