Generate database-agnostic Wheels migrations for creating tables, altering schemas, and managing database changes. Use when creating or modifying database schema, adding tables, columns, indexes, or foreign keys. Prevents database-specific SQL and ensures cross-database compatibility.

Crisis communication and rapid response workflows for journalists and communications professionals. Use when covering breaking news events, managing organizational communications during crises, coordinating rapid fact-checking efforts, or developing crisis response plans. Essential for newsrooms, PR teams, and anyone who needs to communicate accurately under time pressure.

Remote JavaScript console access and debugging on mobile devices. Use when debugging web pages on phones/tablets, accessing console errors without desktop DevTools, testing responsive designs on real devices, or diagnosing mobile-specific issues. Covers Eruda, vConsole, Chrome/Safari remote debugging, and cloud testing platforms.

Generate CLAUDE.md project memory files that transfer institutional knowledge, not obvious information. Use when setting up new journalism projects, onboarding collaborators, or documenting project-specific quirks. Includes templates for editorial tools, event websites, publications, research projects, content pipelines, and digital archives.

Enforce a disciplined bug-fixing workflow that prevents regression and parallelizes fix attempts.

Web page archiving and retrieval from cached/deleted sources. Use when accessing unavailable pages, preserving web content, creating legal evidence archives, or building redundant archival workflows. Covers Wayback Machine, Archive.today, ArchiveBox, and evidence preservation tools.

dependency-handling

test

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

Amazon listing builder and optimizer for sellers. Two modes: (A) Create — build keyword-optimized listings from scratch using keyword lists + product characteristics + AI copywriting, (B) Optimize — audit existing listings, find keyword gaps, score across 8 dimensions, and rewrite with missing keywords. Integrates with amazon-keyword-research for keyword input. Works on 12 Amazon marketplaces. No API key required. Use when: (1) creating a new Amazon listing from keywords, (2) auditing an existing listing for SEO and conversion, (3) checking keyword coverage in title/bullets/description, (4) generating listing copy with target keywords and tone, (5) comparing listings against competitors, (6) preparing a listing for launch or relaunch.

Mandatory filtering of degenerate and uninformative data points before statistical tests. Covers single-sequence alignments, empty files, constant-value features, zero-variance inputs, and all-NaN columns. For NaN-aware correlation computation, see the nan-safe-correlation skill. For broader statistical testing guidance, see the statistical-analysis skill.

Per-feature NaN-safe Spearman/Pearson correlation computation. Use when computing correlations across many features (genes, proteins, variants) with missing values. Covers why bulk matrix shortcuts fail with missing data, correct pairwise deletion, degenerate input filtering, and performance optimization for large datasets. For general statistical test selection use statistical-analysis; for model explainability use shap-model-explainability.

>-

Statistical modeling library for Python. Use for regression (OLS, WLS, GLM), discrete outcomes (Logit, Poisson, NegBin), time series (ARIMA, SARIMAX, VAR), and rigorous inference with detailed diagnostics, coefficient tables, and hypothesis tests. For ML-focused classification/regression use scikit-learn; for guided test selection use statistical-analysis.

Python bridge to ImageJ2/Fiji enabling macro execution, plugin calls (Bio-Formats, TrackMate, Analyze Particles), bidirectional NumPy↔ImagePlus/ImgLib2 data exchange, and ImageJ Ops from Python. Use for automating Fiji-specific workflows headlessly from Python scripts. Use scikit-image instead for pure Python pipelines that do not require Fiji plugins; use napari for interactive visualization.

Guide for choosing and creating scientific visualizations for publications and presentations. Covers selecting chart types for different data structures, color theory for accessibility and print, figure composition, journal-specific formatting requirements (Nature, Cell, ACS), and common pitfalls that undermine scientific credibility. Consult this guide when deciding how to visualize your data or preparing figures for submission.

Guide for annotating statistical significance (p-value asterisk notation) on comparison plots. Covers standard notation conventions (ns, *, **, ***, ****), when to annotate, matplotlib bracket+asterisk implementation, and integration with seaborn box/violin/bar plots. Use when generating publication-ready comparison figures that need significance markers to support statistical claims made in the analysis.

Gene regulatory network inference from expression data using GRNBoost2 (gradient boosting) or GENIE3 (Random Forest). Load expression matrix, optionally filter by transcription factors, infer TF-target-importance links, filter and save network. Dask-parallelized for single-cell scale. Core component of the SCENIC pipeline.

Query uniformly processed RNA-seq gene expression profiles, tissue-specific expression patterns, and co-expression networks from the ARCHS4 database REST API. Retrieve z-score normalized expression across 1M+ human and mouse samples, find co-expressed genes, search samples by metadata, and download HDF5 expression matrices. For variant-level population genetics use gnomad-database; for pathway enrichment from gene lists use gget-genomic-databases (Enrichr).

Toolkit for genomic interval operations on BED, BAM, GFF, VCF files. Find overlapping regions, merge adjacent intervals, calculate coverage depth, extract FASTA sequences, find nearest features, and manipulate interval coordinates. Essential for ChIP-seq peak annotation, target region filtering, and genome arithmetic. Use tabix instead for indexed single-region queries; use deeptools for normalized bigWig coverage.

Automated cell type annotation for scRNA-seq data using pre-trained logistic regression models. CellTypist ships 45+ models covering immune cells, gut, lung, brain, fetal tissues, and cancer microenvironments. Inputs a normalized AnnData; outputs per-cell predicted labels, majority-vote cluster labels, and confidence scores. Use when you want fast, reproducible, reference-model-backed annotation without manual marker inspection.

Detect somatic copy number variants (CNVs) from WES, WGS, or targeted sequencing BAM files with CNVkit v0.9.x. Pipeline: calculate bin-level coverage in target/antitarget regions, normalize against a reference, segment copy ratios with CBS or HMM, call amplifications and deletions, generate scatter/diagram plots, estimate tumor purity and ploidy, and export to VCF/SEG. Both CLI and Python API (cnvlib) shown. Use GATK CNV instead for deep WGS with population-scale controls; use CNVkit for targeted or exome sequencing where antitarget bins are critical.

NGS analysis CLI toolkit for ChIP-seq, RNA-seq, ATAC-seq. BAM→bigWig conversion with normalization (RPGC, CPM, RPKM), sample correlation/PCA, heatmaps and profile plots around genomic features, enrichment fingerprints. For alignment use STAR/BWA; for peak calling use MACS2.

Differential expression analysis for bulk RNA-seq using R/Bioconductor DESeq2. Negative binomial GLM with empirical Bayes shrinkage, Wald and LRT tests, multi-factor designs, interaction terms, Salmon tximeta import, apeglm LFC shrinkage, MA/volcano/heatmap visualization. The R gold standard for DE analysis with native Bioconductor integration. Use pydeseq2-differential-expression for Python-based pipelines; use edgeR for TMM normalization.

European Nucleotide Archive (ENA) REST API access for genomic sequences, raw reads, assemblies, and annotations. Portal API search with query syntax, Browser API retrieval (XML/FASTA/EMBL), file reports for FASTQ/BAM download URLs, taxonomy queries, cross-references. For multi-database Python queries prefer bioservices; for NCBI-specific queries use pubmed-database or Biopython Entrez.

Query Ensembl REST API for gene/transcript/variant annotations across 300+ species. Retrieve gene info by symbol/ID, sequence, cross-references (HGNC, RefSeq, UniProt), variants, regulatory features, comparative genomics. For bulk local access use pyensembl; for pathway lookups use kegg-database or reactome-database.

ETE Toolkit (ETE3) is a Python environment for phylogenetic tree analysis, manipulation, and visualization. Parse Newick/NHX/PhyloXML trees, traverse and annotate nodes, render publication-quality figures with TreeStyle/NodeStyle, integrate NCBI taxonomy for taxon-aware operations, and run PhyloTree workflows for comparative genomics. Use for building species trees, gene family evolution analysis, and annotated tree figures.

All-in-one FASTQ quality control and adapter trimming tool. Automatically detects and removes Illumina adapters, filters low-quality reads, corrects paired-end overlaps, and generates HTML+JSON QC reports in a single fast pass. 3-10× faster than Trim Galore/Trimmomatic. Use as the first step before STAR, BWA-MEM2, or Salmon alignment in any NGS pipeline.

Query NCBI Gene via E-utilities for curated gene records across 1M+ taxa. Retrieve official gene symbols, aliases, RefSeq accessions, summary descriptions, genomic coordinates, GO annotations, and interaction data. Use for gene ID resolution, cross-species queries, and gene function summaries. For sequence retrieval use Ensembl; for expression data use geo-database.

Query gnomAD v4 population variant frequencies via GraphQL API. Retrieve allele counts and frequencies stratified by ancestry group (AFR, AMR, EAS, NFE, SAS, FIN, ASJ, MID), gene-level constraint metrics (pLI, LOEUF, missense z-score), and read depth coverage. Identify variants with low population frequency or under evolutionary constraint. For clinical pathogenicity classifications use clinvar-database; for GWAS associations use gwas-database.

Gene set enrichment analysis (GSEA) and over-representation analysis (ORA) for RNA-seq and proteomics data. Wraps Enrichr API for ORA against MSigDB, KEGG, GO, and 200+ gene set databases; implements preranked GSEA for ranked gene lists from differential expression. Outputs enrichment tables and GSEA running-score plots. Use after DESeq2 or edgeR for pathway-level interpretation of differential expression results.

Query the JASPAR 2024 TF binding profile database via REST API and pyJASPAR. Retrieve position frequency matrices (PFMs) and position weight matrices (PWMs) by TF name, JASPAR ID, species, or structural class. Scan DNA sequences for transcription factor binding sites (TFBS). Browse profiles by taxon (Homo sapiens, Mus musculus) or TF family (bHLH, zinc finger). Use for motif enrichment input, TFBS scanning, and regulatory sequence analysis. For ChIP-seq peak-based motif discovery use homer-motif-analysis; for regulatory variant scoring use regulomedb-database.