computing-ecqms

Compute electronic clinical quality measures (eCQMs) over structured data using CQL/QDM logic, lifting note-derived numerator and exclusion facts from OpenMed to improve measure capture. Use when the user wants to compute an eCQM, evaluate a CMS/ECQI quality measure, improve numerator capture from clinical notes, build CQL/QDM measure logic, or close documentation gaps that structured codes miss. Covers eCQM structure (IPP/denominator/numerator/exclusions), CQL v1.5 and QDM v5.6, MADiE authoring, and mapping OpenMed entities to QDM data elements. Consumes OpenMed analyze_text facts (coded via the linking skills) to supplement structured EHR data; does not replace certified measure engines.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%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 tight, well-structured skill body with an executable quick start, a sequenced workflow with validation checkpoints, and a useful gotchas section. It stays lean and assumes Claude's competence while pointing to external detail appropriately.

Suggestions

Make the QDM-materialization step (5) concrete with a short code example showing how a coded, dated fact becomes a QDM data element, since it is currently described rather than shown.

Add an explicit validate→fix→retry loop for the negation/temporality pass (step 3) to match the destructive/batch feedback-loop guidance.

Tighten the redundant glosses in 'Edge cases & gotchas' (e.g., 'a negated exclusion is not an exclusion', 'don't match on the surface word') since the preceding clause already states the rule.

Dimension	Reasoning	Score
Conciseness	Mostly lean — the anatomy table, workflow, and gotchas each earn their tokens — but a few phrases over-explain (e.g., 'a negated exclusion is not an exclusion', 'don't match on the surface word') beyond what Claude needs.	4 / 5
Actionability	Provides an executable `openmed.analyze_text` quick-start snippet and concrete step-by-step guidance (deidentify, resolving-clinical-context, linking skills, cqframework engine); minor gaps are the illustrative `facts` dict and that QDM materialization is described rather than coded.	4 / 5
Workflow Clarity	Seven clearly sequenced steps with an explicit validation checkpoint (negation/temporality pass before counting, dated-fact-in-measurement-period rule, reconcile & audit), though the destructive/batch validation feedback loop is implied rather than an explicit validate→fix→retry cycle.	4 / 5
Progressive Disclosure	Well-organized single-file overview with clearly signaled sections; external detail is referenced as named sibling skills and standards URLs one level deep rather than inlined. No bundle files are present, so references in the body are to external resources/skills rather than local files.	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.

A precise, comprehensive description that explicitly states both what the skill does and when to use it, with domain-specific trigger terms and a clear scope boundary. It reads in third person and avoids fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'compute eCQMs', 'lifting note-derived numerator and exclusion facts', 'improve numerator capture', 'build CQL/QDM measure logic', 'close documentation gaps', 'mapping OpenMed entities to QDM data elements' — covering the domain comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (compute eCQMs over structured data via CQL/QDM, lift note-derived facts from OpenMed) and 'when' (a concrete 'Use when the user wants to...' clause listing five trigger scenarios), matching the 5-anchor example.	5 / 5
Trigger Term Quality	The 'Use when' clause enumerates natural phrases users would say — 'compute an eCQM', 'evaluate a CMS/ECQI quality measure', 'improve numerator capture from clinical notes', 'build CQL/QDM measure logic', 'close documentation gaps' — with strong synonym and acronym coverage (CMS/ECQI, CQL/QDM).	5 / 5
Distinctiveness Conflict Risk	A clear niche (eCQM computation with OpenMed note-derived fact lifting) with domain-specific triggers (CMS/ECQI, CQL/QDM, MADiE) unlikely to fire for unrelated skills; the scope boundary ('does not replace certified measure engines') further sharpens it.	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/computing-ecqms/SKILL.md
Commit: 80da98c

Reviewed: about 24 hours 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.