doctor-intake

To convert raw user symptom descriptions into structured clinical intake notes, this Skill translates witness statements into clinically precise records while applying terminology normalization and preserving verbatim evidence. It separates observed facts from beliefs to produce clean, actionable intake notes for human review.

Yes, you can separate observed facts from user beliefs during triage handoff workflows. This Skill explicitly enforces the separation of observation versus belief, ensuring that raw witness statements are translated into a clean, actionable intake note without losing the original context.

The best way to normalize clinical terminology from unstructured witness statements is to capture verbatim user input and error strings, then translate that terminology into a clinically meaningful vocabulary. This process ensures triage-ready tokens are generated for rapid downstream routing.

To infer missing context in medical intake notes with explicit uncertainty markers, this Skill analyzes raw descriptions and fills in missing environmental, scope, and recency details. It clearly marks inferred information to support accurate decision-making during human review.

No, this intake note generation process does not require any external dependencies or frameworks. It operates independently using its internal references and assets to produce triage-ready tokens from raw user descriptions.

You should not use automated intake note generation for clinical records when a situation requires direct medical diagnosis rather than structured documentation. This Skill produces notes for human review, triage routing, and handoff workflows, and does not replace clinical judgment.