CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/synthea-healthcare-data

Author and run Synthea (MITRE's open-source synthetic patient population simulator) to produce HIPAA-safe synthetic medical records for testing health IT systems. Covers Gradle build, population-size and state-specific generation, FHIR R4 / STU3 / DSTU2 / C-CDA / CSV / CPCDS output formats, disease-module customisation, and the lifecycle-simulation approach (birth-through-death patient journeys with realistic demographics). Use when testing FHIR servers, EHR integrations, claims processing, or any health IT system that needs realistic patient records without HIPAA exposure (distinct from the generic Faker family - qa-test-data faker-data for fixtures, the pii-masking-pipeline-builder faker-masking-operators reference for masking substitution; this is health-domain-specific).

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

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 highly actionable, well-structured skill body with concrete commands and a real reference file. Adding explicit validation checkpoint gates to the main workflow would lift workflow clarity to the top level.

Suggestions

Reframe the 'How to use' validation steps as explicit checkpoint gates (e.g., 'Stop if `./gradlew check test` fails' and 'Verify expected FHIR resources before loading') to satisfy the batch/destructive feedback-loop expectation.

Trim the common-flags table and output-format list to only flags/formats used in the worked examples, or move the full tables into a reference file.

Factor the CSV schema listing under 'Parsing results' into a reference file to keep the body as an overview.

DimensionReasoningScore

Conciseness

Efficient and mostly lean, though the flag table and output-format list restate README material and could be trimmed slightly; every section still earns its place.

4 / 5

Actionability

Fully executable guidance throughout—`./gradlew build check test`, `./run_synthea -p 1000 Massachusetts`, the curl POST loop, properties config, and a concrete worked example cover the common cases copy-paste ready.

5 / 5

Workflow Clarity

The 7-step 'How to use' sequence is clear with validation mentions ('confirm passes', 'confirm resources present'), but the main flow lacks explicit fail/stop checkpoint gates for the batch FHIR-load operation, keeping it just below the top anchor.

4 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled one-level-deep reference (references/ci-integration.md, verified to exist); appropriate split for the scope, though most detail remains inline rather than further factored 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 specific, well-scoped description that clearly states capabilities and use triggers while distinguishing itself from sibling skills. Minor additions of file-extension synonyms would round out trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—Gradle build, population-size and state-specific generation, FHIR R4/STU3/DSTU2/C-CDA/CSV/CPCDS output, disease-module customisation, lifecycle simulation—giving comprehensive coverage with no major gaps.

5 / 5

Completeness

Explicitly answers both 'what' ('Author and run Synthea...') and 'when' ('Use when testing FHIR servers, EHR integrations, claims processing...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural domain phrases ('FHIR servers', 'EHR integrations', 'claims processing', 'HIPAA', 'patient records') but lacks file-extension synonyms and a few common variants, keeping it just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Clear health-data niche with explicit disambiguation from qa-test-data faker-data and pii-masking-pipeline-builder, giving minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents