Claude Code Skills · page 63

Solve quantitative problems in biophysics — pharmacokinetics (PK volume of distribution, clearance, half-life), epidemiology (R0, attack rate), toxicology (LD50, NOAEL), population genetics (Hardy-Weinberg, Fst), enzyme kinetics (Michaelis-Menten), thermodynamics. Use for first-principles quantitative biology calculations, dose calculations, exposure assessment, and biophysical-property estimation.

Analyze CRISPR-Cas9 genetic screens — MAGeCK gene-level scores, sgRNA count QC, replicate correlation, hit prioritization, and pathway GSEA on screen output. Use for genome-wide essentiality screens, synthetic-lethality discovery, dropout vs positive-selection screen analysis, target identification, and resistance-screen interpretation. Includes screen-QC and statistical thresholds.

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.

Integrate computed statistical results (DEGs, GWAS hits, associations) with biological context from ToolUniverse databases (UniProt, GO, Reactome, ClinVar, OpenTargets). Use for adding gene function/pathway/disease annotations to a result list, building biological narrative around statistical findings, and going beyond p-values to mechanism.

Universal data access patterns for downloading and parsing scientific data when ToolUniverse tools don't cover the source, only return metadata, or you need bulk records. Use for VCF/h5ad/BAM/SDF/GCT parsing, multi-step API workflows (search to filter to download to parse), thousands of records at once, or sources with no dedicated tool. Write Python code via Bash for every step.

Find and evaluate research datasets for any scientific question. Maps research questions to required study designs (longitudinal vs cross-sectional, observational vs experimental, single-cohort vs multi-cohort). Use when the user asks 'find data about X', 'where can I get data on Y', or needs a specific cohort/survey/repository. Covers GEO, ArrayExpress, dbGaP, NHANES, UK Biobank, ClinicalTrials.gov, GWAS Catalog, and 30+ scientific repositories.

Diagnostic test / biomarker accuracy — sensitivity, specificity, PPV, NPV, likelihood ratios, accuracy from a 2x2 table; ROC curve, AUC, and the optimal cutoff (Youden) for a continuous biomarker; and post-test probability via Bayes. Use when you have test results vs a gold standard (binary 2x2, or a continuous score + true labels) and need to judge how good the test is, pick a threshold, or compute the probability of disease given a result. Emphasizes the prevalence-dependence of PPV/NPV.

Generate comprehensive disease research reports covering genetics (causal genes, GWAS, OMIM), pathways (Reactome, KEGG), drugs (existing therapies, repurposing candidates), clinical trials, epidemiology (prevalence, incidence), and phenotypes (HPO). Use for full disease overviews, comprehensive disease characterization, and orphan/rare-disease profiling.

Dose-response / concentration-response curve fitting — IC50, EC50, Hill slope, Emax/Emin efficacy, and relative potency from paired concentration vs response data (enzyme/cell assays, drug screening, agonist/antagonist pharmacology). Fits the 4-parameter logistic (Hill sigmoidal) model. Use when you have concentrations + responses and need a potency value, to compare two compounds' potency, or to judge curve quality. NOT for image-derived dose-response (use tooluniverse-image-analysis) and NOT for survival/regression (use tooluniverse-statistical-modeling).

Assess drug-drug interactions — CYP metabolic interactions (substrate/inhibitor/inducer), transporter (P-gp, BCRP, OATP) effects, pharmacodynamic synergy/antagonism, clinical significance scoring, and management recommendations. Use for polypharmacy review, prescribing decision support, and safety analysis when adding or switching drugs.

Trace drug mechanism of action — primary target → downstream signaling → pathway perturbation → tissue/organ effect → clinical outcome. Uses DrugBank, ChEMBL, KEGG, Reactome, STRING. Use for understanding how a drug works, identifying off-target effects, mechanism-based combination therapy design, and writing mechanism sections of reports.

Drug regulatory and approval research — FDA substance registry, ATC/EPC classification, EMA decisions, generic-drug status, FDA Orange Book exclusivity, NDA/BLA pathways. Use for jurisdiction-aware approval status (FDA vs EMA), generic vs brand availability, exclusivity expiry tracking, and regulatory pathway selection. Always specifies the market when reporting status.

Identify drug repurposing candidates via target-based, compound-based, and disease-based strategies. Combines drug-target-disease network reasoning with mechanism rationale, clinical-trial precedent, and patent/regulatory feasibility. Use for hypothesis-generating repurposing for orphan diseases, finding existing drugs for new indications, and prioritizing candidates by evidence and feasibility.

Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory work.

Drug-combination synergy analysis — quantify whether two drugs together are synergistic, additive, or antagonistic using the standard reference models (Bliss independence, HSA / highest single agent, Loewe additivity, ZIP, and the Chou-Talalay Combination Index). Use when you have measured single-drug and combination effects (inhibition/viability) and need a synergy score. Explains which model to use, what data each one needs, and how to read the score. NOT for looking up pre-computed synergy in a database (use the SYNERGxDB tool / cell-line-profiling skill).

Quantitative drug-target validation pipeline. Scores druggability, selectivity, safety profile, ADMET feasibility, and structural tractability with a composite Target Validation Score (0-100) and GO/NO-GO recommendation. Use for go/no-go decisions on a target before commit-to-medchem, target prioritization across a list, and target-deselection rationale.

Ecology, biodiversity, and conservation biology research — species identification (GBIF, NCBI Taxonomy), invasive species impact, ecosystem dynamics, conservation status (IUCN), niche ecology. Use for biodiversity questions, species comparison, invasion biology, conservation prioritization, and ecology-related literature search.

Search and analyze electron microscopy data — cryo-EM density maps (EMDB), fitted atomic models (PDB), raw micrograph datasets (EMPIAR), and cryo-electron tomography volumes (CryoET Data Portal). Use for finding 3D structural data on a protein/complex, comparing experimental EM resolution to AlphaFold confidence, and accessing raw EM data for re-processing.

Enzyme kinetics — Michaelis-Menten Km, Vmax, kcat (turnover), and kcat/Km (catalytic efficiency / specificity constant) from substrate-velocity data, plus inhibition-mechanism analysis (competitive / uncompetitive / non-competitive, Ki). Fits the MM equation by nonlinear regression (and reports Lineweaver-Burk for reference). Use when you have substrate concentrations and initial reaction velocities and need kinetic parameters or to classify an inhibitor. NOT for BRENDA database lookups of published constants (use the BRENDA tools).

End-to-end observational epidemiology analysis — from research question (PECO Population/Exposure/Comparator/Outcome) to publication-ready statistical report. Covers cohort/case-control/cross-sectional design, regression with confounders, propensity scoring, sensitivity analysis. Writes Python code for every step. Use for epidemiology study analysis, NHANES/UK-Biobank-style analyses.

Histone-modification ChIP-seq, ATAC-seq accessibility, chromatin state, and TF binding analysis from ENCODE, Roadmap Epigenomics, ChIP-Atlas. Use for chromatin-state-by-tissue queries, TF-binding-by-region, regulatory landscape mapping, and ENCODE-cCRE annotations. For DNA methylation use tooluniverse-epigenomics; for RNA-seq use tooluniverse-rnaseq-deseq2.

Genomics and epigenomics analysis: DNA methylation (CpG, 5mC, 5hmC, bisulfite, RRBS), m6A RNA modification (MeRIP-seq), ChIP-seq peaks, ATAC-seq accessibility, histone modifications, chromatin state, multi-omics integration. Combines pandas/scipy/pysam computation with ToolUniverse annotation tools. Use for genome-wide epigenomic statistics, methylation analysis, and chromatin-genome integration.

Retrieve gene expression and omics datasets from ArrayExpress and BioStudies with gene disambiguation and quality assessment. Use for finding RNA-seq/microarray datasets by organism/tissue/condition, comparing across studies (case-control, time-series, dose-response), and assessing dataset suitability before downloading. Always uses English search terms.

Interpret hits from CRISPR-KO/CRISPRi/shRNA screens by integrating DepMap essentiality, gnomAD constraint scores, pathway context (Reactome, STRING), druggability (DGIdb), and clinical evidence (CIViC, COSMIC). Use for screen-hit prioritization, essentiality ranking, and turning a list of screen hits into a prioritized target shortlist.

Gene-disease association analysis across DisGeNET, OpenTargets, Monarch, OMIM, GenCC, Orphanet. Cross-references multiple sources for evidence-graded association reports with concordance scoring (5/5 sources agree → strong, 1/5 → weak). Use for 'which diseases is gene X associated with' or 'which genes cause disease Y' queries with quantitative confidence.

Gene-set enrichment analysis — GO (Biological Process, Molecular Function, Cellular Component), KEGG, Reactome pathway enrichment via clusterProfiler, gseapy, ORA, GSEA. Use for interpreting DEG lists, screen hit lists, or any gene-list-to-pathways query. Includes simplify-cutoff handling and union-vs-total denominator conventions for percent-DE questions.

Gene regulatory network analysis — TF-target inference (JASPAR motifs, ChIP-seq), motif scanning, eQTL integration, perturbation evidence (knockout/overexpression). Use for 'which TF regulates gene X', 'which genes does TF Y target', regulatory pathway reconstruction. Distinguishes direct (binding) vs indirect (co-expression) regulatory evidence.

GPCR receptor pharmacology — agonist/antagonist/inverse-agonist/biased-agonist classification, GPCRdb structural data, receptor-ligand binding analysis, antibody-target interface (SAbDab). Use for GPCR drug discovery, biased-agonism analysis, receptor subtype selectivity questions, and orthosteric vs allosteric pocket characterization.

Transform GWAS signals into drug targets and repurposing opportunities. Connects GWAS-significant loci to causal genes via fine-mapping/eQTL, then to druggable proteins via DGIdb/OpenTargets, then to existing drugs via ChEMBL. Use for GWAS-to-target hypothesis generation, druggable-fraction analysis of disease loci, and human-genetics-validated drug-repurposing prioritization.

Statistical fine-mapping of GWAS loci using credible sets (SuSiE, FINEMAP) and locus-to-gene scoring (Open Targets L2G). Identifies likely causal variants and target genes — distinct from positional 'nearest gene' which is often wrong. Use for prioritizing causal variants at GWAS hits, comparing fine-mapping methods, and converting lead SNPs to target genes.

Interpret a single GWAS SNP across multiple databases — GWAS Catalog hits, LD/haplotype context, eQTL evidence, regulatory annotation, ClinVar pathogenicity, gnomAD frequency. Use for 'what does this SNP do', SNP-to-mechanism tracing, and resolving lead-SNP-vs-causal-variant ambiguity. Always considers LD structure before claiming a SNP is mechanistically responsible.

Compare GWAS studies, perform meta-analyses across cohorts, and assess signal replication. Uses GWAS Catalog metadata, study-level statistics, and cross-cohort comparison. Use for evaluating GWAS reproducibility for a trait, meta-analysis sample size and effect-size aggregation, and detecting study heterogeneity (population, design, ancestry).

Discover causal genes for diseases/traits from GWAS data using Open Targets L2G (locus-to-gene) scoring — integrates eQTL, chromatin interaction, and distance evidence. Use for trait-to-gene mapping, drug-target hypothesis generation from GWAS, and replacing the 'nearest gene' heuristic with multi-evidence L2G scores.

HLA gene-family analysis and MHC-peptide binding for transplant compatibility, vaccine epitope coverage, and cancer immunotherapy. Uses IMGT (HLA polymorphism), IEDB (epitope-MHC binding), UniProt (annotation), DGIdb (druggability). Use for HLA typing/imputation review, vaccine HLA coverage, and immunotherapy prediction biomarkers (HLA-LOH, neoantigen presentation).

Microscopy and quantitative imaging analysis — colony morphometry, fluorescence intensity quantification, cell-count statistics, dose-response curves, and ANOVA/Dunnett on image-derived measurements. Uses pandas/numpy/scipy/scikit-image. Use for analyzing tabular outputs from CellProfiler/ImageJ, image-derived measurement statistics, and image-based assay quantification.

TCR/BCR repertoire analysis — V(D)J segment usage, CDR3 sequence diversity, clonality scoring, antigen specificity matching to IEDB, public-clone identification. Use for adaptive immune response characterization, post-treatment immune monitoring, antigen-specific clone tracking, and clonal-expansion analysis in immunotherapy or vaccination studies.

Immunology research workflows: antibody-antigen interactions, T/B cell repertoire, MHC/HLA binding prediction, autoimmune disease genetics, vaccine epitope mapping. Uses IEDB, IMGT, SAbDab, UniProt. Use for adaptive immunity questions, immune response analysis, antibody/TCR/BCR characterization, immunogenicity prediction, and immune-pathway-to-disease mapping.

Predict patient response to immune checkpoint inhibitors (ICIs) by integrating tumor mutational burden (TMB), microsatellite instability (MSI), PD-L1 expression, HLA status, and immune-related gene expression. Outputs ICI Response Score with drug-specific recommendations and resistance-risk assessment. Use for melanoma/NSCLC/RCC immunotherapy decision support.

Rapid pathogen characterization and drug repurposing for outbreaks. Combines pathogen genomics (NCBI, BVBRC), host immune response (IEDB), drug-target databases (ChEMBL, DGIdb), and literature surveillance (PubMed/EuropePMC). Use for emerging-pathogen profiling, antiviral candidate identification, and outbreak intelligence reporting.

Inorganic chemistry, physical chemistry, and materials science — crystal structures, coordination chemistry, lattice parameters, thermodynamic properties, electronic structure. Use for unit cell volume calculations, coordination geometry, materials property estimation, and inorganic-mechanism reasoning. Complementary to tooluniverse-organic-chemistry.

Detect and auto-install missing ToolUniverse research skills. Checks common Claude Code/Cursor/Codex skill directories for the canary file, and installs any missing skills if none found. Use when the plugin's research skills aren't loading, when migrating between clients, or when verifying a skill installation.

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.

Lipid analysis and lipid-disease associations using LIPID MAPS classification, HMDB metabolite data, KEGG/Reactome lipid pathways (sphingolipid, eicosanoid, steroid, fatty acid), and PubChem chemical info. Use for lipid identification, lipid metabolism pathway mapping, and lipid-associated disease analysis (cardiovascular, diabetes, NAFLD).

Deep literature review — PubMed, EuropePMC, bioRxiv preprints, citation networks, evidence synthesis. Disambiguates queries, runs collision-aware searches, grades evidence T1-T4, and produces structured reports. Use for systematic literature review, meta-analysis evidence collection, and detailed answer-with-citations workflows.

Mendelian randomization (MR) causal inference — does an exposure, risk factor, or biomarker CAUSALLY affect a disease/outcome, using genetic variants as instrumental variables (IEU OpenGWAS / EpiGraphDB MR-EvE). Use this whenever the user asks if X causes Y, whether an observational association is actually causal or just correlation, if a biomarker/trait is a causal risk factor, wants to triangulate epidemiology against genetic evidence, or mentions Mendelian randomization, instrumental-variable analysis, two-sample MR, or genetic causal evidence — even if they never say "MR" (e.g. "is LDL cholesterol actually causal for heart disease?", "does BMI cause type 2 diabetes or just correlate?", "is CRP a causal driver of stroke?"). Covers trait-label resolution, MR effect direction/magnitude, instrument quality (MOE score), method agreement (IVW vs MR-Egger vs weighted median), bidirectional MR for reverse causation, and distinguishing causation from genetic correlation. Not for plain GWAS association lookups (use the GWAS skills) or fitting your own instruments from raw summary statistics.

Meta-analysis / evidence synthesis — pool effect sizes across studies (odds ratios, risk ratios, hazard ratios, mean differences, correlations, GWAS betas) with fixed- or random-effects models, quantify heterogeneity (Q, I², τ²), and build a forest plot. Use when you have results from MULTIPLE studies and need a single pooled estimate, or to synthesize evidence from a systematic review / multiple GWAS / replicated experiments. Handles the error-prone effect-size + standard-error preparation (converting OR/HR/CI, two-group means±SD, proportions, and correlations into the (effect, SE) the pooling step needs).

Analyze metabolomics data end-to-end — metabolite identification, quantification (TIC normalization, batch correction), differential analysis, and pathway interpretation. Use for processing mass-spec metabolomics output, normalization choice, untargeted metabolomics workflows, and integrating with other omics layers.

Metabolomics pathway analysis — metabolite identification (HMDB, KEGG, ChEBI), pathway mapping (Reactome, KEGG, MetaCyc), disease associations, enzyme/gene linkage. Use for metabolite-to-pathway-to-disease connections, BridgeDb-based ID conversion, and integrating metabolomics with gene-level pathway analyses.

Metabolomics research — metabolite identification, study analysis, and database searches across HMDB, MetaboLights, Metabolomics Workbench, KEGG. Use for annotating mass-spec features to known metabolites, finding metabolomics studies of a disease, and structured metabolomics research reports with metabolite-pathway mapping.

Microbiome and metagenomics analysis using MGnify, GTDB taxonomy, ENA sequencing data, and EuropePMC literature. Covers taxonomic classification, genome quality assessment, biome-clinical phenotype linkage, and pathway interpretation. Use for amplicon/shotgun metagenomics study analysis.

Microbiome research using MGnify, GTDB, ENA, OLS (ENVO biomes), and EuropePMC. Covers study discovery, taxonomic profiling, host-microbe interaction analysis, and biome-by-condition queries. Use for microbiome study selection, organism-environment associations, and clinical-microbiome literature review. Distinct from analytical workflow (use tooluniverse-metagenomics-analysis for that).

Cross-species genetic analysis using model organism databases (MGI mouse, ZFIN zebrafish, FlyBase fruit fly, WormBase worm, SGD yeast, RGD rat, GBIF taxonomy). Maps human genes to orthologs, retrieves phenotype/expression/functional data, assesses gene function conservation, and identifies the best animal model for studying a human gene or disease.

Molecular cloning assembly design — Gibson Assembly (overlap design for seamless multi-fragment joining) and Golden Gate Assembly (Type IIS / BsaI / BbsI design with unique 4-bp fusion overhangs). Use when you need to plan how to join DNA fragments into a construct, design assembly overlaps/overhangs, or decide between cloning methods. Covers the domestication (internal-site removal), overhang-uniqueness, and overlap-Tm rules. For PCR primers to generate the fragments, see tooluniverse-primer-design.

Multi-omics integration — orchestrate per-layer analysis (transcriptomics, proteomics, epigenomics, genomics, metabolomics) then perform cross-omics correlation, multi-omics clustering, and pathway-level integration. Use for integrative systems-biology analysis, multi-modal disease characterization, and cross-omics biomarker discovery.

Comprehensive disease characterization across genomics, transcriptomics, proteomics, and pathways for systems-level understanding. Identifies therapeutic opportunities and biomarker candidates by integrating multi-layer molecular data. Use for full-omics disease deep-dive reports, mechanism mapping, and biomarker-and-target identification from multi-omics data.

Compound-target-disease network construction and analysis for drug repurposing, polypharmacology discovery, and multi-target drug design. Uses STRING, BioGRID, ChEMBL, DGIdb, OMIM, OpenTargets. Use for off-target effect prediction, network-based drug repurposing, and identifying molecules with desired multi-target profile.

Neuroscience research workflows: neuroanatomy, neural circuits, neurotransmitter biology, neurological/psychiatric disease genetics, neural-protein function. Uses Allen Brain Atlas, WormBase (C. elegans connectome), UniProt for neural proteins, PubMed for primary literature. Use for brain-region biology, neural development, neurodegeneration mechanisms (Alzheimer's, Parkinson's, ALS), and synaptic-protein characterization.

Non-coding RNA analysis — miRNAs (miRBase, miRDB targets), lncRNAs (LNCipedia, RNAcentral), circRNAs, snoRNAs, and other ncRNA classes. Distinct mechanisms per class — miRNAs repress mRNA; lncRNAs scaffold/decoy/enhance. Use for ncRNA function prediction, miRNA-target prediction, lncRNA functional annotation, and ncRNA-disease association queries.

Organic chemistry reasoning guide for reaction product prediction, mechanism analysis (electrophilic/nucleophilic substitution, addition, elimination, pericyclic, radical), and spectroscopy interpretation (1H/13C NMR, IR, MS). Reasons from first principles (electron flow, kinetic vs thermodynamic) rather than pattern-matching named reactions. Use for organic synthesis problems and mechanism explanations.

Compute and interpret validated bedside clinical risk scores and pretest probabilities for an INDIVIDUAL patient — pick the right score for the scenario, gather inputs, run the deterministic calculator tool, and read the result against an interpretation table. Covers CHA2DS2-VASc (AF stroke risk), HAS-BLED (bleeding on anticoagulation), CURB-65 (pneumonia severity / admit decision), qSOFA (sepsis screen), Child-Pugh + MELD-Na (cirrhosis severity / transplant priority), Wells DVT and Wells PE (VTE pretest probability), ASCVD (10-year cardiovascular risk / statin decision), and eGFR CKD-EPI (kidney function / drug dosing). Use when asked things like "stroke risk for this AF patient", "should this patient be anticoagulated", "pneumonia severity — admit or not?", "sepsis screen this patient", "DVT/PE pretest probability", "10-year cardiovascular risk", "cirrhosis severity / MELD score", or "eGFR / kidney function". Pairs CHA2DS2-VASc with HAS-BLED to weigh anticoagulation. NOT for polygenic/genetic risk (use tooluniverse-polygenic-risk-score), NOT for population-level epidemiology/incidence (use tooluniverse-epidemiological-analysis), and NOT for diagnostic test sensitivity/specificity/likelihood-ratio math (use tooluniverse-diagnostic-test-evaluation).

FASTQ quality control and adapter/quality-trimming decisions with local NGS tools — run FastQC on raw reads, summarize a project with MultiQC, interpret per-base sequence quality, per-base N content, adapter content, overrepresented sequences, sequence duplication and GC content, and decide whether (and how) to trim with fastp / Cutadapt before downstream analysis. seqkit for read counts/stats/subsampling. Use when someone asks "run QC on my FASTQs", "are my reads good quality?", "do I need to trim adapters?", "interpret this FastQC report", "what does this WARN/FAIL mean", "why are overrepresented sequences flagged", "should I quality-trim before alignment", "make a MultiQC summary", or "clean up these reads with fastp". NOT for differential expression / DEG analysis (use tooluniverse-rnaseq-deseq2), NOT for read alignment, coverage, or variant calling (use tooluniverse-variant-analysis / tooluniverse-sequence-analysis). Honest: shells out to real local binaries; if a tool is missing it emits an install plan and stops rather than inventing QC numbers, and it never auto-trims or overwrites raw FASTQs.

Genome-ASSEMBLY discovery, QC, and replicon mapping for any organism (bacteria, archaea, fungi, and beyond) using NCBI Datasets. Resolves an organism name or taxid to assemblies, picks the reference/representative or best-quality assembly, pulls assembly QC metrics (total length, contig/scaffold N50, contig count, GC%, assembly level, RefSeq category), enumerates chromosomes and plasmids via per-replicon sequence reports, and compares candidate assemblies on quality. Use for "what genomes are available for [organism]", "assembly stats / N50 / GC content for [GCF_/GCA_ accession]", "how many plasmids does [strain] have", "compare assemblies for [species]", "find the reference genome for [taxon]", "is this assembly Complete Genome or just contigs". NOT for gene-level orthology/synteny (use tooluniverse-comparative-genomics), plant gene structure (use tooluniverse-plant-genomics), de novo assembly from raw reads (no tool exists), or taxonomy-only name/lineage lookups.

Dereplicate a putative natural product and assign its chemical taxonomy. Use to answer "is [compound] a known natural product", "what microbe/organism produces [compound]", "what chemical class is [compound]", "dereplicate this metabolite (by formula/exact mass/InChIKey/SMILES)", or "classify this molecule into ChemOnt". Searches NPAtlas for known microbial natural products (producing organism + literature reference), assigns the ChemOnt kingdom→superclass→class→subclass hierarchy via ClassyFire, resolves systematic IUPAC names to structure via OPSIN, and cross-references identity in PubChem. NOT for general drug/compound identity or ADMET (use tooluniverse-chemical-compound-retrieval / tooluniverse-small-molecule-discovery) and NOT for metabolomics pathway/enrichment analysis (use tooluniverse-metabolomics skills).

Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on Google Antigravity (AGY / Antigravity IDE / Antigravity 2.0). ALWAYS consult this skill for any of those — don't answer from memory, because the exact CLI name (agy), the "agy plugin install <path>" flow, the uvx tooluniverse MCP server, and the API-key env vars are easy to get wrong. Use it whenever someone wants to get ToolUniverse (or "the 1000+ scientific tools" / "the harvard tools") working on Antigravity, says the Antigravity plugin or its tools/skills won't load, hits a uvx or MCP-server startup error, asks how Antigravity updates it, wants to pin or remove it, or finds it running an old tool version. Not for the Codex plugin (use tooluniverse-codex-plugin) or Claude Code plugin (use tooluniverse-claude-code-plugin), for running research with the tools, or for authoring new tools or skills.

Answer biomedical FACTUAL / recall / multiple-choice questions by querying ToolUniverse database tools instead of answering from memory. Triggers on any 'which gene/drug/variant/disease/pathway/miRNA/TF...' lookup, any question phrased 'according to <database>' (DisGeNet, OMIM, MSigDB, miRDB, GTRD, MGI, Ensembl, ClinVar, ChEMBL, OpenTargets, Reactome, GtoPdb, UniProt...), and multiple-choice biology/medicine knowledge questions where one option must be verified against an authoritative source. NOT for analyzing user-supplied data files (CSV/VCF/h5ad → use the data-analysis router) and NOT for open-ended literature synthesis. Use whenever a single correct answer exists in a public biomedical database and could be looked up rather than guessed.

Evaluate the human safety liability of knocking down, knocking out, degrading, or pharmacologically inhibiting a gene. Use for gene safety scoring, on-target toxicity assessment, essentiality and genetic-constraint review, critical-organ expression analysis, or deciding whether a target needs partial, transient, or tissue-specific modulation.

Create Claude Code custom slash commands with proper structure, frontmatter, and best practices. Use this skill whenever the user wants to create a new command, add a slash command, build a custom command, or mentions "create-command", "new command", "add command", or "make a command" for Claude Code. Also trigger when the user wants to turn a workflow into a reusable command.

>-

Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review. Triggers: "codex", "use gpt", "gpt-5", "let openai", "full-auto", "adversarial review", "second opinion review", "用codex", "让gpt实现", "对抗式审查", "让codex审查计划", "第二意见". Use this skill whenever the user wants to delegate coding tasks to OpenAI models, run code or plan reviews via codex, get a second-opinion review from a different model, or execute tasks in a sandboxed environment.

Interactive feature development workflow from idea to implementation. Creates requirements (EARS format), design documents, and task lists. Triggers: "kiro", ".kiro/specs/", "feature spec", "需求文档", "设计文档", "实现计划".

Generate or edit images via Google Gemini (nanobanana). This is the DEFAULT image skill — use whenever the user asks to generate, create, or edit an image and does NOT name another provider. Triggers: "nanobanana", "generate image", "create image", "edit image", "图片生成", "生成图片", "AI绘图", "图片编辑". Do NOT use for diagrams (架构图/流程图/时序图) — draw those with Mermaid or code instead.

GitHub Spec-Kit integration for constitution-based spec-driven development. 7-phase workflow. Triggers: "spec-kit", "speckit", "constitution", "specify", ".specify/", "规格驱动开发", "需求规格".

Extract subtitles/transcripts from YouTube videos. Triggers: "youtube transcript", "extract subtitles", "video captions", "视频字幕", "字幕提取", "YouTube转文字", "提取字幕".

Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless `claude -p` subprocesses, aggregate results into a polished report file. Use for systematic web/document research, competitive or industry analysis, batch link/dataset processing, and long-form evidence synthesis. Triggers: "深度调研", "deep research", "wide research", "多 Agent 调研", "系统调研".

Capture technical breakthroughs and transform them into actionable, reusable documentation. Use this skill when the user has achieved a significant technical insight, solved a hard problem, discovered a non-obvious solution, or wants to document a breakthrough moment. Also trigger when the user mentions "eureka", "breakthrough", "document this insight", "capture this discovery", or wants to turn a technical win into reusable knowledge.

Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submission. Use whenever the user mentions fixing a GitHub issue, says "fix issue #123", "work on this issue", "修复 issue", or references a GitHub issue number or URL.

Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for local uncommitted changes — this skill only reviews pull requests on GitHub.

Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Use ONLY when the user explicitly names OpenAI or GPT as the provider: "gpt image", "openai image", "generate image with openai", "用 openai 画图", "用 GPT 生成图片". For generic image requests without a provider, use nanobanana-skill instead. Do NOT use for diagrams (架构图/流程图) — draw those with Mermaid or code.

Analyze development sessions, capture learnings, and improve Claude Code instructions. Use when the user wants to reflect on a session, improve CLAUDE.md, extract learnings, or optimize AI-human collaboration. Supports two modes: quick (default) focuses on CLAUDE.md improvements, deep mode performs comprehensive session analysis with learning capture.

Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.

Translate English or Japanese tech articles into natural, fluent Chinese. Use whenever the user asks for Chinese translation, says "translate to Chinese" or "翻译", or provides English/Japanese content (pasted text or a file) to convert into Chinese. Chinese output only — not for translating into other languages.

Explore user intent, requirements, and design options through collaborative dialogue before implementation. Use before building new features, components, or systems — whenever the user describes something to build and design decisions are involved. Triggers: \"brainstorm\", \"help me design\", \"think through the requirements\", \"头脑风暴\", \"设计方案\", \"梳理需求\". Not for bug fixes, config changes, or tasks with an obvious implementation path.

针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。

将当前对话压缩为交接文档（handoff document / session handoff brief），供下一个 agent 接续工作。手动调用 /handoff。

Use whenever driving agent-browser against the local Relaticle app (relaticle.test and its panels) for testing, QA, business review, or UI automation. Covers Filament v5 + Livewire v4 quirks specific to this codebase: panel URL derivation (domain-routed vs path-routed, never assumed), login flows for the app and sysadmin panels, seeded credentials, Select/date-picker interaction, the $wire.mountAction gold pattern, tenant switching, Reverb/queue hazards, and session isolation. Every hard fact here is a DATED CACHED HINT. When one fails, re-derive from the running app and update this file (self-heal). Not for other sites or generic browser automation.

TRIGGER when working with ai-sdk which is Laravel official first-party AI SDK. Activate when building, editing AI agents, chatbots, text generation, image generation, audio/TTS, transcription/STT, embeddings, RAG, vector stores, reranking, structured output, streaming, conversation memory, tools, queueing, broadcasting, and provider failover across OpenAI, Anthropic, Gemini, Azure, Groq, xAI, DeepSeek, Mistral, Ollama, ElevenLabs, Cohere, Jina, and VoyageAI. Invoke when the user references ai-sdk, the `Laravel\Ai\` namespace, or this project's AI features — not for other AI packages used directly.

Use when the user asks to business-review their work (local mode default, via 'business-review' or 'review my branch'), a Relaticle pull request ('--pr <N>' or a bare PR number), or a described change (--describe). v3 is a panel-of-QAs engine. It resolves the live environment first (URLs/creds/queue/Redis/Reverb are DISCOVERED from the running app, never assumed), runs a browser-capability preflight, auto-tiers by blast radius, synthesizes journeys from the diff plus Relaticle CRM priors, walks them happy AND sad through the real browser, sweeps the regression ledger, adversarially cold-reproduces every bug, and emits a substance-gated verdict (ai-approved / ai-rejected / ai-needs-human, or blocked on a degraded channel). Browser-truth only: never tinker or hit the DB to fix or fake a result. On request ('fix all issues', --fix) enters fix mode: fix → re-verify each finding against its original repro → re-gate. Publishing to the PR is opt-in and hard-disabled on a degraded run. Does NOT do code/security/scope review; for that use /code-review, /review, /deep-review.

Handles Laravel Cashier Stripe integration including subscriptions, webhooks, Stripe Checkout, invoices, charges, refunds, trials, coupons, metered billing, and payment failure handling. Triggered when a user mentions Cashier, Billable, IncompletePayment, stripe_id, newSubscription, Stripe subscriptions, or billing. Also applies when setting up webhooks, handling SCA/3DS payment failures, testing with Stripe test cards, or troubleshooting incomplete subscriptions, CSRF webhook errors, or migration publish issues.

Use this skill whenever the user mentions Horizon by name in a Laravel context. Covers the full Horizon lifecycle: installing Horizon (horizon:install, Sail setup), configuring config/horizon.php (supervisor blocks, queue assignments, balancing strategies, minProcesses/maxProcesses), fixing the dashboard (authorization via Gate::define viewHorizon, blank metrics, horizon:snapshot scheduling), and troubleshooting production issues (worker crashes, timeout chain ordering, LongWaitDetected notifications, waits config). Also covers job tagging and silencing. Do not use for generic Laravel queues without Horizon, SQS or database drivers, standalone Redis setup, Linux supervisord, Telescope, or job batching.

Develops real-time broadcasting with Laravel Echo. Activates when setting up broadcasting (Reverb, Pusher, Ably); creating ShouldBroadcast events; defining broadcast channels (public, private, presence, encrypted); authorizing channels; configuring Echo; listening for events; implementing client events (whisper); setting up model broadcasting; broadcasting notifications; or when the user mentions broadcasting, Echo, WebSockets, real-time events, Reverb, or presence channels.

ACTIVATE when the user works on authentication in Laravel. This includes login, registration, password reset, email verification, two-factor authentication (2FA/TOTP/QR codes/recovery codes), passkeys, profile updates, password confirmation, or any auth-related routes and controllers. Activate when the user mentions Fortify, auth, authentication, login, register, signup, forgot password, verify email, 2FA, passkeys, WebAuthn, or references app/Actions/Fortify/, CreateNewUser, UpdateUserProfileInformation, FortifyServiceProvider, config/fortify.php, or auth guards. Fortify is the frontend-agnostic authentication backend for Laravel that registers all auth routes and controllers. Also activate when building SPA or headless authentication, customizing login redirects, overriding response contracts like LoginResponse, or configuring login throttling. Do NOT activate for Laravel Passport (OAuth2 API tokens), Socialite (OAuth social login), or non-auth Laravel features.

Use this skill to analyze how a Laravel application is actually written and record its conventions as shared rules. Trigger when the user wants to detect, infer, document, or standardize project conventions or coding style, set up or grow `.ai/rules`, resolve mixed or conflicting patterns (e.g. \"are we using Form Requests or inline validation?\"), or onboard agents and teammates to \"how we do things here\". Covers: a systematic sweep of ~49 Laravel convention dimensions (validation, models, architecture, testing, frontend, database, console), open-ended house-pattern discovery, conflict reporting, and recording rules scoped to the right paths via the Boost `record-rule` MCP tool. Do not use for one-off code review, enforcing formatting a linter already handles, or editing `.ai/rules` files by hand.

Apply this skill whenever writing, reviewing, or refactoring Laravel PHP code. This includes creating or modifying controllers, models, migrations, form requests, policies, jobs, scheduled commands, service classes, and Eloquent queries. Triggers for N+1 and query performance issues, caching strategies, authorization and security patterns, validation, error handling, queue and job configuration, route definitions, and architectural decisions. Also use for Laravel code reviews and refactoring existing Laravel code to follow best practices. Covers any task involving Laravel backend PHP code patterns.

Build filtered, sorted, and included API endpoints using spatie/laravel-query-builder. Activates when working with QueryBuilder, AllowedFilter, AllowedSort, AllowedInclude, or when the user mentions query parameters, API filtering, sorting, includes, or spatie/laravel-query-builder.

Use for any task or question involving Livewire. Activate if user mentions Livewire, wire: directives, or Livewire-specific concepts like wire:model, wire:click, wire:sort, or islands, invoke this skill. Covers building new components, debugging reactivity issues, real-time form validation, drag-and-drop, loading states, migrating from Livewire 3 to 4, converting component formats (SFC/MFC/class-based), and performance optimization. Do not use for non-Livewire reactive UI (React, Vue, Alpine-only, Inertia.js) or standard Laravel forms without Livewire.

Use this skill for Laravel MCP development. Trigger when creating or editing MCP tools, resources, prompts, servers, or UI apps in Laravel projects. Covers: artisan make:mcp-* generators, routes/ai.php, Tool/Resource/Prompt/AppResource classes, schema validation, shouldRegister(), OAuth setup, URI templates, read-only attributes, MCP debugging, MCP UI apps, the x-mcp::app Blade component, createMcpApp(), default AppResource handle() auto-infers view from class name, Response::view(), AppMeta/Csp/Permissions/appMeta() configuration, #[RendersApp] attribute, Library enum for CDN libraries (Tailwind, Alpine), and host theming via CSS variables. Use this whenever the user mentions MCP apps, MCP UI, interactive MCP resources, styling MCP apps with Tailwind or Alpine, or building visual interfaces for AI agents.

Build and work with spatie/laravel-medialibrary features including associating files with Eloquent models, defining media collections and conversions, generating responsive images, and retrieving media URLs and paths.

Develops OAuth2 API authentication with Laravel Passport. Activates when installing or configuring Passport; setting up OAuth2 grants (authorization code, client credentials, personal access tokens, device authorization); managing OAuth clients; protecting API routes with token authentication; defining or checking token scopes; configuring SPA cookie authentication; handling token lifetimes and refresh tokens; or when the user mentions Passport, OAuth2, API tokens, bearer tokens, or API authentication. Make sure to use this skill whenever the user works with OAuth2, API tokens, or third-party API access, even if they don't explicitly mention Passport.

Use when working with Laravel Pennant the official Laravel feature flag package. Trigger whenever the query mentions Pennant by name or involves feature flags or feature toggles in a Laravel project. Tasks include defining feature flags checking whether features are active creating class based features in `app/Features` using Blade `@feature` directives scoping flags to users or teams building custom Pennant storage drivers protecting routes with feature flags testing feature flags with Pest or PHPUnit and implementing A B testing or gradual rollouts with feature flags. Do not trigger for generic Laravel configuration authorization policies authentication or non Pennant feature management systems.

Mandatory point-of-use sequence for capturing annotated screenshots that go into deliverables (ClickUp reviews, bug repros, internal evidence, end-user docs). Invoke this BEFORE every screenshot capture, not once per session, so the rules are fresh in context at the moment you actually shoot. Covers the annotate → verify-crop → shoot → read-back flow, the helper JS files (annotate.js, verify-crop.js), and the audience-specific annotation rules (label vs. no label). If you are about to type `agent-browser screenshot file.png` for any reason other than throwaway debugging, invoke this skill first.