All skills

Writes and debugs TorchDrug 0.2.1 code for molecular property prediction, generation, retrosynthesis, protein encoders, and knowledge graph reasoning.

A research-only skill for using PathML 3.0.5 to tile slides, build preprocessing/QC pipelines, quantify multiplex images, construct spatial graphs, and plan bounded local inference.

Guides Claude to analyze, edit, compare, annotate, and visualize existing phylogenetic trees with ETE 4.4.0.

Plans, audits, and cost-bounds ChicagoHAI HypoGeniC/HypoRefine hypothesis-generation runs entirely locally before any LLM call.

Version-aware guidance for PufferLib RL work — environment adaptation, vectorization, PuffeRL training, and safe checkpoint review across the 3.0.0 release and 4.0 source line.

Triage compound libraries with drug-likeness rules (Lipinski, Veber, CNS), PAINS/NIBR structural alerts, complexity metrics, and the medchem query language.

A skill for cleaning, filtering, comparing, and library-searching MS/MS spectra with the current matchms 0.33.1 API.

An end-to-end SpikeInterface workflow for Neuropixels recordings: loading, preprocessing, drift correction, spike sorting, quality metrics, and unit curation.

A routing-style skill for installing, configuring, and building on Pi, the minimal terminal coding harness.

A skill for building, running and monitoring reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets and workflow importers.

A Geniml-focused skill that validates BED/universe contracts and plans Region2Vec, scEmbed, and consensus-universe runs with safety and compatibility checks.

A skill for doing genomic interval set algebra, coverage, tokenization, and refget work with gtars (Python/Rust/CLI) under exact version pins and explicit safety gates.

Structures scope, controlled documents, traceability, CAPA and supplier evidence into a reviewable draft package for ISO 13485, 14971, 17025 and 15189.

Safely inspect, export, and plan microscopy data workflows on an OMERO.server using omero-py, the OMERO CLI, and bounded dry-run helpers.

A guide skill for running DeepSpot-M to predict transcriptome-wide spatial gene expression from H&E histology tiles.

A skill for storing, ingesting, querying and exporting VCF/BCF variant data on TileDB sparse arrays for population genomics.

Build Word papers from official templates and convert full LaTeX manuscripts into DOCX with editable native equations, plus strict validation.

A three-role pipeline (modeler → coder → paper writer) that solves math-modeling competition problems end to end with independent QA gates.

An interactive wizard that designs a chaos engineering experiment, computes blast radius, and emits a peer-reviewable markdown plan.

Turns a contest problem, modeling analysis and real code results into a complete, validated Word (optionally LaTeX) math-modeling paper.