Data skills

Extracts clean Markdown from HTML pages with the Defuddle CLI.

Molecular biology toolkit: sequence manipulation, FASTA, GenBank and PDB parsing, phylogenetics and NCBI access.

Runs exploratory analysis on scientific data files: profiles, missing-data audits and outlier checks.

Reference for Matplotlib: fine-grained control over plot elements and export to PNG, PDF or SVG for publication.

Creates, analyses and visualises networks and graphs in Python with NetworkX.

Reference for Polars, the Python DataFrame library: expressions, lazy queries, streaming and migration from pandas.

Builds Bayesian models with PyMC: hierarchical models, MCMC, variational inference and model comparison.

Cheminformatics with RDKit: SMILES parsing, molecular descriptors, fingerprints, substructure search and reactions.

Runs the standard single-cell RNA-seq pipeline with Scanpy: QC, normalisation, clustering and differential expression.

Creates and audits publication-ready scientific figures with Matplotlib, Seaborn or Plotly.

Machine learning in Python with scikit-learn: classification, regression, clustering, model evaluation and tuning.

Statistical visualisation with Seaborn: distributions, relationships and categorical comparisons.

Guides statistical analysis of research data: test selection, assumption checks, effect sizes and APA-formatted reporting.

Statistical modelling with statsmodels: OLS, GLM, mixed models and ARIMA, with diagnostics and inference.

Creates and edits Jupyter notebooks for experiments, explorations and tutorials from bundled templates.

Fetches any URL and converts it to markdown through Chrome, with adapters for X, YouTube transcripts and Hacker News.

Creates reports from Google Analytics properties with the Analytics Data API.

Manages BigQuery datasets, tables and jobs, and runs SQL queries for basic ingestion and analysis.

Creates and explains Cloud SQL instances and databases for MySQL, PostgreSQL and SQL Server.

Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai and lighteval.

Works with the Hugging Face Dataset Viewer API: split metadata, row pagination, text search, filters and parquet downloads.

Tracks and visualises ML training experiments with Trackio: logged metrics, alerts and a live dashboard.

Postgres best practices maintained by Supabase, for schema changes, queries, indexes and security on any Postgres.

Designs SQL and NoSQL database schemas: normalisation, indexing, constraints and migration patterns.