normalizing-rxnorm

Normalizes drug mentions extracted by OpenMed to RxNorm RxCUIs using the free public RxNav/RxNorm REST API. Use when the user wants to code, standardize, or de-duplicate medication names, resolve a brand/generic/ingredient to a stable RxCUI, link strength+dose-form to an SCD/SBD, attach NDCs, or build a US Core Medication resource. Trigger keywords: RxNorm, RxCUI, RxNav, drug normalization, medication coding, NDC, ingredient, SCD, SBD, brand vs generic, getApproximateMatch. Pairs after OpenMed NER: consume Pharmaceutical/Chemical entities from openmed.analyze_text and map each drug span to an RxCUI. RxNorm and RxNav are fully public and free — no API key, no license barrier, the lowest-friction terminology in this set.

Quality

91%

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

82%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, actionable coding skill with real RxNav examples and a sensible validated workflow. It is slightly held back by minor editorial verbosity and by keeping all API detail inline rather than splitting into bundled references.

Suggestions

Trim editorial framing in the intro (e.g. 'highest value-to-friction ratio — start here when grounding medications') so every line is task-relevant.

Tighten the Workflow's validation step into an explicit checkpoint with a retry loop (e.g. 'If properties.tty does not match expected TTY, re-query /related.json and retry once') rather than describing recovery only in Edge cases.

Consider moving the full API endpoint reference into a bundled references/ file and keeping only the core quick-start calls inline to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly lean, with real code and non-obvious facts (no-auth, licensing nuance), but editorial phrases like 'highest value-to-friction ratio — start here' and a prose-heavy intro could be trimmed; not a 5 because a few tokens do not earn their place.	4 / 5
Actionability	Fully executable, copy-paste-ready RxNav calls cover the common cases — exact match, approximate match, properties, related-by-TTY, and NDC attachment — using the real public API surface.	5 / 5
Workflow Clarity	A clear Extract→Parse→Exact-match→TTY→Validate→Emit sequence includes an explicit validation step and an exact→approximate fallback, but the validate→fix→retry feedback loop is described in edge cases rather than as a tight in-flow checkpoint.	4 / 5
Progressive Disclosure	Sections are well-organized and external references are one level deep, but with no bundle files present all API detail lives inline in SKILL.md rather than being split into reference files; good but not exemplary.	4 / 5
	Total	17 / 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 strong, third-person description that concretely names capabilities, trigger terms, and use conditions with minimal fluff. It answers what, when, and how it fits alongside OpenMed clearly.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — normalize, code, standardize, de-duplicate, resolve brand/generic/ingredient to RxCUI, link strength+form to SCD/SBD, attach NDCs, build US Core Medication — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	It clearly states what it does (normalize OpenMed drug mentions to RxCUIs via RxNav) and gives an explicit 'Use when…' clause with concrete triggering scenarios, satisfying both what and when.	5 / 5
Trigger Term Quality	An explicit 'Trigger keywords' list covers RxNorm, RxCUI, RxNav, drug normalization, medication coding, NDC, ingredient, SCD, SBD, brand vs generic, and getApproximateMatch — comprehensive synonyms a clinical-coding user would naturally say.	5 / 5
Distinctiveness Conflict Risk	A clear RxNorm/RxNav niche with domain-specific triggers and explicit positioning relative to a sibling skill ('Pairs after OpenMed NER') keeps conflict risk minimal.	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/normalizing-rxnorm/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.