generating-synthea-data

Generates synthetic but realistic patient records (FHIR R4 bundles, C-CDA documents, CSV) with MITRE Synthea for development, CI fixtures, demos, and leakage-gate test sets — zero real PHI. Use when you need safe, shareable test data for an OpenMed pipeline, reproducible fixtures for tests, or a held-out set for de-identification leakage gates, instead of touching real clinical data. Synthea output feeds the FHIR/C-CDA ingestion skills and openmed.eval. Trigger keywords: Synthea, synthetic data, fake patients, test fixtures, demo data, FHIR bundle generator, synthetic EHR, no PHI.

Quality

88%

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

76%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-organized, actionable skill body with executable commands and a clear workflow, but the batch-generation workflow lacks explicit validation checkpoints for verifying generated/committed fixtures, which caps workflow clarity. Conciseness is strong with minor padding.

Suggestions

Add an explicit validation step in the Workflow (e.g., verify generated FHIR bundles parse and fixtures are non-empty before committing) to lift the batch-operation workflow above the validation cap.

Trim motivational phrasing in the opening paragraph ('and you shouldn't have to', 'which is exactly what makes it a great test bed') to improve token efficiency.

Consider a short 'Verify' subsection or checklist after the Quick start so the seed-pinned fixture workflow has a feedback loop.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's competence (e.g., the Quick start jumps straight to commands), but a few phrases pad — 'and you shouldn't have to', 'a great test bed', and the motivation framing in the opening paragraph add tokens beyond what Claude needs.	4 / 5
Actionability	Quick start provides fully executable, copy-paste ready shell commands with real flags, plus a runnable Python snippet that loads a FHIR bundle and calls openmed APIs covering the common case.	5 / 5
Workflow Clarity	The numbered Workflow is well-sequenced, but it drives a batch file-generation operation (populations of patients, committed fixtures) with no validation/verification checkpoint — e.g., no step to verify generated output is valid FHIR or that fixtures are non-empty before committing, so the destructive/batch validation cap holds at 3.	3 / 5
Progressive Disclosure	Good structure with clear sections (Quick start, Workflow, Hand-off, Edge cases, Standards & references) and external links one level deep; no bundle files exist so all content is appropriately inline, with only minor organization gaps.	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 strong, specific description that clearly states both what it does and when to use it, with an explicit trigger-keyword block and concrete output formats. It assumes a known project context (OpenMed) but is otherwise comprehensive and well-scoped.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and outputs — 'Generates synthetic but realistic patient records (FHIR R4 bundles, C-CDA documents, CSV)' for 'development, CI fixtures, demos, and leakage-gate test sets' — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Clearly answers both 'what' (generates synthetic FHIR/C-CDA/CSV patient records) and 'when' via an explicit 'Use when you need safe, shareable test data... or a held-out set for de-identification leakage gates, instead of touching real clinical data' clause with concrete triggers.	5 / 5
Trigger Term Quality	An explicit 'Trigger keywords:' block provides comprehensive natural terms — 'Synthea, synthetic data, fake patients, test fixtures, demo data, FHIR bundle generator, synthetic EHR, no PHI' — including synonyms users would naturally say.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Synthea synthetic patient data for OpenMed) with distinct triggers and explicit adjacent-skill pairing ('feeds the FHIR/C-CDA ingestion skills and openmed.eval') gives minimal conflict risk with other 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/generating-synthea-data/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.