defining-cohort-phenotypes

Authors computable phenotype and cohort definitions in the OHDSI ATLAS / CIRCE style over the OMOP CDM, combining standard concept sets with NLP-derived features that OpenMed extracts. Use when the user wants to define a patient cohort, write a computable phenotype, reuse PheKB or OHDSI Phenotype Library logic, build concept sets, or augment code-based criteria with text features. Trigger keywords: phenotype, cohort definition, OHDSI, ATLAS, CIRCE, OMOP CDM, concept set, PheKB, Phenotype Library, eMERGE, computable phenotype. Pairs adjacent to OpenMed: NLP features from openmed.analyze_text augment code-based phenotypes for entities that are poorly captured by structured codes. OMOP CDM and OHDSI tools are open source; restricted vocabularies (SNOMED, CPT) are user-supplied.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, domain-rich skill body that gives executable code, a real CIRCE JSON shape, a sequenced workflow with validation, and a focused edge-cases section. It is held back only by minor redundancy, commented rather than coded OMOP-materialization steps, and an implied rather than explicit error-recovery loop.

Suggestions

Make the 'materialize NLP feature as OMOP rows' step (workflow step 3 / python steps 2–3) executable — show the INSERT/measurement-row shape or a helper call instead of only comments.

Spell out the validate→fix→re-validate feedback loop as an explicit sub-sequence under workflow step 5 rather than relying on 'iterate with PheValuator-style checks'.

Tighten the one redundant restatement of 'structured codes miss text-only facts' so the intro and 'Augmenting' section each earn their tokens distinctly.

Dimension	Reasoning	Score
Conciseness	Mostly lean and purposeful with domain-specific context that Claude would not already know (CIRCE/ATLAS roles), but minor redundancy such as restating 'structured codes miss text facts' in both the intro and the augmenting section keeps it just short of fully efficient.	4 / 5
Actionability	Provides a concrete, copy-paste-ready `openmed.analyze_text` call and an abridged real CIRCE JSON shape, but the 'materialize as OMOP rows' steps (2–3) are left as commented guidance rather than executable code, leaving a minor gap.	4 / 5
Workflow Clarity	A clear six-step sequence with an explicit validation checkpoint ('Validate against OMOP CDM... iterate with PheValuator-style checks'), but the error-recovery branch is implied rather than spelled out as a fix-and-revalidate sub-loop.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections (When to use, Anatomy, Augmenting, Workflow, Hand-off, Edge cases, Standards & references) with external links gathered in one place; no bundle files exist, and content is appropriately self-contained with only minor opportunities to split out detail.	4 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: third-person voice, explicit 'Use when' trigger guidance, a enumerated keyword list, multiple concrete actions, and clear niche scoping with adjacent-skill disambiguation. It answers what, when, and how-it-differs with no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Authors computable phenotype and cohort definitions', 'combining standard concept sets with NLP-derived features', 'reuse PheKB or OHDSI Phenotype Library logic', 'build concept sets', 'augment code-based criteria with text features' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly answers both 'what' (authors computable phenotype/cohort definitions combining concept sets with NLP features) and 'when' (explicit 'Use when the user wants to define a patient cohort, write a computable phenotype, reuse PheKB...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and acronyms via the explicit 'Trigger keywords: phenotype, cohort definition, OHDSI, ATLAS, CIRCE, OMOP CDM, concept set, PheKB, Phenotype Library, eMERGE, computable phenotype', reinforced by natural 'Use when the user wants to...' phrasing.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (OHDSI ATLAS/CIRCE phenotyping over OMOP CDM with OpenMed NLP augmentation) with distinct triggers, and even disambiguates adjacent skills ('Pairs adjacent to OpenMed'), minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: maziyarpanahi/openmed
Path: skills/defining-cohort-phenotypes/SKILL.md
Commit: 80da98c

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.