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.

Query disease-gene-phenotype associations, entity details, and cross-species orthology from the Monarch Initiative knowledge graph REST API. Retrieve MONDO disease-to-gene and disease-to-phenotype mappings, HP phenotype profiles, and cross-species phenotype comparisons. Use for rare disease gene prioritization, phenotype-based candidate gene ranking, and building disease-phenotype networks. For GWAS associations use gwas-database; for clinical pathogenicity use clinvar-database.

Annotate prokaryotic genome assemblies (bacteria, archaea, viruses) with Prokka's BLAST/HMM-based pipeline. Identifies CDS, rRNA, tRNA, tmRNA, and signal peptides against Pfam, TIGRFAMs, and RefSeq databases. Produces GFF3, GenBank, protein FASTA, and TSV outputs. Use PGAP instead when submitting to NCBI GenBank; use Bakta for faster annotation with NCBI-compatible outputs on modern assemblies.

Bulk RNA-seq differential expression analysis with PyDESeq2. Load count matrices, normalize, fit negative binomial models, Wald test with BH-FDR correction, LFC shrinkage, volcano/MA plots. Use for two-group comparisons, multi-factor designs with batch correction, and multiple contrast testing.

Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences. Region queries, coverage/pileup analysis, variant filtering, read group extraction. Python wrapper for htslib with samtools/bcftools CLI access. For alignment pipelines use STAR/BWA; for variant calling use GATK/DeepVariant.

Query the EBI QuickGO REST API for Gene Ontology terms and protein GO annotations. Fetch GO term metadata by ID, search terms by keyword, retrieve ancestor/descendant hierarchies, and download GO annotations filtered by taxon ID, evidence code, and GO aspect. Use for GO term resolution, ontology traversal, and annotation-set retrieval before enrichment analysis. For enrichment analysis itself use gseapy-gene-enrichment; for protein function annotations use uniprot-protein-database.

Query the ReMap 2022 TF ChIP-seq binding peak database via REST API and BED file downloads. Retrieve all TF binding peaks overlapping a genomic region (chr:start-end), find TF peaks near a gene by name, list TFs available for a species, filter peaks by regulatory biotype (promoter, enhancer), and download peak BED files for a TF-cell type pair. Use for TF co-occupancy analysis, regulatory region annotation, and building TF binding atlases. For JASPAR motif matrices use jaspar-database; for ENCODE regulatory tracks use encode-database.

Command-line toolkit for SAM/BAM/CRAM alignment file manipulation. Sort, index, convert, filter, and QC sequencing alignments. Core commands: view (filter/convert), sort, index, flagstat, stats, depth, markdup, merge. Required for all NGS pipelines between alignment and variant calling or peak calling. Use pysam for Python-native BAM access; use deeptools for normalized coverage tracks.

>-

Guide to mandatory quality filtering of raw/unfiltered VCF files before computing summary statistics such as Ts/Tv ratio, variant counts, or allele frequency distributions. Covers detection of raw VCFs via FILTER column and QUAL distribution inspection, QUAL-based filtering with bcftools, interpretation of Ts/Tv ratios, and when NOT to filter. Essential reading before any variant-level QC task. Cross-references: bcftools-variant-manipulation for advanced filtering expressions, gatk-variant-calling for upstream caller configuration, samtools-bam-processing for alignment QC prior to variant calling.

Parse and query the Human Metabolome Database (HMDB) local XML for metabolite information, chemical properties, biological context, disease associations, spectral data, and cross-database mapping. No public REST API — primary access via downloaded XML (~6 GB). For drug-focused queries use drugbank-database-access; for live compound lookups use pubchem-compound-search.

Mass spectrometry spectral matching and metabolite identification with matchms. Use for importing spectra (mzML, MGF, MSP, JSON), filtering/normalizing peaks, computing spectral similarity (cosine, modified cosine, fingerprint), building reproducible processing pipelines, and identifying unknown metabolites from spectral libraries. For full LC-MS/MS proteomics pipelines, use pyopenms instead.

MaxQuant + Perseus proteomics pipeline: configure and run MaxQuant for label-free quantification (LFQ) and SILAC; parse proteinGroups.txt in Python; filter contaminants/reverse decoys; log2-transform and median-normalize LFQ intensities; impute MNAR missing values; t-test with FDR correction; volcano plot; GO/pathway enrichment. Use Proteome Discoverer for Thermo instrument-native processing; FragPipe/MSFragger for GPU-accelerated database search.

Mass spectrometry data processing with PyOpenMS. Use for LC-MS/MS proteomics and metabolomics workflows — mzML/mzXML file I/O, signal processing (smoothing, peak picking, centroiding), feature detection and linking across samples, peptide/protein identification with FDR control, untargeted metabolomics pipelines. For simple spectral matching and metabolite ID, use matchms instead.

Graph and network analysis toolkit: create, manipulate, and analyze complex networks. Four graph types (directed, undirected, multi-edge), centrality measures, shortest paths, community detection, graph generators, I/O (GraphML, GML, edge list, pandas, NumPy), visualization with matplotlib. For large-scale graphs (100K+ nodes) use igraph or graph-tool; for graph neural networks use PyG.

NeuroKit2 is a Python toolkit for neurophysiological signal processing. Process ECG (heart rate, HRV, R-peak detection), EEG (complexity, power spectral density), EMG (muscle activation onset), EDA/GSR (skin conductance, SCR decomposition), PPG (photoplethysmography), and RSP (respiration) signals. Simulate synthetic signals for testing. Alternatives: BioSPPy (older, less maintained), MNE (EEG/MEG specialist), heartpy (ECG only), scipy.signal (raw DSP without biosignal abstraction).

pymoo is a Python framework for single- and multi-objective optimization using evolutionary algorithms. Define problems as vectorized objective functions and constraints, then solve with NSGA-II, NSGA-III, MOEA/D, genetic algorithms, or differential evolution. Analyze Pareto fronts, visualize trade-off surfaces, and customize operators and callbacks. Ideal for engineering design, hyperparameter search, process optimization, and any problem with multiple conflicting objectives. Alternatives: scipy.optimize (single-objective, gradient-based), platypus (fewer algorithms), jMetalPy (Java-based, more algorithms).

Unified Python framework for extracellular electrophysiology. Load recordings from 20+ formats (SpikeGLX, OpenEphys, NWB, Intan, Maxwell, Blackrock), preprocess signals, run 10+ spike sorters (Kilosort4, SpykingCircus2, Tridesclous, MountainSort5) with a single API, compute quality metrics (SNR, ISI violations, firing rate, amplitude cutoff), compare sorter outputs, and export to NWB or Phy. Use for format-agnostic and multi-sorter workflows. For a Neuropixels-specific Kilosort4 pipeline with PSTH and population decoding, use neuropixels-analysis instead.

Use HuggingFace Transformers with biomedical language models for scientific NLP tasks. Load BioBERT, PubMedBERT, BioGPT, and BioMedLM for named entity recognition (genes, diseases, chemicals), relation extraction, question answering on biomedical literature, text classification, and abstract summarization. Covers model loading, tokenization of biomedical text, inference pipelines, and fine-tuning on domain-specific datasets. Alternatives: spaCy with en_core_sci_lg (rule-based NER), Stanza (Stanford NLP, biomedical models), NLTK (classical NLP).

General scientific figure quality checklist for generated plots. Covers visual inspection for overlapping labels, clipped text, missing axes/legends, empty plot areas, overcrowded data, and resolution/format best practices across journals.

Figure and image preparation guide for The Lancet. Covers resolution (300+ DPI at 120% size), file formats (PowerPoint, Word, SVG preferred), column widths (75/154 mm), Times New Roman font, and Lancet in-house redraw policy.

Systematic strategies for searching, retrieving, and analyzing scientific literature across PubMed, arXiv, Google Scholar, and AI-assisted tools. Covers the PICO framework for clinical question formulation, three-tiered search strategy (database-specific, AI-assisted, content extraction), PubMed field tags and MeSH vocabulary, boolean query construction, and full-text extraction workflows. Consult this guide when planning a literature search, constructing database queries, or deciding which search tier to use for a given research question.

Scientific manuscript writing knowledge: IMRAD structure, citation styles (APA/AMA/Vancouver/IEEE), figures and tables best practices, reporting guidelines (CONSORT/STROBE/PRISMA/ARRIVE), writing principles (clarity/conciseness/accuracy), field-specific terminology, venue-specific style adaptation. For LaTeX report formatting see companion assets.

Molecular docking with AutoDock Vina via Python API. Receptor/ligand preparation (Meeko + RDKit), grid box setup, docking execution, pose extraction, binding energy analysis, and batch virtual screening. Use for protein-ligand docking and hit identification.

Cross-reference chemical compound identifiers across 50+ databases (ChEMBL, DrugBank, PubChem, ChEBI, PDB, KEGG) using the UniChem REST API. Resolve InChIKeys to database-specific IDs, find all sources for a compound, discover related compounds by structural connectivity, and batch-translate compound lists between naming systems. No authentication required.

Query BRENDA Enzyme Database for kinetic parameters (Km, Vmax, kcat, Ki), enzyme classifications, substrate specificity, inhibitors, cofactors, and organism-specific enzyme data via SOAP/REST API. 80,000+ enzyme entries, 7M+ kinetic values. Requires free academic registration. For metabolic pathway modeling use cobrapy-metabolic-modeling; for metabolite structures use hmdb-database.

Build, read, validate, and modify SBML biological network models using libSBML Python API. Supports all SBML Levels (1–3), reactions with kinetic laws, species/compartments, rules (assignment/rate/algebraic), the FBC extension for flux balance analysis models, and model conversion utilities. Integrates with COBRApy, Tellurium/RoadRunner, and COPASI for simulation. Use when programmatically constructing ODE-based or constraint-based metabolic/signaling models in the standard SBML format.

Multi-Omics Factor Analysis v2 (MOFA+) with mofapy2. Jointly decompose multiple omics layers (scRNA-seq, ATAC-seq, proteomics, methylation) into latent factors that capture major sources of biological variation. Supports multi-group designs (patients, conditions). Pipeline: prepare AnnData views → create MOFA object → train → inspect variance explained → correlate factors with metadata → visualize and cluster → enrichment of top loadings.

Multi-modal single-cell analysis with muon and MuData. Joint RNA+ATAC (10x Multiome), CITE-seq (RNA+protein), and other multi-omics combinations. MuData container holds modality-specific AnnData objects with shared obs. Weighted Nearest Neighbor (WNN) graph for joint embedding, per-modality preprocessing, cross-modal factor analysis with MOFA. Use scanpy-scrna-seq for single-modality RNA analysis; use muon when combining two or more omics modalities from the same cells.

Comprehensive decision guide for analyzing omics data (transcriptomics, proteomics) using a three-tiered approach: validated pipelines first, standard workflows second, custom analysis last. Covers quality control strategies, normalization method selection, missing value imputation, statistical test selection based on data properties, and result visualization. Consult this guide when planning a bulk RNA-seq or proteomics differential analysis to choose the right tools, tests, and preprocessing steps.

Query Reactome pathway database via REST API. Pathway queries, entity retrieval, keyword search, gene list enrichment analysis, pathway hierarchy, cross-references. Content Service (pathway data) and Analysis Service (enrichment). For Python wrapper use reactome2py. For KEGG pathways use kegg-database; for protein interactions use string-database-ppi.

Query STRING REST API for protein-protein interactions (59M proteins, 20B interactions, 5000+ species). Retrieve interaction networks, perform GO/KEGG enrichment analysis, discover interaction partners, test PPI enrichment significance, generate network visualizations, and analyze protein homology for systems biology and pathway analysis.

Amazon brand protection toolkit. Detect hijackers, counterfeits, and unauthorized sellers. Includes MAP violation monitoring, trademark abuse detection, complaint templates for Brand Registry, and test buy evidence collection guides. No API key required.

Creates visual concepts for album artwork and generates AI art prompts. Use during planning for concept discussion, or after all tracks are Final for actual artwork generation.

Shows a structured progress dashboard for an album with percentage complete per phase, blocking items, and status breakdown. Use for a quick visual overview of album progress.

Generates platform-specific social media copy from album themes, track concepts, and lyrics. Use when promo/ templates need to be populated before release.

Scans lyrics for pronunciation risks and prevents Suno mispronunciations. Use when writing lyrics with proper nouns, technical terms, homographs, or non-English words.

Runs automated tests to validate plugin integrity across 14 categories. Use before creating PRs, after making changes to skills or templates, or to verify plugin health.

Use when running claudikins-kernel:verify, checking implementation quality, deciding pass/fail verdicts, or enforcing cross-command gates — requires actual evidence of code working, not just passing tests

Build a reproducible, cached environment overlay for ephemeral containers using a Dockerfile-like spec.

>-

Write effective instructions for Claude: project instructions, standalone prompts, and skill content. Use when users need help writing prompts, setting up project instructions, choosing between instruction formats, or improving how they communicate with Claude. Covers writing principles, model-aware calibration, and format selection. For building and testing complete skills, use skill-creator instead.

Systematic web application penetration testing methodology. Apply when performing authorized security assessments, bug bounty hunting, or pre-deployment security validation. Covers recon, scanning, exploitation, and reporting.

Build end-to-end tests with Playwright, Feature Object pattern, cross-browser testing, and visual regression. Apply when testing critical user flows, automating regression testing, or validating integrations.

Design database schemas, create migrations, manage data relationships, and sync with production using Prisma. Apply when designing database schemas, creating migrations, or defining data models.

Extract structured data from construction PDFs. Convert specifications, BOMs, schedules, and reports from PDF to Excel/CSV/JSON. Use OCR for scanned documents and pdfplumber for native PDFs.

Extract structured data from construction specifications. Parse CSI sections, requirements, submittals, and product data from spec documents.

Build automated BIM validation pipelines for IFC/Revit data. Continuous validation against IDS, LOD requirements, COBie, and project-specific BEP standards.

Implement semantic vector search for construction data. Build AI-powered search using embeddings and vector databases (Qdrant, ChromaDB) for intelligent querying of specifications, standards, and project documents.

Build multi-agent AI systems for construction estimation. Use CrewAI/LangGraph to orchestrate specialized agents: QTO agent, pricing agent, validation agent. Automate complex estimation workflows.