Vital Skills: Upskilling Genie Code with Healthcare and Life Sciences skills

Databricks released Vital Skills, an open-source set of packaged playbooks built on the Agent Skills standard that give its Genie Code coding agent healthcare and life sciences domain knowledge. On BiomniBench, a public benchmark of biomedical data-analysis tasks graded against expert-written rubrics, Genie Code with Vital Skills scored higher on relevant tasks and showed no negative impact on out-of-scope tasks, after the agent alone parsed documents and generated charts but sometimes fell short on domain-specific methodology and over-assumed. Databricks said Genie Code outperforms a leading coding agent by more than twice on real-world data tasks, and that the starter skill set, including a bulk-rnaseq skill for finding top differentially expressed genes from bulk RNA-seq counts, is expected to grow via contributions to its open-source repository.

Accelerate healthcare and life sciences workflows with AI coding and skills by Zachary Phillips https://www.databricks.com/blog/author/zachary-phillips , May Merkle-Tan https://www.databricks.com/blog/author/may-merkle-tan , Praneeth Paikray https://www.databricks.com/blog/author/praneeth-paikray , Peter Hawkins https://www.databricks.com/blog/author/peter-hawkins , Vimal Thomas Joseph https://www.databricks.com/blog/author/vimal-thomas-joseph , Rohan Parikh https://www.databricks.com/blog/author/rohan-parikh and Yen Low https://www.databricks.com/blog/author/yen-low Genie Code https://www.databricks.com/blog/introducing-genie-code , our coding agent optimized for Databricks, allows you to chat instead of code to perform your data and AI tasks https://www.databricks.com/blog/why-frontier-data-agent-outperforms-general-coding-agents-quality-and-cost . Critically, Genie Code’s integration with Unity Catalog ensures that the agent understands your enterprise’s data and follows the same security and governance rules as the rest of the Databricks platform. Thus, Genie Code significantly outperforms a leading coding agent by more than twice https://www.databricks.com/blog/introducing-genie-code on real-world data tasks such as exploratory data analysis, machine/deep learning, creating dashboards, agents, apps, declarative automation bundles, Lakeflow jobs and scheduling them. However, Genie Code and other general AI coding assistants lack domain specificity and assume generic methods and clinical thresholds that do not meet healthcare and life sciences HLS standards or best practices. Databricks Vital Skills https://databricks-industry-solutions.github.io/vital-skills/ bridges this gap by providing packaged playbooks built in the open Agent Skills https://agentskills.io/specification standard. They equip AI coding agents with industry knowledge so agents know which questions to ask, which steps are non-negotiable, and which tested tools to use. Vital Skills is designed for Genie Code to make the best use of the unified Databricks ecosystem https://www.databricks.com/product/platform so generated code is not disconnected from your governed data, and you're not left to stand up serving, GPUs, governance, and scheduling yourself. You get a system, not just a sandbox. With the Databricks ecosystem, you: We tested Genie Code with and without Vital Skills on BiomniBench https://huggingface.co/datasets/phylobio/BiomniBench-DA , a public benchmark of biomedical data-analysis tasks graded against expert-written rubrics https://www.biorxiv.org/content/10.64898/2026.05.12.724604v2.full . Genie Code alone rarely failed on the obvious parts. It parsed documents and generated charts with ease. However, it sometimes fell short on domain-specific methodology and knowledge and was prone to overassumptions. With Vital Skills, Genie Code scored higher on the relevant tasks https://github.com/databricks-industry-solutions/hls-skills/blob/main/benchmarks/biomnibench/tasks.json L11 and had no negative impact on tasks that were out of scope of Vital Skills. Each skill started with a field engineer who had solved the problem several times with customers. We held on to three principles: Vital Skills puts the know-how of a biostatistician, privacy officer, bioinformatician, or actuary directly in the hands of every analyst, helping teams move faster before engaging additional expertise. The Databricks Healthcare and Life Sciences field team has built skills across the industry, covering key steps in data processing, analysis, model life cycle management, evaluation, report and slide generation. These skills can be used directly, or further customized to your needs and to leverage your deep expertise in your discipline. We expect this starter set of skills to grow over time and welcome contributions to the open source repository https://github.com/databricks-industry-solutions/vital-skills . | Skill | What it does | |---|---| | Bioinformatics | | | bulk-rnaseq | Find top differentially expressed genes from bulk RNA-seq counts. | | open-weight-models | Package, register, validate & deploy open-weight HLS models on Databricks, e.g. TEDDY and Geneformer. | | pathway-enrichment-analysis | Pathway enrichment for RNA-seq ORA or GSEA . | | sc-rnaseq | Analyze single-cell RNA-seq data from .h5ad files. | | Clinical | | | cohort-builder | Build a reproducible, feasibility-checked patient cohort from coded + free-text clinical data. | | rwe-cohortstudy | Comparative effectiveness cohort study with propensity adjustment matching, IPW . | | semantic-builder | Build a semantic layer like Metric Views using 64 common measures from EHR or claims so they are dashboard or agent ready | | phi-deidentifier | HIPAA Safe-Harbor de-identify a Unity Catalog table k-anonymity + governed view . | | Others | | | presentation-builder | Build presentation-ready slides | | report-writer | Move your analysis methods and results to a report | | accelerators | Route to a relevant HLS accelerator or library with the right tools for your task | | skill-eval | Benchmark a skill: paired runs with/without it, MLflow genai.evaluate scoring, win/loss + failure taxonomy. | Go from data to a finished report https://databricks-industry-solutions.github.io/vital-skills/guide/skills/report-builder/ or agent or dashboard seamlessly on Databricks. For example, our semantic-builder skill https://databricks-industry-solutions.github.io/vital-skills/guide/skills/payer-provider-measure-catalog/ defines and computes commonly used metrics https://github.com/databricks-industry-solutions/vital-skills/blob/main/skills/semantic-builder/references/catalog.md e.g. length of stay into a Metric View https://docs.databricks.com/aws/en/uc-semantics/metric-views/ from claims or electronic health records. Once Metric Views are defined in Unity Catalog, you can easily re-use them across multiple tools https://docs.databricks.com/aws/en/uc-semantics/metric-views/query consume-metric-views-in-tools like dashboards, Genie Agents, external BI or spreadsheets. In the following sections, we will dive into a couple of key skills. An analyst describes a population in plain language — "patients with type 2 diabetes and uncontrolled blood sugar" — and the skill turns that into a cohort they can reproduce, explain, and defend. Cohort building is an integral starting point for nearly every analytics effort: RWE studies, clinical-trial feasibility, payer care-management and population-health outcomes research. After building cohorts, consider comparative effectiveness studies https://databricks-industry-solutions.github.io/vital-skills/guide/skills/rwe-cohortstudy/ and share your results using the presentation-builder https://databricks-industry-solutions.github.io/vital-skills/guide/skills/presentation-builder/ . Some of the most promising AI applications for life sciences are open source biological foundation models that encode single-cell transcriptomics Geneformer, scGPT, Scimilarity, TEDDY or protein structure AlphaFold/OpenFold, Boltz2, etc . They are also difficult to get running, requiring specialized infrastructure and abilities. Because this skill summons the appropriate code, libraries and GPU serving, a scientist can go from “I need this model" to serving a governed model that one can actually use. Along the way it: On a TEDDY single-cell model deployment task, Genie Code without the skill wrote correct code but missed key deployment-readiness steps — pinned dependencies, a post-registration smoke test, and more — completing 19 of 27 checks. With the skill, all 27 completed. We included a skill to evaluate skills https://github.com/databricks-industry-solutions/vital-skills/tree/main/skills/skill-eval because there is no single universal “accuracy” for healthcare and life sciences workflow. For each skill, it builds a customizable evaluation harness, complete with appropriate tasks, data, scorers, and expected results and behavior, tailored to what each skill is designed to achieve. We ran and scored https://github.com/databricks-industry-solutions/vital-skills/tree/main/skills/skill-eval the evaluation tasks with and without Vital Skills. We also tested Genie Code with and without Vital Skills three times https://github.com/databricks-industry-solutions/vital-skills/blob/main/benchmarks/biomnibench/README.md on BiomniBench which curated https://huggingface.co/datasets/phylobio/BiomniBench-DA tasks from top biomedical peer-reviewed papers. The right skill makes the right behaviors reliable . On one cohort task, the baseline silently dropped half the eligible patients; with the skill, every one was recovered. Previous research has shown that Genie Code is more cost-efficient https://www.databricks.com/blog/why-frontier-data-agent-outperforms-general-coding-agents-quality-and-cost than other coding agents because it uniquely understands your data on Databricks, skipping the typical random walk search. Extend https://docs.databricks.com/aws/en/genie-code/skills Genie Code with additional skills like https://docs.databricks.com/aws/en/agent-skills/ skill-repositories Vital Skills for healthcare and life sciences tasks. Together, one can chain a myriad of skills into complex tasks. For example, after deploying open-weight models, create and schedule a batch inferencing job. If it is an embedding model, prompt Genie Code to create a vector search index. Browse and install Vital Skills https://databricks-industry-solutions.github.io/vital-skills/ in Genie Code https://docs.databricks.com/aws/en/genie-code/ , Genie One https://docs.databricks.com/aws/en/genie-one/chat skills or Genie Code CLI https://docs.databricks.com/aws/en/genie-code/genie-code-cli . Publish https://github.com/databricks-industry-solutions/vital-skills/tree/main optional-register-and-sync-the-skills-to-unity-gateway these skills to Unity Gateway to govern and share https://docs.databricks.com/aws/en/agents/uc-skills/create-share-uc-skills share-your-skill them with your coworkers. Try the ones that fit your work or customize them to suit your needs. Genie Code even helps you create https://databricks-industry-solutions.github.io/vital-skills/guide/contributing/ new skills. Vital Skills is open source https://github.com/databricks-industry-solutions/vital-skills and welcomes your contributions. Solutions https://www.databricks.com/blog/category/platform/solutions , News https://www.databricks.com/blog/category/company/news , Best Practices https://www.databricks.com/blog/category/data-strategy/best-practices , Healthcare & Life Sciences https://www.databricks.com/blog/category/industries/healthcare-and-life-sciences and Solution Accelerators https://www.databricks.com/blog/category/engineering/solution-accelerators Subscribe to our blog and get the latest posts delivered to your inbox.