coding-icd10

Suggests candidate ICD-10-CM diagnosis codes (and ICD-10-PCS procedure codes) for diagnoses and procedures extracted by OpenMed, with rationale and a human-coder caveat. Use when the user wants to code a problem list, map a diagnosis span to a billable ICD-10-CM code, route a finding to the right chapter, cross-walk ICD-9 via GEMs, or pre-fill an encounter for coder review. Trigger keywords: ICD-10-CM, ICD-10-PCS, diagnosis coding, billable code, GEMs, problem list coding, encounter diagnosis, chapter range, CMS code lookup. references/icd10-chapters.md holds the chapter/section ranges. Pairs after OpenMed NER: consume Disease/Pathology entities from openmed.analyze_text and propose codes a certified coder validates. ICD-10-CM/PCS files are public domain from CMS — no license barrier (unlike CPT, which is restricted and out of scope).

Quality

91%

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

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, highly actionable skill body with executable code for both local-CMS and FHIR-API paths and a clear coding workflow gated by human-in-the-loop review. The main weaknesses are mild redundancy of the licensing note and an inlined reference URL list that slightly blurs the overview/detail split.

Suggestions

State the public-domain/CPT licensing boundary once (e.g. in Edge cases) and remove the duplicate from the intro paragraph to tighten conciseness.

Add an explicit validation checkpoint to the Workflow — e.g. confirm the billable flag and required specificity (laterality, episode, 'with') before emitting a candidate — to create a validate→flag→retry loop.

Move the full 'Standards & references' URL list into references/icd10-chapters.md (or a new references file) so SKILL.md stays a lean overview pointing one level deep.

Dimension	Reasoning	Score
Conciseness	Mostly lean with executable code and no over-explanation of ICD-10 basics, but the public-domain/CPT licensing note is restated in the description, the intro paragraph, and the Edge cases — a minor redundancy that could be trimmed.	4 / 5
Actionability	Provides two complete copy-paste code paths (local CMS file parsing with exact column offsets, and the NLM Clinical Tables API call) plus a concrete OpenMed hand-off snippet with a real model_name, covering the common cases.	5 / 5
Workflow Clarity	A clear six-step sequence (Extract → Route → Search → Apply specificity → Rank → Emit) with the 'flag missing detail' and needs-coder-review status checkpoints; not a 5 because there is no explicit validate→fix→retry feedback loop, though the task is decision-support rather than destructive.	4 / 5
Progressive Disclosure	Well-organized into When-to-use / Quick start / Workflow / Hand-off / Edge cases / Standards sections with the one referenced file (references/icd10-chapters.md) clearly signaled and one level deep; not a 5 because the body still inlines a URL reference list that could live in the references file.	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 dense, specific description that concretely names capabilities, use cases, and trigger keywords while staying in third person and scoping out adjacent skills (CPT). It answers both 'what' and 'when' with concrete triggers, though it is long for a description field.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Suggests candidate ICD-10-CM diagnosis codes', 'map a diagnosis span to a billable code', 'route a finding to the right chapter', 'cross-walk ICD-9 via GEMs', 'pre-fill an encounter' — matching the comprehensive-coverage anchor; third-person voice is maintained.	5 / 5
Completeness	Explicitly states what ('Suggests candidate ICD-10-CM diagnosis codes… with rationale and a human-coder caveat') and when ('Use when the user wants to code a problem list, map a diagnosis span…'), matching the concrete-trigger-phrases anchor.	5 / 5
Trigger Term Quality	An explicit 'Trigger keywords:' list gives natural user phrases — ICD-10-CM, ICD-10-PCS, diagnosis coding, billable code, GEMs, problem list coding, encounter diagnosis, chapter range, CMS code lookup — covering synonyms and the key system names.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear ICD-10-CM/PCS coding niche tied to OpenMed, with distinct triggers and explicit boundary notes ('unlike CPT, which is restricted and out of scope'), minimizing overlap with adjacent coding skills.	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/coding-icd10/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.