Top Agent Skills

Train unsupervised machine learning models on genomic interval data from BED files, including region embeddings, single-cell ATAC-seq analysis, and consensus peak building.

Perform numerical computing, matrix operations, data analysis, and scientific visualization using MATLAB or GNU Octave.

Submit protein sequences to the Adaptyv Bio Foundry for experimental characterization (binding, thermostability, expression, fluorescence) and retrieve results via API or Python SDK.

Perform constraint-based metabolic modeling with COBRApy: run FBA, FVA, gene knockouts, flux sampling, and manage SBML models for systems biology and metabolic engineering.

Simplify molecular cheminformatics with a Pythonic wrapper around RDKit for SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, and parallel processing.

Manage biological datasets and models with LaminDB, an open-source lineage-native lakehouse. Covers setup, artifact registration, query/search, lineage tracking, validation, ontology-backed annotation, collections, branches, storage, and workflow integrations.

Process and analyze mass spectrometry data: import spectra from MGF, mzML, MSP, and JSON formats; apply 40+ filters for metadata harmonization and peak cleaning; compute spectral similarities (cosine, modified cosine) for compound identification; build reproducible processing pipelines.

Apply medicinal chemistry filters for compound triage: drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and a custom query language for library filtering.

Convert chemical structures (SMILES or RDKit molecules) into numerical representations for machine learning using 100+ featurizers, including ECFP, MACCS, descriptors, and pretrained models like ChemBERTa.

Query the 1000 Genomes Project dataset at the individual participant level to find variants, carriers, and relatedness information.

Infer gene regulatory networks from gene expression data using scalable algorithms (GRNBoost2, GENIE3) with support for distributed computation.

Predict molecular properties, train graph neural networks, and run drug discovery workflows using DeepChem's featurizers, models, and MoleculeNet benchmarks.

Predict 3D binding poses of small molecule ligands to protein targets using diffusion-based molecular docking, supporting single complexes, batch processing, and virtual screening.

Build, run, and debug Nextflow data pipelines and nf-core workflows end to end, covering processes, channels, operators, configuration, testing, and deployment to HPC or cloud.

Install, configure, and extend Pi, a terminal coding harness, with support for custom providers, models, extensions, skills, packages, themes, SDK integration, RPC mode, JSON event streams, and ecosystem packages for subagent delegation, MCP servers, interactive forms, and web access.

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

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

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

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.

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.

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

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

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).

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

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

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.

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

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

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.

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.

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.

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.

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

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.

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

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.

Access microscopy images and metadata via the OMERO Python API: retrieve datasets, analyze pixels, manage ROIs and annotations, and batch-process for high-content screening workflows.

Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard, MLflow), and distributed training (DDP, FSDP, DeepSpeed) for scalable neural network training.

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).

Run pathway and gene-set enrichment analysis on gene lists or ranked gene data, then interpret the results. Covers over-representation analysis (ORA), Gene Set Enrichment Analysis (GSEA), and single-sample scoring using gseapy, g:Profiler, and Enrichr libraries.

Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.

Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries.

Write Opentrons Protocol API v2 protocols for Flex and OT-2 robots to automate liquid handling, control hardware modules, and manage labware configurations.

Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase.

Handles git and GitHub operations using the gh CLI, triggered by any github.com URL. Covers creating and reviewing PRs, watching CI checks, interactive rebasing, branch cleanup, submodule management, and repository archaeology.

Provides deep expertise in Node.js internals: V8 engine, libuv event loop, native addon development, build systems, and performance debugging.

Generate polished code snippet images with syntax highlighting, supporting PNG, SVG, and WebP exports via the snipgrapher CLI.

Designs complex generic types, refactors `any` types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors.

Configures ESLint v9 flat config and neostandard for JavaScript and TypeScript projects, including migrating from legacy .eslintrc files or the standard package.

Collect and parse forensic artifacts from Windows systems using KAPE for rapid DFIR triage.

Detect anomalies in DNP3 protocol communications used in SCADA systems by monitoring for unauthorized control commands, firmware update attempts, protocol violations, and deviations from baseline traffic patterns using deep packet inspection and machine learning approaches.

Identify and exploit OAuth 2.0 and OpenID Connect misconfigurations including redirect URI manipulation, token leakage, and authorization code theft during authorized security assessments.

Test web applications for Cross-Site Request Forgery vulnerabilities by crafting forged requests that exploit authenticated user sessions during authorized security assessments.

Systematically test web applications for broken access control vulnerabilities including privilege escalation, missing function-level checks, and insecure direct object references.

Detect compromised O365 and Google Workspace email accounts by analyzing inbox rule creation, suspicious sign-in locations, mail forwarding rules, and unusual API access patterns via Microsoft Graph and audit logs.

Detects DNS tunneling by computing Shannon entropy of DNS query names, analyzing query length distributions, inspecting TXT record payloads, and identifying high subdomain cardinality using scapy for packet capture analysis.

Test web application email functionality for SMTP header injection vulnerabilities that allow attackers to inject additional email headers, modify recipients, and abuse contact forms for spam relay.

Detect DNS tunneling and data exfiltration by analyzing Zeek dns.log for high-entropy subdomain queries, excessive query volume, long query lengths, and unusual DNS record types indicating covert channel communication.

Provides a structured framework for analyzing cyber intrusions by examining four core features: Adversary, Capability, Infrastructure, and Victim. Covers implementing the Diamond Model programmatically to classify and correlate intrusion events, build activity threads, and generate pivot-ready intelligence.

Perform coverage-guided fuzzing of compiled binaries using AFL++ to discover memory corruption, crashes, and security vulnerabilities.