CtrlK
BlogDocsLog inGet started
Tessl Logo

parsing-hl7v2-messages

Decodes pipe-delimited HL7 v2.x messages (ADT, ORU, MDM, ORM) into structured segments/fields/components and surfaces OBX-5 and NTE-3 free-text narrative for OpenMed. Use before OpenMed processing when ingesting HL7 v2 feeds from an interface engine, lab/results system, or ADT stream and you need the embedded clinical note text de-identified and analyzed. Flatten OBX/NTE text then call openmed.deidentify and openmed.analyze_text; segment-aware redaction is available via openmed.interop.hl7v2. Trigger keywords: HL7, HL7 v2, ADT, ORU, OBX, MSH, PID, pipe-delimited, interface engine, Mirth, lab results.

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

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.

The body is executable and well-structured with concrete code and a clear workflow, but its destructive de-identification step lacks an explicit validation/verification checkpoint, and conciseness has minor room to improve.

Suggestions

Add an explicit verification step to the workflow after de-identification/redaction (e.g., 'Confirm redacted fields and free text contain no residual PHI before persisting') to satisfy the destructive-operation validation requirement.

Tighten the 'HL7 v2 structure in one minute' section by moving basic encoding-character explanations into a reference, keeping only the MSH-1/MSH-2 special-case detail Claude would not infer.

Add a short 'Verify' snippet showing how to check that PID-3 is hashed and OBX-5 free text is masked after redact_hl7v2, so the verify loop is actionable rather than implied.

DimensionReasoningScore

Conciseness

Dense and assumes HL7 familiarity throughout; the 'structure in one minute' prose and edge-case section are load-bearing rather than padding, with only minor over-explanation that could be trimmed. Not a 5 because a few sentences restate encoding basics Claude likely knows.

4 / 5

Actionability

Two complete, copy-paste-ready code blocks (parse + narrative extraction; whole-message redaction) with named APIs, one-based field semantics, and concrete edge-case handling (MLLP stripping, value-type gating, unescaping).

5 / 5

Workflow Clarity

The Workflow section gives a clear 5-step sequence, but de-identification/redaction is a destructive, persisted-PHI operation with no explicit validation or verification checkpoint (e.g., confirm no PHI leaked before persisting), which caps workflow clarity at 3 per the destructive-operation guidance.

3 / 5

Progressive Disclosure

Well-organized into clearly labeled sections (Quick start, Workflow, Edge cases, Standards) in a single self-contained file with no nested references; no bundle files exist to verify deeper references, keeping it just below 5.

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.

The description is concrete, comprehensive, and well-structured, explicitly stating both capability and trigger context with a rich set of natural keywords and minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Decodes pipe-delimited HL7 v2.x messages (ADT, ORU, MDM, ORM) into structured segments/fields/components and surfaces OBX-5 and NTE-3 free-text narrative' plus 'segment-aware redaction' — with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (decode + surface narrative + de-identify + analyze) and 'when' via 'Use before OpenMed processing when ingesting HL7 v2 feeds from an interface engine, lab/results system, or ADT stream'.

5 / 5

Trigger Term Quality

Comprehensive natural trigger list including synonyms and a vendor name: 'HL7, HL7 v2, ADT, ORU, OBX, MSH, PID, pipe-delimited, interface engine, Mirth, lab results'.

5 / 5

Distinctiveness Conflict Risk

A clear HL7 v2 / OpenMed niche with distinct triggers (ADT, ORU, OBX, Mirth, interface engine) that are unlikely to fire for unrelated skills.

5 / 5

Total

20

/

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.

Repository
maziyarpanahi/openmed
Reviewed

Table of Contents

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.