Search Skills

Helps teams recognize productive disagreements and maintain multiple valid approaches without forcing premature resolution.

Detects system resources and provides strategic recommendations for computational approaches in scientific tasks.

Downloads YouTube video transcripts from URLs or user requests, enabling quick access to video content for reference and analysis.

Provides fast nonlinear dimensionality reduction using UMAP for 2D/3D visualization and clustering preprocessing of high-dimensional data.

Builds and deploys bioinformatics pipelines using Latch SDK with Nextflow/Snakemake integration for data processing workflows.

Enables fine-tuning, inference, and training of transformer-based models for NLP, computer vision, and multimodal AI tasks using HuggingFace.

Query and analyze the CZ CELLxGENE Census database for single-cell expression data with cell type, tissue, and disease filtering, integrating with scanpy and PyTorch.

Automates access to Benchling R&D platform data including biological registries, inventory, ELN entries, and workflows via API for lab data management.

Provides access to ClinPGx pharmacogenomics database for querying gene-drug interactions, CPIC guidelines, and allele functions to support precision medicine decisions.

Provides automated metrics, human feedback, and benchmarking for evaluating LLM application performance and quality.

Extracts flow cytometry data from FCS files, converting events and metadata into structured NumPy arrays and DataFrames for analysis.

Efficiently searches and retrieves life sciences preprints from bioRxiv with keyword, author, date, and category filters for literature reviews.

Generates algorithmic art using p5.js with seeded randomness, flow fields, and particle systems for creative visualizations.

Comprehensive toolkit for developing, testing, and deploying machine learning models using clinical data, EHR, and healthcare datasets like MIMIC.

Queries PubChem chemical database for compound properties, similarity, and bioactivity using PUG-REST or PubChemPy APIs.

Queries ChEMBL database for bioactive molecules, drug discovery data, and supports SAR studies in medicinal chemistry.

Enables genomics pipeline development and execution on DNAnexus, including data management, workflow runs, and dxpy SDK integration for FASTQ/BAM/VCF processing.

DeepTools is a genomic analysis toolkit for converting BAM to bigWig, performing QC, and generating visualizations for ChIP-seq, RNA-seq, and ATAC-seq data.

Provides AI-ready drug discovery datasets including ADME, toxicity, DTI benchmarks, scaffold splits, and molecular oracles for therapeutic ML models.

Traces historical evolution of ideas to identify reusable solutions and prevent recurrence of past failures in problem-solving.

Provides access to and analysis of comprehensive drug data from DrugBank, including properties, interactions, targets, and pharmacology for research and discovery.

Extracts clean, ad-free article content from URLs and saves as readable text for easy reference and offline use.

Provides tools for sequence analysis, phylogenetic trees, microbiome diversity metrics, and statistical tests like UniFrac and PERMANOVA.

Ensures wiki documentation health by verifying link integrity, naming consistency, cross-references, and topic coverage.