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.
Corrects the gene-independent copy-number artifact in CRISPR-Cas9 screens (Aguirre 2016 / Munoz 2016 Cancer Discov) where amplified loci appear essential from DNA-damage burden of simultaneous cuts. Covers the p53-dependent G2-arrest mechanism, CRISPRcleanR (Iorio 2018) unsupervised pre-hoc correction, CERES (Meyers 2017) joint CN + gene-effect model, Chronos (Dempster 2021) DepMap-standard population-dynamics + CN model with lowest residual bias, the decision tree by data availability, the Spearman LFC-vs-CN diagnostic, focal-amplification examples (ERBB2 in HER2+, MYC in colorectal, FGFR1 in head and neck), and CRISPRi/a alternatives that bypass the artifact. Use when screening cancer cell lines, diagnosing essentiality at amplified loci, choosing CRISPRcleanR / CERES / Chronos, deciding whether CN correction is needed before MAGeCK / BAGEL2 / drugZ, or switching from Cas9 to CRISPRi.
Build tissue and condition-specific metabolic models using GIMME, iMAT, and INIT algorithms with expression data constraints. Create models that reflect cell-type specific metabolism. Use when building tissue-specific metabolic models or integrating transcriptomics with FBA.
Detect sample contamination and cross-species reads using FastQ Screen. Screen reads against multiple reference genomes to identify bacterial, viral, adapter, or sample swap contamination. Use when suspecting cross-contamination or working with samples prone to microbial contamination.
Quality control and exploration of RNA-seq count matrices before differential expression. Check for outliers, batch effects, and sample relationships. Use when assessing count matrix quality before DE analysis.
Normalize read-depth copy-ratio profiles and segment them into copy-number regions using circular binary segmentation (CBS, DNAcopy), hidden Markov models, HaarSeg, and fused-lasso methods. Covers GC-content, mappability, and replication-timing (wave-artifact) bias correction, panel-of-normals/PCA denoising, diploid-baseline centering, and algorithm selection by sequencing depth and event size. Use when choosing a segmentation algorithm, correcting depth bias, diagnosing oversegmentation or a mis-centered baseline, tuning CBS or HMM parameters, or understanding why a downstream CNV caller produced fragmented or shifted segments.
Load gene expression count matrices from various formats including CSV, TSV, featureCounts, Salmon, kallisto, and 10X. Use when importing quantification results for downstream analysis.
Calculate read depth and coverage across genomic intervals using bedtools genomecov and coverage. Generate bedGraph files, compute per-base depth, and summarize coverage statistics. Use when assessing sequencing depth, creating coverage tracks, or evaluating target capture efficiency.
Designs covalent inhibitors and warheads targeting cysteine (most common, 98% of covalent drugs), lysine, serine, threonine, tyrosine, and aspartate residues, with explicit handling of warhead reactivity (acrylamide, chloroacetamide, vinyl sulfone, sulfonyl fluoride, fluorosulfate, aldehyde, boronate, nitrile), reversibility (kinact/Ki, t_residence), glutathione (GSH) stability, intrinsic reactivity assays, and covalent docking (DOCKovalent, GOLD, HCovDock). Use when designing covalent inhibitors for targeted covalent inhibition (TCI), KRAS G12C-style approaches, or rationalizing covalent SAR.
Quantifies CRISPR editing outcomes with CRISPResso2 (Clement 2019 Nat Biotechnol) across Cas9-nuclease (indels, HDR), CBE and ABE base editors (target conversion + bystander), and prime editor (pegRNA-templated) modes. Covers single-amplicon (CRISPResso), multi-sample batch (CRISPRessoBatch), pooled-amplicon (CRISPRessoPooled), WGS off-target (CRISPRessoWGS), and sample-comparison (CRISPRessoCompare) workflows; quantification-window math that controls what is called edited; substitution-vs-indel diagnostic to distinguish BE from Cas9 contamination; MMEJ deletion pattern interpretation; allele-frequency tables; and failure modes from amplicon misalignment or contamination. Use when quantifying editing from amplicon sequencing, choosing CRISPResso mode by design, distinguishing intended edits from bystanders and indel byproducts, debugging low-alignment runs, or generating publication-grade editing reports.
End-to-end pooled and single-cell CRISPR screen analysis from FASTQ to hit genes. Orchestrates library design QC, guide counting, six-stage screen QC (plasmid Gini, replicate Pearson, CEGv2 PR-AUC, copy-number artifact), method-appropriate hit calling across MAGeCK RRA/MLE, BAGEL2, drugZ, JACKS, and Chronos, cancer-cell-line copy-number correction (CRISPRcleanR / Chronos), batch correction for multi-batch screens, and the specialized branches for combinatorial paralog screens, single-cell Perturb-seq, base-editor variant-function screens, prime-editor screens, and in vivo bottleneck-aware screens. Use when analyzing any pooled CRISPR screen end-to-end, choosing the correct hit-calling method by experimental design, integrating copy-number correction into the pipeline, or branching the workflow for single-cell, combinatorial, base-editor, prime-editor, or in vivo variants.
End-to-end CRISPR experiment design from target selection to delivery-ready constructs. Covers guide RNA design, off-target assessment, and specialized editing strategies including knockouts, base editing, and HDR knockins. Use when designing complete CRISPR editing experiments for gene knockout, correction, or tagging.
Detect single-nucleotide crosslink (CL) sites in CLIP-seq data using truncation patterns (iCLIP/eCLIP CITS), crosslink-induced mutations (HITS-CLIP CIMS deletions, PAR-CLIP T-to-C), or HMM/kernel-density methods (PureCLIP, PARalyzer, CTK). Use when single-nucleotide resolution is required for motif registration (mCross), allele-specific binding (BEAPR), variant-effect prediction, or comparing crosslink chemistry across CLIP variants.
Analyzes CUT&RUN (Skene Henikoff 2017) and CUT&Tag (Kaya-Okur 2019) chromatin profiling data. Handles SEACR vs MACS2 peak calling (with the btaf375 2025 benchmark guidance), pA-MNase vs pA-Tn5 vs pAG-Tn5 chimera differences, E. coli spike-in carryover normalization, IgG-only control logic (no input), characteristic fragment-size signatures (25-75 bp for CUT&Tag), and lower depth requirements (5M reads typical vs 25M for ChIP). Use when calling peaks from CUT&RUN/CUT&Tag, scaling by E. coli spike-in carryover, choosing SEACR norm mode, or comparing CUT&RUN/Tag results to traditional ChIP.
Detects somatic mutations in circulating tumor DNA using variant callers optimized for low allele fractions with UMI-based error suppression. Reliably detects mutations at VAF above 0.5 percent using consensus-based approaches. Use when identifying tumor mutations from plasma DNA or tracking specific variants.
Create portable, standards-based bioinformatics pipelines with Common Workflow Language (CWL). Use when building workflows that need maximum portability across execution platforms, sharing pipelines with collaborators using different systems, or contributing to community workflow registries.
Comprehensive quality control for flow cytometry and CyTOF data. Covers flow rate stability, signal drift, margin events, dead cell exclusion, and batch QC. Use when assessing acquisition quality or identifying problematic samples before analysis.
End-to-end flow cytometry workflow from FCS files to differential analysis. Orchestrates compensation, transformation, gating/clustering, and statistical testing with CATALYST/diffcyt. Use when processing flow or mass cytometry data end-to-end.
Preprocessing and harmonization of multi-omics data before integration. Covers normalization, batch correction, feature alignment, and missing value handling across data types. Use when preparing multi-omics datasets for integration analysis.
Load and parse mass spectrometry data formats including mzML, mzXML, and quantification tool outputs like MaxQuant proteinGroups.txt. Use when starting a proteomics analysis with raw or processed MS data. Handles contaminant filtering and missing value assessment.
Read, write, and create single-cell data objects using Seurat (R) and Scanpy (Python). Use for loading 10X Genomics data, importing/exporting h5ad and RDS files, creating Seurat objects and AnnData objects, and converting between formats. Use when loading, saving, or converting single-cell data formats.
Load and preprocess imaging mass cytometry (IMC) and MIBI data. Covers MCD/TIFF handling, hot pixel removal, and image normalization. Use when starting IMC analysis from raw MCD files or preparing images for segmentation.
Resolves rsIDs, navigates RsMergeArch/SNPHistory merge chains, and converts between rsID, SPDI, HGVS, and VCF representations using the dbSNP Build 156 JSON architecture. Use when normalizing variant identifiers, joining variant databases by cluster ID, or tracking deprecated rsIDs through historical merges.
Extract, filter, annotate, and export differential expression results from DESeq2 or edgeR. Use for identifying significant genes, applying multiple testing corrections, adding gene annotations, and preparing results for downstream analysis. Use when filtering and exporting DE analysis results.
Visualize differential expression results using DESeq2/edgeR built-in functions. Covers plotMA, plotDispEsts, plotCounts, plotBCV, sample distance heatmaps, and p-value histograms. Use when visualizing differential expression results.
Sequence-based deep learning for ATAC-seq using chromBPNet, BPNet, scBasset, or EnFormer. Use when correcting Tn5 bias with neural networks beyond k-mer models, predicting per-base accessibility profiles, scoring in silico variant effects at GWAS or rare-variant SNPs, discovering motifs via DeepLIFT/TF-MoDISco from a trained model, or generating cell-type-specific accessibility predictions for unobserved cell states.
Deep learning-based variant calling with Google DeepVariant. Provides high accuracy for germline SNPs and indels from Illumina, PacBio, and ONT data. Use when calling variants with DeepVariant deep learning caller or when highest germline calling accuracy is required.
Perform differential expression analysis using DESeq2 in R/Bioconductor. Use for analyzing RNA-seq count data, creating DESeqDataSet objects, running the DESeq workflow, and extracting results with log fold change shrinkage. Use when performing DE analysis with DESeq2.
Data-independent acquisition (DIA) proteomics analysis with DIA-NN and other tools. Use when analyzing DIA mass spectrometry data with library-free or library-based workflows for deep proteome profiling.
Differential abundance testing for microbiome data using compositionally-aware methods like ALDEx2, ANCOM-BC2, and MaAsLin2. Use when identifying taxa that differ between experimental groups while accounting for the compositional nature of microbiome data.
Identify differentially accessible chromatin regions across conditions using DiffBind, csaw, DESeq2, or edgeR. Use when comparing ATAC-seq accessibility between treatment groups, choosing between consensus-peak vs sliding-window approaches, picking the correct normalization (full library vs reads-in-peaks), correcting batch with SVA/RUVseq, or interpreting log2FC and FDR thresholds in a chromatin context.
Differential abundance and state analysis for cytometry data. Compare cell populations between conditions using statistical methods. Use when testing for significant changes in cell frequencies or marker expression between groups.
Use when source material must be transformed into a compact, evidence-aware model for learning, decisions, or an Obsidian concept note.
Use when property-service operations need an AI plus ontology plus DMAIC design for work orders, dispatch, quotes, evidence, CTQ metrics, and control dashboards.
Use when a goal must be converted into a repeatable behavior, cue, SOP, review cadence, and identity-aligned reinforcement.
Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that require bounded multi-agent command.
Use when a long-running agent task needs context budgeting, checkpointing, compaction, retrieval, or capability-based model routing.
Use when a defined problem needs diverse ideas, cross-domain combinations, and cheap experiments instead of a single untested answer.
Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable state, and verified write-back.
Use when a personal or team operating system needs a bounded redesign using Four-C, closed-loop controls, 70/30 allocation, 3B creativity, experiments, and prediction-error learning.
Use when a workflow has explicit data dependencies, independently executable branches, typed joins, or node-local recovery needs that justify a bounded static dependency graph.
Use when a decision-relevant question needs multi-source search, claim-level citations, contradiction handling, uncertainty, or a durable wiki handoff.
Use when an Obsidian knowledge system needs classification, deduplication, retrieval, synchronization, debt queues, or governed Agent/Wiki promotion.
Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, scheduling, evaluation, recovery, or maintenance.
Use when planning or closing a daily knowledge-compounding cycle across input, cognition, wiki, behavior, creativity, output, and feedback.
Use when projects or tasks need explicit state, WIP control, ownership, definitions of done, blocker handling, and verified closure.
Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal agent, or metric-driven research cycle.
Use when a completed work session should yield durable concepts, corrections, decisions, reusable patterns, and a traceable next action.
Use when a startup needs an evidence-weighted health check, investor lens, runway diagnosis, top constraint, or cheapest next validation test.
Use when a PDF, URL, transcript, clipping, or raw note must become source-grounded, linked, governed knowledge in an Obsidian vault.
Use when an agent is about to claim completion, correctness, safety, publication, deployment, or any consequential external fact.
Use when an Obsidian wiki needs a reproducible health audit for structure, provenance, links, understanding, lifecycle, and promotion readiness.
Fetch and render web pages using the Servo browser engine — a single binary with JS execution, CSS layout, screenshots, and content extraction. Use when a URL returns empty or incomplete content with plain HTTP fetch, when you need a screenshot without GPU, or when you need to run JavaScript in a page context. No browser download required.
Query visual scientific figure references, show candidates for human preference selection, export selected reference bundles, and guide plotting agents from human-selected visual examples to code action.
Claude Skills — questions
Answers built from the skills we actually parsed.