Data Science & ML Agent Skills

Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr…

Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al. 2025…

Analyze ML experiment results, compute statistics, generate comparison tables and insights.

Monitor running experiments, check progress, collect results.

CAMB cosmological perturbation skill for CMB power spectra, matter power spectra, and cosmological parameter estimation

SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial…

Clean and reshape Qualtrics conjoint exports to analysis-ready long format.

Design conjoint experiments: attributes, power, AMCE/AMIE estimation.

Diagnose conjoint design integrity, estimation choices, and validity.

Creates a Jupyter notebook with Jupytext pairing and registers it in _quarto.yml.

Audit datasets for structure, missingness, labeling, suspicious values, duplicate identifiers, and documentation readiness.

Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

Deploy and query Databricks Model Serving endpoints.

Generate realistic synthetic data using Spark + Faker (strongly recommended).

DeepVariant deep learning variant calling skill for high-accuracy SNV and indel detection

Delphes fast detector simulation skill for phenomenological studies and BSM searches

Embed proteins with Meta AI's ESM-2 (`fair-esm` package).

Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023…

Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer…