Explore

Process-based discrete-event simulation. Model queues, shared resources, timed events: manufacturing, service ops, network traffic, logistics. Processes are Python generators yielding events. Resources: capacity-limited (Resource/Priority/Preemptive), bulk (Container), objects (Store, FilterStore). For continuous use SciPy ODEs; for agent-based use Mesa.

Model interpretability via SHAP (Shapley values from game theory). Covers explainer choice (Tree, Deep, Linear, Kernel, Gradient, Permutation), feature attribution, and plots (waterfall, beeswarm, bar, scatter, force, heatmap). Use to explain ML predictions, rank features, debug models, audit fairness, or compare models. Works with tree, deep, linear, and black-box models.

CLI toolkit for SAM/BAM/CRAM: sort, index, convert, filter, QC alignments. Core commands: view, sort, index, flagstat, stats, depth, markdup, merge. Required between alignment and variant/peak calling. Use pysam for Python-native BAM access; deeptools for normalized coverage tracks.

Therapeutics Data Commons (TDC) AI-ready drug discovery datasets. Curated ADME, toxicity, DTI, DDI with scaffold/cold splits, standardized metrics, molecular oracles, and ADMET benchmarks for therapeutic ML and property prediction. For chemical database queries use chembl-database-bioactivity; for featurization use molfeat.

当用户需要系统、详细、完整地生成一篇可发布的 GEO 科普文章，并附带 How-to 教程、概念解释、购买/选择指南、避坑清单、FAQ、术语表、证据分级、读者场景、决策路径、品牌自然植入建议、真实数据核验附录，以及带固定目录菜单的 HTML 包、Word、PDF 和 Markdown 四格式报告时使用；适配 Kimi、千问、豆包、DeepSeek、元宝等国内 AI 搜索/问答平台；不用于榜单排行、整站诊断、页面审计、标题生成或无证据品牌软文。

当用户用一句话要求生成产品发布片、功能预告片、应用宣传片或网站展示视频时使用；从空白目录自动生成简报、设计规范、分镜、HyperFrames 源码和经过验收的 MP4，而不是重渲染仓库内已有案例。

Record browser or Web UI interaction demos as optimized GIFs using the available built-in browser, state-based frame capture, and deterministic encoding, then publish to a dedicated assets branch when the task includes attaching the GIF to a pull request. Use when asked to make, record, or generate a GIF that demonstrates a browser workflow, and for every pull request that changes product-user-visible GUI behavior, which MUST include a GIF recorded from the pull request's real server and model flow.

Read/write SAM/BAM/CRAM, VCF/BCF, FASTA/FASTQ. Region queries, pileup, variant filtering, read groups. Python htslib wrapper exposing samtools/bcftools CLI. Use STAR/BWA for alignment; GATK/DeepVariant for variant calling.

Pure Python DICOM for medical imaging (CT, MRI, X-ray, ultrasound). Read/write DICOM, pixels as NumPy, edit tags, windowing (VOI LUT), PHI anonymization, build DICOM, series→3D volumes. Use histolab for WSI pathology; nibabel for NIfTI.

Interactive visualization with Plotly. 40+ chart types (scatter, line, heatmap, 3D, geographic) with hover, zoom, pan. Two APIs: Plotly Express (DataFrame) and Graph Objects (fine control). For static publication figures use matplotlib; for statistical grammar use seaborn.

Interactive scientific visualization with Plotly. Two APIs: plotly.express (px) for one-liner DataFrame plots, plotly.graph_objects (go) for trace-level control. 40+ chart types with hover, zoom, pan, animation. Exports HTML or static PNG/SVG/PDF via kaleido. Use for volcano plots with gene hover, dose-response dashboards, expression heatmaps, 3D molecular views. Use seaborn for stats; matplotlib for publication figures.

LLM-driven hypothesis generation/testing on tabular data. Three methods: HypoGeniC (data-driven), HypoRefine (literature+data), Union. Iterative refinement, Redis caching, multi-hypothesis inference. Manual: hypothesis-generation; ideation: scientific-brainstorming.

Harmony batch correction for scRNA-seq and other omics. Removes batch effects from PCA embeddings while preserving biology. Run after PCA, before UMAP. Scales to millions of cells. Python (harmonypy, scanpy) and R (Seurat).

GSEA and over-representation analysis (ORA) for RNA-seq and proteomics. Wraps Enrichr for ORA against MSigDB, KEGG, GO, and 200+ databases; runs preranked GSEA on ranked DE gene lists. Outputs enrichment tables and running-score plots. Use after DESeq2 or edgeR for pathway-level interpretation.

All-in-one FASTQ QC and adapter trimming. Auto-detects Illumina adapters, filters low-quality reads, corrects paired-end overlaps, emits HTML+JSON QC in one pass. 3-10x faster than Trim Galore/Trimmomatic. First step before STAR, BWA-MEM2, or Salmon.

Protein language models (ESM3, ESM C) for sequence generation, structure prediction, inverse folding, and embeddings. Design novel proteins, extract ML features, or fold sequences. Local GPU or EvolutionaryScale Forge API. Use AlphaFold for traditional folding; RDKit for small molecules.

Automated scRNA-seq cell type annotation via pre-trained logistic regression. 45+ models: immune, gut, lung, brain, fetal, cancer microenvironments. Input normalized AnnData; outputs per-cell labels, majority-vote cluster labels, confidence scores. Use for fast, reference-backed annotation without manual marker inspection.

Infer and visualize intercellular communication from scRNA-seq with CellChat (R). Build CellChat from Seurat/counts → subset CellChatDB ligand-receptor pairs → over-expressed genes per group → communication probabilities → pathway signaling → network centrality (senders/receivers/influencers) → chord/heatmap/bubble plots → cross-condition compare. Human, mouse. Use liana for pure-Python.

Fast short-read DNA aligner for WGS/WES/ChIP-seq. 2× faster BWA-MEM successor; outputs SAM/BAM with read group headers for GATK. Primary plus supplementary records for chimeric reads. Use STAR for RNA-seq splice-aware alignment; Bowtie2 is a comparable alternative.

CLI for VCF/BCF: filter, merge, annotate, query, normalize, compute stats. Core post-variant-calling: quality filtering, multi-sample merging, rsID annotation, genotype extraction. Samtools companion in HTSlib. Use GATK for complex indel realignment during calling; use VCFtools for population genetics stats.

API + Python SDK for ordering cell-free protein expression and binding assays. Submit sequences for expression (10–100 µg), measure binding affinity (KD) against targets, track status, and retrieve results programmatically — no wet-lab setup. Built for ML-guided directed evolution and antibody/nanobody optimization. Requires Adaptyv account and API key.

Extract medical entities (symptoms, medications, lab values, diagnoses) from patient messages.

Real-time hand detection in egocentric videos using victordibia/handtracking. Outputs bounding boxes for hands, specifically trained on EgoHands dataset. Supports video input/output with labeled hand boxes. Lightweight and fast for egocentric view applications.

High-quality 3D hand pose estimation for egocentric videos from ECCV 2024 (ap229997/hands). Provides 3D joint keypoints and skeleton visualization projected to 2D. Optimized for daily egocentric activities with state-of-the-art accuracy. Outputs hand skeleton overlays on video frames.

Egocentric Hand-Object Segmentation (EgoHOS) - pixel-level hand and object segmentation in egocentric videos. Outputs fine-grained segmentation masks with hand regions highlighted. Specialized for hand-object interaction scenarios with pixel-accurate masks. Ideal for detailed interaction analysis.

Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like "what if...", "what would happen if...", "what are the possibilities", "explore scenarios", "scenario analysis", "possibility space", "what could go wrong", "best case / worst case", "risk analysis", "contingency planning", "strategic options", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.

Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, run energy minimization and production MD, analyze trajectories (RMSD, RMSF, contact maps, free energy surfaces). For structural biology, drug binding, and biophysics.

Extract cognitive patterns and thinking fingerprints from any text. Use this skill when the user wants to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, compare thinking styles between people, asks "what's my thinking style", "analyze how this person reasons", "cognitive profile", "thinking pattern", "DHDNA", "digital DNA", or wants to understand the mind behind any text. Also trigger when the user provides text and wants deeper insight into the author's reasoning patterns, decision-making style, or cognitive signature.

Annotate VCF variants with Ensembl VEP REST, ClinVar significance, gnomAD/population frequency context, and prioritized variant ranking.

Semantic search across UK Biobank's 12,000+ data fields and publications — find the right variables for your research question.

Build, query, and analyse biomedical knowledge graphs in TuringDB, a columnar graph database with git-like versioning.

Evidence-grounded target validation scoring with GO/NO-GO decisions for drug discovery campaigns

Protein structure prediction with Boltz-2. Accepts YAML inputs (single protein or multi-chain complex), runs boltz predict, extracts per-residue pLDDT and PAE confidence, and writes a markdown report with figures.

Compile SOUL.md character profiles into synthetic diploid genomes (.genome.json) via trait-to-allele mapping

Local Scanpy pipeline for single-cell RNA-seq QC, optional doublet detection, clustering, marker discovery, optional CellTypist annotation, optional latent downstream mode from integrated.h5ad/X_scvi, and optional dataset-level plus within-cluster contrastive marker analysis from raw-count .h5ad or 10x Matrix Market input.

Local scVI/scANVI-based single-cell latent embedding and batch-aware integration from raw-count .h5ad or 10x Matrix Market input, with stable integrated AnnData export for downstream latent analysis.

Differential expression analysis for bulk RNA-seq and pseudo-bulk count matrices with QC, PCA, and contrast testing.

Export any bioinformatics analysis as a reproducible bundle with Conda environment, Singularity container definition, and Nextflow pipeline.

Produce offspring genomes from parent pairs via meiotic recombination, mutation, and clinical evaluation

Search PubMed for a gene name or disease term and generate a structured research briefing of the top recent English-language papers.

Differential expression analysis for label-free quantitative (LFQ) intensity data with standard MaxQuant and DIA-NN output. Workflow includes preprocessing, imputation, and statistical testing.

Unified personal genomic profile report — reads a PatientProfile JSON and synthesizes all skill results into a single "Your Genomic Profile" document.

Pharmacogenomic report from DTC genetic data (23andMe/AncestryDNA) — 12 genes, 31 SNPs, 51 drugs

Aggregate public target-level evidence across omics and translational sources for research triage.

Personalised nutrition report from consumer genetic data (23andMe, AncestryDNA, VCF) — interrogates nutritionally-relevant SNPs and generates actionable dietary guidance, all computed locally.

Wrapper skill for running nf-core/rnaseq bulk RNA-seq preprocessing from FASTQ or BAM inputs with strict preflight, reproducibility outputs, and downstream handoff to ClawBio bulk RNA-seq DE skills.

Aggregates QC reports from any bioinformatics tool outputs (FastQC, fastp, STAR, Picard, samtools, etc.) into a single MultiQC HTML report plus a ClawBio markdown summary with per-sample QC metrics.

Two-sample Mendelian Randomisation from GWAS summary statistics with IVW, MR-Egger, weighted median/mode, and full sensitivity analysis (Cochran Q, Egger intercept, Steiger, F-statistic, leave-one-out).

Search PubMed and bioRxiv for bioinformatics literature, synthesise results into a structured report, and build a citation graph — all locally, with a reproducibility bundle.

Import DRAGEN-exported Illumina result bundles into ClawBio for local tertiary analysis and downstream routing.

Calculate polygenic risk scores from DTC genetic data using the PGS Catalog

End-to-end GWAS automation wrapping PLINK2 for genotype QC and REGENIE for two-step whole-genome regression association testing. Produces Manhattan plots, QQ plots, clumped lead variants, and structured summary statistics.

Federated variant lookup across 9 genomic databases — GWAS Catalog, Open Targets, PheWeb (UKB, FinnGen, BBJ), GTEx, eQTL Catalogue, and more.

Fetch a region of GWAS summary statistics from the NHGRI-EBI GWAS Catalog harmonised collection via tabix-on-FTP. Use when an agent needs GWAS beta / SE / p-value for every variant in a window for one specific study (GCST accession). Input: accession, chromosome, start, end. Output: harmonised TSV slice in canonical format.

Score genetic compatibility across all male-female pairings in a Genomebook generation

Flow.bio API bridge — authenticate, browse pipelines/samples/projects, search, upload data, launch pipeline executions, and check run status on any Flow instance.

Statistical fine-mapping of GWAS loci using SuSiE, SuSiE-inf, and Approximate Bayes Factors to identify credible sets and posterior inclusion probabilities (PIPs) for causal variant discovery. SuSiE-inf adds an infinitesimal polygenic component for improved calibration at well-powered loci.

Compute HEIM diversity and equity metrics from VCF or ancestry data. Generates heterozygosity, FST, PCA plots, and a composite HEIM Equity Score with markdown reports.

Fetch a region of cis-eQTL summary statistics from EBI eQTL Catalogue v7+ via tabix-on-FTP. Use when an agent needs eQTL beta / SE / p-value for every variant in a window around a gene's TSS for one specific dataset (study × tissue × quantification method). Input: dataset_id, chromosome, start, end, optional molecular_trait_id. Output: harmonised TSV slice.

Medication photo to personalised PGx dosage card via Claude vision — snap a pill, get genotype-informed guidance