building-with-openmed

Orient and bootstrap any project that uses OpenMed, the on-device clinical and biomedical NLP library, for named-entity recognition, PHI de-identification, FHIR export, and evaluation. Use when the user mentions OpenMed, wants to install it, asks which OpenMed capability or model fits a task, or is starting to build a clinical/medical text pipeline and needs the right entry point.

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

83%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, highly actionable overview with excellent code examples and routing to companion skills. Its main weakness is the lack of explicit validation/feedback-loop checkpoints in the de-identification pipeline, which the rubric caps at 3 for batch/destructive operations.

Suggestions

Add explicit validation checkpoints to the typical pipeline — e.g. after de-identify, run `openmed.eval` leakage gates and only proceed when they pass; after FHIR assembly, validate the FHIR resources.

Add a short validate→fix→retry feedback loop for the de-identification step, mirroring the 'verified, not assumed' non-negotiable rule, to lift workflow clarity above the cap.

Consider extracting the extras/policy-profile catalog into a small reference file so SKILL.md stays a lean overview and progressive disclosure reaches the clear one-level-deep ideal.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — assumes Claude knows Python/pip/CLI and FHIR, with every section (install, three core calls, runtime discovery, rules, pipeline) earning its place and no padded explanations.	5 / 5
Actionability	Provides copy-paste-ready, executable code for the three core calls with real arguments, real pip extras, real CLI commands, and real runtime-discovery calls covering the common cases.	5 / 5
Workflow Clarity	The typical pipeline is well-sequenced (ingest → de-identify → extract → ground → FHIR → evaluate), but PHI de-identification is a batch/destructive-adjacent operation with no explicit validate→fix→retry checkpoints, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep pointers to companion skills via a routing table and no nested references; falls short of 5 because no bundle reference files exist and some API surface (extras, policy profiles) could be split out.	4 / 5
	Total	17 / 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 answers what the skill does and when to invoke it, anchored to the OpenMed product name with minimal conflict risk. The only mild gap is a few missing natural synonyms in the trigger phrases.

Suggestions

Add a few plain-language synonyms to the trigger clause such as 'medical NER', 'HIPAA de-identification', or 'clinical text de-identification' to lift trigger-term coverage to comprehensive.

Consider adding the .py / pip framing or 'Python' keyword so users framing it as a Python library need also surface this skill.

Dimension	Reasoning	Score
Specificity	Names the clinical/biomedical NLP domain and lists several concrete capabilities — 'named-entity recognition, PHI de-identification, FHIR export, and evaluation' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what ('Orient and bootstrap any project that uses OpenMed... for named-entity recognition, PHI de-identification, FHIR export, and evaluation') and when ('Use when the user mentions OpenMed...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases ('mentions OpenMed', 'wants to install it', 'starting to build a clinical/medical text pipeline') with good coverage, but misses some plain synonyms like 'medical NER' or 'HIPAA de-identification'.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to the OpenMed product and clinical/medical text pipelines, with name-anchored triggers that create a clear niche and minimal overlap with other skills.	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/building-with-openmed/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.