HL7 Desk

Paste one HL7 version 2 message off a hospital interface log and work it through one sitting. A real HL7 v2 parser runs free in your browser: it reads the five delimiters out of MSH-1 and MSH-2 instead of assuming pipes and carets, splits every repetition, component and subcomponent, decodes the escape sequences, validates every timestamp against the real calendar, resolves the message structure your trigger event actually maps to (an A08 is ADT_A01, not an invented ADT_A08), checks the required segments and their order against it, and inventories every field carrying a patient identifier so you can redact the message in one click before anything is sent. Then run one of four AI lanes over that same message: decode it segment by segment, check its conformance against HL7 v2 and IHE PAM and get a corrected message back, build the acknowledgment the receiver should return with the right code and ERR segments and the MSH direction the right way round, or map it to FHIR R4 with a field-level mapping table and a Bundle. Every model claim is reconciled against the parser's own flags and every HL7 location it cites is checked against the message you pasted. A derived work inspired by the @dedalus-erp-pas/hl7-pam-parser and @anthropics/fhir-developer-skill agent skills; not affiliated with Dedalus ERP-PAS or with either repository's maintainers. A developer tool for health interfaces, not a medical device and not clinical advice.

Every public app is built from a security-scanned skill and must pass a clean scan — skill and frontend — before it can be listed. Have a skill of your own? Turn it into an app — or read the step-by-step walkthrough.