Orchestrates an end-to-end de novo genome assembly project, routing each step to the right genome-assembly skill rather than restating it. Profiles the genome first (k-mer spectrum -> size, heterozygosity, ploidy), QCs reads, chooses an assembly path by data type (SPAdes for Illumina, Flye for noisy long reads, hifiasm for HiFi, metaFlye for communities), polishes only when needed, decontaminates, scaffolds with Hi-C, and finishes with three-axis QC (contiguity + completeness + correctness). Use when assembling a genome from raw reads and deciding which assembler, whether to polish, and how to prove the result is good.
Orchestrates an end-to-end CRISPR editing experiment design from target gene to delivery-ready, validatable constructs. Sequences guide design, off-target assessment, edit-modality selection (knockout, base editing, prime editing, HDR knock-in), and template/donor design, with a QC checkpoint at each handoff. Use when designing a complete CRISPR experiment for knockout, point correction, or tagging and the order of operations, the modality decision, and the cross-cutting traps are needed rather than a single step. Defers each step's mechanics to the genome-engineering skills.
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, matching the hit-calling method to the 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.
Orchestrates an end-to-end long-read structural-variant pipeline - basecalling to minimap2 alignment (platform-matched preset) to Sniffles2/cuteSV/pbsv calling to optional assembly-based calling (dipcall/PAV) to two-step .snf cohort merging to Truvari benchmarking - chaining ONT and PacBio HiFi runs while handing the SV signal mechanism off to the component skills. Use when running a long-read SV workflow from reads to a benchmarked callset, choosing the minimap2 preset and SV caller by platform and goal, deciding when long reads are worth it for the insertions and repeat-mediated SVs short reads physically miss, building a joint-genotyped cohort with the two-step .snf design, or parameterizing a Truvari benchmark against GIAB HG002 Tier 1 plus CMRG. Not for the SV signal mechanism itself (see variant-calling/structural-variant-calling) or short-read SV.
End-to-end biomarker discovery workflow from expression data to validated biomarker panels. Covers feature selection with Boruta/LASSO, leakage-safe cross-validation, calibration, and SHAP interpretation. Use when building and validating diagnostic or prognostic biomarker signatures from omics data.
End-to-end genome-scale metabolic modeling from genome sequence to flux predictions. Covers automated reconstruction with CarveMe, model validation with memote, FBA/FVA analysis, and gene essentiality prediction. Use when building metabolic models or predicting metabolic phenotypes from genomic data.
End-to-end gene regulatory network inference pipeline from processed single-cell data to regulon discovery and perturbation simulation. Supports RNA-only (pySCENIC) and multiome (SCENIC+) paths. Use when building gene regulatory networks from single-cell transcriptomic or multiome data.
Orchestrates an end-to-end MeRIP-seq / m6A-seq analysis from raw FASTQ to differential m6A peak calls and metagene plots, chaining fastp adapter trimming, STAR splice-aware alignment (NO deduplication for non-UMI MeRIP), deepTools replicate-concordance + IP-enrichment QC, PreSeq saturation curves, exomePeak2 (transcript-aware Poisson GLM) peak calling, optional MACS3 broad-peak cross-check, DRACH motif confirmation as a sanity check (NOT a per-peak filter), exomePeak2 differential calling via the four-BAM-vector interface (bam_ip + bam_input control; bam_treated_ip + bam_treated_input treatment), ChIPseeker annotation, and the canonical Guitar metagene with stop-codon enrichment as the biological QC anchor. Use when running a complete MeRIP analysis from raw reads, when chaining the constituent epitranscriptomics skills (merip-preprocessing -> m6a-peak-calling -> m6a-differential -> modification-visualization), or when wrapping the pipeline in Snakemake / Nextflow.
Runs and configures curated nf-core community Nextflow pipelines (rnaseq, sarek, atacseq, methylseq, ampliseq, taxprofiler, fetchngs) reproducibly, pinning the pipeline revision with -r and selecting a container engine and institutional config via -profile. Use when deciding to adopt a community pipeline versus author one from scratch; picking a pipeline and pinning its -r revision; selecting -profile test/docker/singularity/conda plus an institutional config from nf-core/configs; building and validating a samplesheet CSV against the pipeline schema (nf-schema); choosing --genome/iGenomes versus custom references; configuring resources and max_memory for SLURM/AWS Batch; using -resume and -stub; and reading MultiQC outputs.
Build AI scientist systems with the ToolUniverse Python SDK for scientific research. Covers the 3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search. Use for SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows.
Install or update ToolUniverse in Claude Science — create the conda env, install the tooluniverse pip package, and (re)build the tooluniverse-research skill by fetching the current workflow library from GitHub. Use for first-time setup, upgrading the ToolUniverse version, refreshing the bundled workflows after an upstream release, or reinstalling on a new machine.
Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems, service operations, network traffic, logistics, or any system where entities interact with shared resources over time.
Generate the success criteria for a task or question, then review work against them. Given a task, goal, or open-ended question, decompose it into scenarios, evaluation perspectives, and fine-grained weighted YES/NO criteria using the Recursive Expansion Tree (RET) method; if work is supplied, score it criterion-by-criterion and surface what is missing or could be better. Use when asked to self-review or check your own work, judge whether a task is done well or completely, build a definition-of-done or completeness checklist, create an evaluation rubric or grading criteria, score or grade answers to a question, set up an LLM-as-judge rubric, or when the user mentions self-review, completeness check, success criteria, evaluation criteria, scoring rubric, Qworld, or the RET algorithm.
Authors reproducible Nextflow DSL2 pipelines built on reactive dataflow, where processes communicate only through channels and execution order is not guaranteed. Use when deciding channel/dataflow (Nextflow) vs rule-based (Snakemake) authoring; wiring queue vs value channels and fixing shared-reference exhaustion with .first(); composing DSL2 modules and subworkflows with take/main/emit; selecting container/conda profiles and pinning images by digest for portability across local/SLURM/LSF/AWS Batch/Google Batch/Kubernetes executors; diagnosing why -resume misses the cache (nondeterministic input order, mtime on network filesystems, mutable :latest tags) with cache 'lenient' and -dump-hashes; managing work/ vs publishDir and dynamic retry escalation; and choosing whether to adopt an nf-core community pipeline or author from scratch.
Add custom local tools to ToolUniverse alongside the 1000+ built-in tools. Covers JSON-config tools (simplest, no code), Python class tools (REST/SOAP/GraphQL APIs, computational logic), and best-practices for return schemas. Use for wrapping new APIs, adding domain-specific computations, or contributing tools to the registry.
Install the ToolUniverse Claude Code plugin in one step — provides MCP server with 1000+ scientific tools, 120+ research skills, slash commands, hooks, and the research agent. Use for first-time plugin install, troubleshooting plugin not loading, verifying MCP server connection, listing API key requirements, or configuring auto-update.
Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.
End-to-end imaging mass cytometry workflow from raw acquisitions to spatial cell analysis. Orchestrates image preprocessing, segmentation, phenotyping, and spatial statistics. Use when analyzing imaging mass cytometry data end-to-end.
KEGG-based disease-drug-variant network research. Connects diseases to causal genes, drugs to molecular targets, and variants to pathways using KEGG's editorially curated databases (KEGG Disease, Drug, Network, Variant, Pathway). Use for drug repurposing via shared pathways, mechanistic disease-gene-drug networks, and pathway-based target discovery. Distinguishes direct (binding) vs indirect (pathway co-membership) drug-target relationships.
Code quality patterns and guidelines for ToolUniverse tool development. Apply when writing, fixing, or refactoring tool Python code in the ToolUniverse project. Encodes lessons from 80+ debug rounds. Use alongside devtu-fix-tool and devtu-self-evolve. Triggers: implementing tool fixes, writing new tool classes, reviewing tool code quality, checking schema correctness, looking up API-specific bug fixes.
PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.