Skip to content

Skill catalog

Each skill is a folder with a SKILL.md that an agent loads when a task matches its description. This page is generated from each skill's frontmatter when the site is built.

Skill What it does Version Evaluation
bulk-rnaseq Find top differentially expressed genes from bulk RNA-seq counts 1.0.0 Report
open-weight-models Package, register, validate & deploy open-weight HLS models on Databricks, such as TEDDY and Geneformer 1.0.0 Report
pathway-enrichment-analysis Pathway enrichment for RNA-seq (ORA or GSEA) 1.0.0 Pending
sc-rnaseq Analyze single-cell RNA-seq data from .h5ad files 1.0.0 Evidence
cohort-builder Build a reproducible, feasibility-checked patient cohort from coded + free-text clinical data 1.0.0 Report
phi-deidentifier HIPAA Safe-Harbor de-identify a Unity Catalog table (k-anonymity + governed view) 1.0.0 Report
rwe-cohortstudy Comparative effectiveness (cohort study) with propensity adjustment (matching, IPW) 1.0.0 Report
semantic-builder Canonical payer+provider measure catalog mapped to Unity Catalog metric views 1.0.0 Pending
accelerators Route imaging, biology-model and HL7v2 tasks to an HLS accelerator (Pixels, Genesis Workbench or funke-hl7v2) with the exact next step 1.0.0 Report
presentation-builder Turn a cohort, dataset, model, or analysis into a grounded, shareable HTML deck (PHI de-id delegated to phi-deidentifier) 1.0.0 Pending
report-builder LaTeX report generation and PDF compilation from analysis notebooks via Tectonic 1.0.0 Pending
scientific-figures Publication-quality scientific and biopharma figures for notebooks, apps, and reports 1.0.0 Pending
skill-eval Benchmark a skill: paired runs with/without it, MLflow genai.evaluate scoring, win/loss + failure taxonomy 1.0.0 Pending

Evaluation: Report links a paired with/without-skill comparison, Evidence links benchmark files without a report yet, and Pending means no evaluation has been committed. See Evaluation.