Latest Agent Skills

Conduct systematic literature reviews by searching multiple academic databases, synthesizing findings, and generating professionally formatted documents with verified citations.

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server, returning 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions.

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, and other RAPIDS libraries for dramatic speedups on numerical, data, ML, graph, and simulation workloads.

Analyze and engineer protein glycosylation by scanning sequences for N-glycosylation sequons, predicting O-glycosylation hotspots, and accessing curated glycoengineering tools for therapeutic antibody optimization and vaccine design.

Submit and manage protocols on Ginkgo Bioworks Cloud Lab for autonomous lab execution, including protein expression, purification, quantification, RNA synthesis, and custom workflows via EstiMate.

Generate comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports, clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries) with templates, regulatory compliance, and validation tools.

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data, enabling efficient access to cell metadata, gene expression slices, summary counts, and embeddings without downloading whole datasets.

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues, academic conferences, research posters, and grant proposals.

Generate concise (3-4 page) medical treatment plans in LaTeX/PDF format across all clinical specialties, with SMART goals, evidence-based interventions, and HIPAA compliance.

Build and train graph neural networks with PyTorch Geometric, covering node/link/graph classification, message passing layers, heterogeneous graphs, and custom datasets.

Perform survival analysis and time-to-event modeling in Python using scikit-survival, including Cox models, random survival forests, gradient boosting, survival SVMs, and evaluation metrics like concordance index and Brier score.

Look up current research and scientific information across three backends: fast web search, deep multi-source synthesis, and scholarly paper searches. Automatically routes each query to the best backend and saves every result for reproducible citation.

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC with agency-specific formatting, review criteria, budget preparation, and compliance guidance.

Discovers and uses scientific datasets, models, blog posts, and interactive demos from a curated catalog for AI/ML work in domains like biology, chemistry, physics, and genomics.

Query documented public database APIs with explicit endpoints, filters, pagination, and provenance for reproducible retrieval of scientific, regulatory, or financial facts.

Run structured What-If scenario analysis with 4-6 branch possibility exploration (best, likely, worst, wild card, contrarian, second-order). Use for speculative questions about uncertain futures, strategic forks, contingency planning, or stress-testing decisions.

Generate and edit high-quality images using OpenRouter's AI models including FLUX.2 Pro and Gemini 3.1 Flash Image Preview.

Analyze any text to extract a cognitive fingerprint across 12 dimensions, revealing reasoning patterns, decision styles, and thinking signatures.

Build and analyze phylogenetic trees using MAFFT, IQ-TREE 2, and FastTree, with visualization via ETE3 or FigTree for evolutionary analysis, microbial genomics, viral phylodynamics, and molecular clock studies.

Self-host an open-source research notebook with AI-powered note generation, multi-speaker podcast creation, and context-aware document chat, supporting 16+ AI providers.

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter with layout design, color schemes, multi-column formats, and figure integration.

Query the U.S. Treasury Fiscal Data REST API for federal financial data including national debt, daily and monthly treasury statements, securities auctions, interest rates, exchange rates, savings bonds, and government revenue and spending statistics. No API key required.

Load pre-trained models from Hugging Face Hub, run pipeline inference, generate text, and fine-tune models on NLP, vision, audio, and multimodal tasks using the Transformers library.

Build and evaluate machine learning models using scikit-learn for classification, regression, clustering, dimensionality reduction, and preprocessing.

Create research posters using HTML/CSS that can be exported to PDF or PPTX, with AI-generated visual elements and responsive layouts.

Search the web, extract URL content, enrich datasets with web-sourced fields, and run deep research reports, prioritizing academic and scientific sources.

Search 10 academic literature APIs for papers, preprints, citations, and open-access full text with reproducible provenance.

Generate publication-quality infographics using Nano Banana Pro AI with Gemini 3 Pro quality review and optional Perplexity Sonar research. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.

Store and process large N-dimensional arrays with chunking, compression, and parallel I/O, integrating with NumPy, Dask, and Xarray for cloud-native scientific computing.

Fit statistical models (OLS, GLM, ARIMA, mixed models) with detailed diagnostics, residuals, and inference for econometrics and time series analysis.

Evaluate scientific manuscripts and grant proposals with structured, checklist-based peer review covering methodology, statistics, reproducibility, ethics, and reporting standards.

Orchestrates a complete bulk RNA-seq differential-expression study from raw FASTQ reads through QC, alignment, quantification, differential expression, pathway enrichment, and publication figures.

Query 40+ bioinformatics services (UniProt, KEGG, ChEMBL, Reactome) with a unified Python interface for cross-database analysis, identifier mapping, and sequence analysis.

Perform nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows using the umap-learn library.

Provides deep generative models for single-cell omics analysis, including probabilistic batch correction, transfer learning, differential expression, and multi-modal integration.

Analyze biological sequences, alignments, phylogenetic trees, and diversity metrics (alpha/beta, UniFrac) with ordination (PCoA) and PERMANOVA for microbiome and community ecology data.

Control liquid handling robots, plate readers, pumps, and other lab equipment through a unified Python interface across platforms.

Perform high-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames, including overlap, nearest, merge, coverage, complement, subtract, and reading/writing BED, VCF, BAM, GFF, FASTA, and FASTQ formats with streaming and cloud-native support.

Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Fetch feeds, read papers, leave feedback, and export data using the pz CLI.

Validates inputs, generates samplesheets and launch scripts, and optionally executes nf-core/pacsomatic matched tumor-normal workflows from BAM files, supporting local runs and scheduler submission (LSF/Slurm/PBS/SGE).

Create publication-quality static, animated, and interactive plots with fine-grained control over every element using Matplotlib's pyplot and object-oriented APIs.

Convert files and office documents to Markdown using Microsoft's MarkItDown tool. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.

Search the web and extract content from URLs using Exa, with support for academic and scientific sources.

Manipulate phylogenetic trees, detect evolutionary events, integrate NCBI taxonomy, and create publication-quality visualizations using the ETE toolkit.

Build and train graph neural networks for drug discovery, protein modeling, and molecular science using PyTorch-native tools.

Store, query, and export genomic variant data (VCF/BCF) using TileDB's sparse array technology for scalable population genomics workflows.

Train reinforcement learning agents at millions of steps per second using optimized PPO, vectorized environments, and multi-agent support.

Train quantum circuits like neural networks with automatic differentiation, device-independent programming, and integration with PyTorch or JAX.

Process and analyze physiological signals including ECG, EEG, EDA, RSP, PPG, EMG, and EOG using Python.

Parse PDFs, Office files, and images locally with layout-preserved text, bounding boxes, OCR, and page screenshots for RAG and multimodal agents.

Automates hypothesis generation and testing on tabular datasets using LLMs, combining data-driven discovery with literature integration for scientific research.

Extends pandas for geospatial vector data analysis, including reading/writing shapefiles, GeoJSON, GeoPackage, and PostGIS, performing spatial joins, geometric operations, coordinate transformations, and creating static or interactive maps.

Process satellite imagery, perform GIS analysis, and apply spatial machine learning across 70+ geospatial topics with code examples in 8 programming languages.

Process and analyze high-throughput sequencing data with deepTools for quality control, normalization, comparison, and publication-quality visualizations of ChIP-seq, RNA-seq, and ATAC-seq experiments.

Manipulate biological sequences, parse FASTA/GenBank/PDB files, access NCBI databases, run BLAST searches, and perform phylogenetics using the Biopython library.

Analyze recent screen activity via a local screenpipe daemon, detect repeated research workflows, and draft new skills or composition recipes for uncovered patterns.

Run computational biology tools for protein structure prediction, design, docking, and molecular dynamics on managed cloud GPUs via REST API or MCP server.

Manage Zotero reference libraries programmatically using the pyzotero Python client. Retrieve, create, update, and delete items, collections, tags, and attachments via the Zotero Web API v3.

Analyze proteomics and metabolomics mass spectrometry data with PyOpenMS: read/write MS file formats, process spectra, detect and quantify features, identify peptides and proteins, and run end-to-end LC-MS/MS pipelines using ready-to-run scripts.

Analyze and manipulate crystal structures, compute phase diagrams, and access the Materials Project database using the pymatgen library.