reconciling-problem-lists

Deduplicate and reconcile OpenMed-extracted conditions into one clean active problem list with clinical status (active / resolved / historical). Use after NER and context resolution when the user wants a problem list, condition reconciliation, dedup of synonymous diagnosis mentions, or active-vs-resolved status from a note. Covers clustering synonymous mentions into one concept, excluding negated mentions, applying clinical context (historical / hypothetical / recent) to set status, and emitting a USCDI-Problem-shaped list. SNOMED CT concept grounding is user-supplied and out-of-process. Hand-off: consume openmed.analyze_text Disease entities plus resolving-clinical-context axes. Pairs after extracting-clinical-entities.

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

85%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 clinical skill with fully executable examples, a clear validation-aware workflow, and clean organization. The main weakness is mild verbosity in the intro and edge-case prose that restates what the code and workflow already demonstrate.

Suggestions

Trim the opening paragraph and the Edge Cases bullets that re-explain rationale already shown in the Quick start code (e.g. the active-beats-historical and negation-as-exclusion points), trusting the workflow steps to carry that guidance.

Consider collapsing the 'Active beats historical for the same concept' edge case into the workflow's step 5, where the rule is already stated, to avoid duplicate exposition.

The 'Standards & references' links could be moved to a single compact line each since the surrounding prose re-describes what USCDI/FHIR/SNOMED are.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-organized, but the intro paragraph and several Edge Cases bullets re-explain concepts Claude can infer (e.g. restating why active beats historical, and re-deriving the negation/exclusion rationale already shown in code), so it could be tightened.	3 / 5
Actionability	Quick start is fully executable, copy-paste-ready Python using real OpenMed imports and a worked note example with expected output, and the workflow gives concrete, specific steps rather than vague direction.	5 / 5
Workflow Clarity	The 6-step workflow is clearly sequenced with explicit validation/exclusion checkpoints (drop NEGATED/HYPOTHETICAL, aggregate before assigning status, active-wins rule) and an Edge Cases section that serves as error-recovery guidance for the fragile reconciliation cases.	5 / 5
Progressive Disclosure	No bundle files exist and none are needed; the body is a well-organized overview with clearly signaled one-level-deep external references (USCDI, FHIR R4, SNOMED links) and clean section navigation, fitting the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

92%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 strong, specific description that clearly states both what the skill does and when to use it, grounded in a distinct OpenMed clinical-NLP niche. Trigger terms are domain-appropriate but slightly heavy on jargon over lay phrasings.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Deduplicate and reconcile... conditions", "clustering synonymous mentions into one concept", "excluding negated mentions", "applying clinical context... to set status", and "emitting a USCDI-Problem-shaped list" — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ("Deduplicate and reconcile OpenMed-extracted conditions... with clinical status") and when ("Use after NER and context resolution when the user wants a problem list, condition reconciliation, dedup... or active-vs-resolved status from a note") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural domain triggers a user would say ("problem list", "condition reconciliation", "dedup of synonymous diagnosis mentions", "active-vs-resolved status") but leans on clinical jargon rather than common phrasings/synonyms, leaving a few natural terms out.	4 / 5
Distinctiveness Conflict Risk	Scoped to the OpenMed clinical-NLP niche with explicit hand-off ("consume openmed.analyze_text Disease entities plus resolving-clinical-context axes", "Pairs after extracting-clinical-entities"), giving it a clear niche with minimal conflict risk.	5 / 5
	Total	19 / 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/reconciling-problem-lists/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.