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.
Runs cis-pQTL Mendelian randomization for drug-target validation using UKB-PPP (Olink), deCODE (SomaScan), Fenland, INTERVAL, ARIC, and FinnGen-PPP proteomes plus colocalization triangulation, phenome-wide on-target adverse-effect scans, cross-platform Olink/SomaScan replication, and PAV (protein-altering variant) sensitivity. Use when nominating or de-risking a drug target from plasma-proteome GWAS, mimicking pharmacological inhibition via cis-pQTL instruments, separating shared-causal from LD-confounded signal under the Schmidt 2020 cis-MR framework, screening on-target adverse phenotypes pheWAS-style, or producing publication-grade STROBE-MR plus PP.H4 evidence for a target gene.
End-to-end proteomics workflow from MaxQuant output to differential protein abundance. Orchestrates data import, normalization, imputation, and statistical testing with limma (default) or MSstats for complex feature-level designs. Use when processing mass spectrometry proteomics.
Quality control and assessment for proteomics data. Use when evaluating proteomics data quality before downstream analysis. Covers sample metrics, missing value patterns, replicate correlation, batch effects, and intensity distributions.
Find nearest features, search within windows, and extend intervals using closest, window, flank, and slop operations. Use when performing TSS proximity analysis, assigning enhancers to genes, defining promoter regions, or finding nearby genomic features.
Post-translational modification analysis including phosphorylation, acetylation, and ubiquitination. Covers site localization, motif analysis, and quantitative PTM analysis. Use when analyzing phosphoproteomic data or other modification-enriched samples.
QIIME2 command-line workflow for 16S/ITS amplicon analysis. Alternative to DADA2/phyloseq R workflow with built-in provenance tracking. Use when preferring CLI over R, needing reproducible provenance, or working within QIIME2 ecosystem.
Design qPCR primers and TaqMan/molecular beacon probes using primer3-py. Configure probe Tm, primer-probe spacing, and hydrolysis probe constraints for real-time PCR assays. Use when designing qPCR primers and probes.
Builds QSAR / QSPR models using chemprop D-MPNN, MolFormer, Uni-Mol, ChemBERTa, random forest baselines, and Gaussian processes with explicit handling of OECD 5 principles, applicability domain (kNN, leverage, conformal prediction, Mahalanobis), scaffold-balanced splits, ensemble uncertainty, calibration (Platt, isotonic), feature importance (SHAP, atomic attribution), and prospective validation. Use when building target-specific predictive models from in-house bioassay data, ADMET endpoints, or selectivity profiles.
Filter reads by quality scores, length, and N content using Trimmomatic and fastp. Apply sliding window trimming, remove low-quality bases from read ends, and discard reads below thresholds. Use when reads have poor quality tails or require minimum quality for downstream analysis.
Quality metrics for IMC data including signal-to-noise, channel correlation, tissue integrity, and acquisition QC. Use when assessing data quality before analysis or troubleshooting problematic acquisitions.
Generate and interpret quality reports from FASTQ files using FastQC and MultiQC. Assess per-base quality, adapter content, GC bias, duplication levels, and overrepresented sequences. Use when performing initial QC on raw sequencing data or validating preprocessing results.
Protein quantification from mass spectrometry data including label-free (LFQ, intensity-based), isobaric labeling (TMT, iTRAQ), and metabolic labeling (SILAC) approaches. Use when extracting protein abundances from MS data for differential analysis.
Build reproducible scientific documents, presentations, and websites with Quarto supporting R, Python, Julia, and Observable JS. Use when creating reproducible reports with Quarto.
Enumerates virtual chemical libraries via reaction SMARTS transformations using RDKit and Reaction templates, with explicit handling of atom mapping, template extraction (RDKit reaction mining), product validation, RECAP/BRICS fragmentation, R-group decomposition, matched molecular pair analysis (MMPA), and Free-Wilson analysis. Use when generating combinatorial libraries from building blocks, enumerating analog series, deriving structure-activity rules, or extracting transformations from reaction data.
Reactome pathway enrichment using ReactomePA package. Use when analyzing gene lists against Reactome's curated peer-reviewed pathway database. Performs over-representation analysis and GSEA with visualization and pathway hierarchy exploration.
Read biological sequence files (FASTA, FASTQ, GenBank, EMBL, ABI, SFF) using Biopython Bio.SeqIO. Use when parsing sequence files, iterating multi-sequence files, random access to large files, or high-performance parsing.
Identify recurrent and driver copy number alterations across a tumor cohort with GISTIC2 (G-score, Ziggurat deconstruction, focal vs broad/arm-level analysis, q-values from permutation) and quantify copy-number signatures with the Steele 2022 COSMIC framework and the Drews 2022 CINSignatures framework. Covers driver-gene localization from recurrence peaks, distinguishing focal drivers from arm-level passengers, and the caller-sensitivity caveats of copy-number signatures. Use when finding recurrently amplified or deleted regions in a cohort, localizing driver genes, separating focal from broad events, running GISTIC2, or extracting copy-number mutational signatures.
Generate consensus sequences and manage reference files using samtools. Use when creating consensus from alignments, indexing references, or creating sequence dictionaries.
Download, prepare, and manage reference panels for phasing and imputation. Covers 1000 Genomes, HRC, and TOPMed panels. Use when setting up imputation infrastructure or selecting appropriate reference panels for target populations.
Detect distant homologs using profile and structure-aware methods that go beyond standard BLAST. Use when sequence identity falls into the twilight zone (<35% pairwise), when BLAST fails to find homologs that should exist, when working at metagenomic scale (DIAMOND, MMseqs2), or when structure beats sequence (Foldseek). Covers PSI-BLAST (iterative PSSM), jackhmmer (iterative HMM), HHblits/HHsearch (profile-profile), DIAMOND, MMseqs2, and Foldseek (3Di structural alphabet, van Kempen 2024).
Identify and classify repetitive elements and transposable elements using RepeatModeler for de novo repeat library construction and RepeatMasker for genome-wide repeat annotation. Quantify TE expression from RNA-seq with TEtranscripts. Use when masking repeats before gene prediction or analyzing transposable element activity.
Create publication-quality visualizations of immune repertoire data including circos plots, clone tracking, diversity plots, and network graphs. Use when generating figures for repertoire comparisons, clonal dynamics, or V(D)J gene usage.
Create restriction maps showing enzyme cut positions on DNA sequences using Biopython Bio.Restriction. Visualize cut sites, calculate distances between sites, and generate text or graphical maps. Use when creating or analyzing restriction maps.
Find restriction enzyme cut sites in DNA sequences using Biopython Bio.Restriction. Search with single enzymes, batches of enzymes, or commercially available enzyme sets. Returns cut positions for linear or circular DNA. Use when finding restriction enzyme cut sites in sequences.
Performs retrosynthetic planning using AiZynthFinder (MCTS, template-based), Chemformer (template-free transformer), ASKCOS, and emerging RetroSynFormer with explicit handling of route scoring, building-block availability (eMolecules, Enamine, Mcule), forward prediction validation (Molecular Transformer), and disconnection-aware multi-objective search (MO-MCTS). Use when assessing synthetic feasibility of generated or selected molecules, planning multi-step syntheses, building synthesis-aware design pipelines, or screening libraries for retro-route feasibility.
Generate reverse complements and complements of DNA/RNA sequences using Biopython. Use when working with opposite strands, primer design, or converting between template and coding strands.
End-to-end Ribo-seq analysis from FASTQ to translation efficiency and ORF detection. Use when analyzing ribosome profiling data to study translation.
Preprocess ribosome profiling data including adapter trimming, size selection, rRNA removal, and alignment. Use when preparing Ribo-seq reads for downstream analysis of translation.
Validate Ribo-seq data quality by checking 3-nucleotide periodicity and calculating P-site offsets. Use when assessing library quality or determining read offsets for downstream analysis.
Detect ribosome pausing and stalling sites from Ribo-seq data at codon resolution. Use when studying translational regulation, identifying pause sites, or analyzing codon-specific translation dynamics.
Create reproducible bioinformatics analysis reports with R Markdown including code, results, and visualizations in HTML, PDF, or Word format. Use when generating analysis reports with RMarkdown.
RNA-seq specific quality control including rRNA contamination detection, strandedness verification, gene body coverage, and transcript integrity metrics. Use when validating RNA-seq libraries before differential expression analysis.
End-to-end RNA-seq workflow from FASTQ files to differential expression results. Covers QC, quantification (Salmon or STAR+featureCounts), and DESeq2 analysis with visualization. Use when running RNA-seq from FASTQ to DE results.
View, convert, and understand SAM/BAM/CRAM alignment files using samtools and pysam. Use when inspecting alignments, converting between formats, or understanding alignment file structure.
Estimates required sample sizes for differential expression, ChIP-seq, methylation, and proteomics studies. Use when budgeting experiments, writing grant proposals, or determining minimum replicates needed to achieve statistical significance for expected effect sizes.
Creates sashimi-style plots showing RNA-seq read coverage and splice junction counts using ggsashimi (general-purpose, condition-grouped overlays), rmats2sashimiplot (rMATS-output-aware), MAJIQ-VOILA (LSV posteriors interactive HTML), leafviz (leafcutter clusters Shiny), Jutils (tool-agnostic heatmaps and sashimi for rMATS/leafcutter/SUPPA2/MAJIQ output), or pyGenomeTracks (multi-track publication figures). Tool choice depends on the upstream differential-splicing tool's output format and the publication vs interactive use case. Use when visualizing specific splicing events, validating differential splicing calls, or producing publication-quality figures.
Analyzes chemical libraries by scaffold using Bemis-Murcko scaffolds, generic frameworks, cyclic skeletons, matched molecular pair (MMP) analysis via mmpdb, R-group decomposition, Free-Wilson analysis, scaffold hopping, and chemotype-aware ML train/test splits. Use when identifying chemotype clusters in a library, deriving SAR transformation rules, decomposing series into R-groups, performing scaffold-balanced QSAR splits, or planning analog campaigns.
Scaffold contigs into chromosome-level assemblies using Hi-C data with YaHS, 3D-DNA, SALSA2, and validate with BUSCO and contact maps. Use when scaffolding contigs to chromosome-level assemblies.
Single-cell ATAC-seq analysis with Signac (R/Seurat) and ArchR. Process 10X Genomics scATAC data, perform QC, dimensionality reduction, clustering, peak calling, and motif activity scoring with chromVAR. Use when analyzing single-cell ATAC-seq data.
Infer gene regulatory networks and identify transcription factor regulons from single-cell RNA-seq data using pySCENIC. Discovers co-expression modules with GRNBoost2, prunes by cis-regulatory motif enrichment, and scores regulon activity per cell with AUCell. Use when identifying transcription factor regulons, scoring TF activity in single cells, or finding master regulators of cell identity.
Python population genetics with scikit-allel. Read VCF files, compute allele frequencies, calculate diversity statistics, perform PCA, and run selection scans using GenotypeArray and HaplotypeArray data structures. Use when analyzing population genetics in Python.
Analyze single-cell TCR and BCR data integrated with gene expression using scirpy. Use when working with 10x Genomics VDJ data alongside scRNA-seq or when integrating immune receptor information with cell state analysis.
Quality control for pooled CRISPR screens covering library representation, Gini index, log-skew, replicate Pearson and Spearman concordance, essentialome precision-recall AUC against CEGv2 (Hart 2017), Cas9 cut-toxicity diagnostics, copy-number amplicon detection (Aguirre 2016 / Munoz 2016), bottleneck propagation through plasmid pool, infection, selection, and endpoint stages, MOI verification, and DepMap-style screen-quality scoring. Use when assessing screen quality before hit calling, deciding whether to repeat or rescue a screen, diagnosing low-confidence hits, choosing between MAGeCK / BAGEL2 / Chronos based on quality grade, picking a normalization strategy from QC signatures, or evaluating whether an in-vivo screen retained adequate library complexity.
End-to-end single-cell RNA-seq workflow from 10X Genomics data to annotated cell types. Covers QC, normalization, clustering, marker detection, and cell type annotation. Use when analyzing single-cell RNA-seq data.
Predicts RNA secondary structures using minimum free energy folding and partition function analysis with ViennaRNA (RNAfold, RNAalifold, RNAcofold). Computes base-pair probabilities, centroid structures, and consensus structures from alignments. Use when predicting RNA folding, evaluating structural stability, or comparing structures across homologs.
Detect signatures of natural selection using Fst, Tajima's D, iHS, XP-EHH, and other selection statistics. Calculate population differentiation, test for departures from neutrality, and identify selective sweeps with scikit-allel and vcftools. Use when computing selection signatures like Fst or Tajima's D.
Create and manipulate Seq, MutableSeq, and SeqRecord objects using Biopython. Use when creating sequences from strings, modifying sequence data in-place, or building annotated sequence records.
Build sequence logos from aligned DNA, RNA, or protein motifs using ggseqlogo (R), Logomaker (Python), or WebLogo with explicit bits vs probability encoding, background-frequency correction, custom alphabets, and multi-logo stacking. Use when visualizing motif PWMs (TF binding, splice sites, CRISPR spacers), aligned-position composition, or comparing two motif sets.
Calculate sequence properties like GC content, molecular weight, isoelectric point, and GC skew using Biopython. Use when analyzing sequence composition, computing physical properties, or comparing sequences.
Slice, extract, and concatenate biological sequences using Biopython. Use when extracting subsequences, joining sequences, or manipulating sequence regions by position.
Calculate sequence statistics (N50, length distribution, GC content, summary reports) using Biopython. Use when analyzing sequence datasets, generating QC reports, or comparing assemblies.
Performs 3D shape-based similarity searching using ROCS (OpenEye), USRCAT (ultra-fast), Open3DAlign (RDKit), ESPSim (electrostatic), and ShaEP with explicit handling of Tanimoto-Combo (shape + color), shape vs ECFP4 complementarity, conformer-ensemble searching, alignment optimization, and scaffold hopping. Use when searching for shape-mimicking compounds with different scaffolds, identifying bioisosteric replacements, prospective scaffold hopping, or expanding hit series beyond 2D similarity.
De novo genome assembly from Illumina short reads using SPAdes. Covers bacterial, fungal, and small eukaryotic genome assembly, as well as metagenome and transcriptome assembly modes. Use when assembling genomes from Illumina reads.
Similarity Network Fusion (SNF) for patient stratification using multi-omics data. Integrates multiple data types into a unified patient similarity network. Use when performing patient stratification or integrating multi-omics data into unified similarity networks.
Performs molecular similarity searching using Tanimoto, Tversky, Dice, and cosine coefficients on bit/count fingerprints with explicit choice rules for symmetric vs asymmetric measures, scaffold-hopping vs lead-optimization regimes, activity-cliff diagnosis, and large-library nearest-neighbor methods (BulkTanimoto, Annoy MHFP6, USRCAT). Use when ranking compounds by structural resemblance to a query, clustering libraries, finding analogs, or diagnosing activity cliffs.
Process and analyze single-cell ATAC-seq data with Signac, ArchR, SnapATAC2, or Cell Ranger ATAC. Use when handling 10X scATAC or 10X Multiome (paired RNA+ATAC) data, performing per-cell QC, choosing between ArchR/Signac/SnapATAC2 ecosystems, building per-cluster consensus peaksets, integrating with paired scRNA-seq, doublet detection (AMULET vs ArchR vs scDblFinder), or running pseudobulk differential accessibility per cluster.
Analyzes alternative splicing at single-cell resolution. The first decision is library chemistry — 10X 3' is fundamentally limited (RT primes from poly-A, R2 falls in 3' UTR, <0.1 junction read per cell per AS event). Plate-based full-length methods (Smart-seq3, FLASH-seq, VASA-seq, STORM-seq) and single-cell long-read (MAS-Iso-seq, scISOr-Seq2) are the chemistries that give per-cell isoform structure. Tools include MARVEL (R, Smart-seq integrated), BRIE2 (Bayesian PSI with regulatory features and ELBO_gain test), scQuint (junction-cluster, plate-based; not for 10X), SpliZ (annotation-free Z-score), Psix (graph-smoothness regulated AS), and Sierra (alternative polyadenylation, often confused with AS). Use when analyzing isoform usage in scRNA-seq, identifying cell-type-specific splicing, or determining whether scRNA-seq chemistry supports splicing analysis at all.
End-to-end small RNA-seq analysis from FASTQ to differential miRNA expression. Use when analyzing miRNA, piRNA, or other small RNA sequencing data.
Preprocess small RNA sequencing data with adapter trimming and size selection optimized for miRNA, piRNA, and other small RNAs. Use when preparing small RNA-seq reads for downstream quantification or discovery analysis.
Build reproducible bioinformatics pipelines with Snakemake using rules, wildcards, and automatic dependency resolution. Use when creating Python-based workflows, automating multi-step analyses with make-like dependency tracking, or running pipelines on HPC clusters with SLURM.
Claude Skills — questions
Answers built from the skills we actually parsed.