agentleFS
Sign inStart free
databricks-industry-solutionsdatabricks-industry-solutions/hls-skills/skills/cohort-builder/SKILL.md

cohort-builder

Skill6 starsChanged 20 days agoLicence not identifiedView on GitHub

Cohort builder for structured coded clinical data (OMOP/FHIR-flattened conditions, labs, meds, procedures) AND free-text clinical notes. Turns a natural-language patient-population description — e.g. "type 2 diabetics with uncontrolled HbA1c", "how many patients qualify for X", "define a sepsis cohort" — into a defensible, reproducible, feasibility-checked cohort. Grounds codes in the data (no hallucinated ICD/LOINC), ascertains the diagnosis from notes via ai_query (negation- and subject-aware, span-grounded), SURFACES ambiguous clinical thresholds and how to combine coded vs note evidence (code_only/note_only/union/intersection) for the user to choose, reports feasibility N before building, materializes a verified cohort plus a reproducible phenotype definition, and never fabricates literature citations. Run by calling the vetted entrypoints in scripts/cohort_run.py — do not hand-write cohort SQL. For PHI de-identification of the result use phi-deidentifier.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free