Agents & OrchestrationSûr100100/100
Encounter Summary (Microsoft)
Reproduce the deterministic Clinical Notes Agent — encounter summary workflow from packaged synthetic evidence.
ou envoie-le directement à ton agent.
Installer dans ton projet
$ curl -fsSL https://arboristhree.xyz/cli/install-skill.mjs -o /tmp/arboris-install-skill.mjs && node /tmp/arboris-install-skill.mjs encounter-summary__microsoft-aibast-agents-library__solutions-clinical-notes-summarizer-manual-skills-b12f8edb34caMicrosoft
microsoft/aibast-agents-library
Contenu à copier
--- name: clinical-notes-summarizer-encounter-summary description: Reproduce the deterministic Clinical Notes Agent — encounter summary workflow from packaged synthetic evidence. metadata: origin: Microsoft --- <!-- bic:source=blank --> # Clinical Notes Agent — encounter summary ## Locked persona prompt `Summarize synthetic encounter SYN-ENC-001 using source facts only.` Route semantically equivalent requests here without requiring an operation name. ## Source Use both packaged knowledge files. Select only the exact synthetic identifier requested; never request live patient information or invent a substitute. ## Required output contract `# Source-Grounded Encounter Summary`; exact patient/date, source note, observations, and no-clinical-interpretation line. Preserve exact identifiers, names, dates, values, statuses, headings, uncertainty, and source ordering from the knowledge files. ## Review boundary This is read-only synthetic evidence. Do not diagnose, recommend treatment, decide eligibility or authorization, schedule, contact, submit, place, approve, deny, or change any record. Apply the exact human clinical, utilization, quality, or operational review gate in the review-rules file. ## Fallback If the identifier or evidence is absent, say what is missing and list the known synthetic identifiers. Do not substitute another record.
Colle ce Markdown dans ton agent ou utilise les boutons ci-dessus pour l’écrire dans ton projet.
Ce que fait Encounter Summary (Microsoft)
Applique les pratiques du skill encounter-summary__microsoft-aibast-agents-library__solutions-clinical-notes-summarizer-manual-skills-b12f8edb34ca.
Comment utiliser Encounter Summary (Microsoft)
1
Copie le prompt
Un clic copie le prompt packagé (ou l'envoie à ton agent).
2
L'agent installe le skill
Il ajoute le SKILL.md et ses ressources à ton projet.
3
Activation automatique
Le skill s'active dès que le contexte correspond.
Déclencheurs pour Encounter Summary (Microsoft)
Dis simplement à ton agent quelque chose comme :
Applique le skill encounter-summary__microsoft-aibast-agents-library__solutions-clinical-notes-summarizer-manual-skills-b12f8edb34ca à cette tâche
Utilise encounter-summary__microsoft-aibast-agents-library__solutions-clinical-notes-summarizer-manual-skills-b12f8edb34ca pour améliorer cette implémentation
Passe en revue ce sujet avec encounter-summary__microsoft-aibast-agents-library__solutions-clinical-notes-summarizer-manual-skills-b12f8edb34ca
Skills liés à Encounter Summary (Microsoft)
Acceleration (Microsoft)
Compare synthetic acceleration options and clearly separate scenario value from forecast commitments.Account Overview (Microsoft)
Create a synthetic Acme account overview and identify evidence that merits seller attention.Acroform Writer (Microsoft)
Use this skill whenever the user wants values written INTO an existing PDF form that lives in the connected SharePoint knowledge source — filling out, completing, populating, or submitting a fillable PDF (application, intake sheet, contract, government form) from data they supply, a spreadsheet row, or the conversation. Triggers include "fill out the job application form", "complete the intake form for [person]", "populate our standard NDA template", and "make this ready to send / non-editable" (flatten). The source form should be found via knowledge search; only ask the user to upload it if knowledge search turns up nothing plausible. different task), and do NOT use it on scanned/image-only PDFs that have no real fillable fields — those need OCR or manual overlay instead, which this skill explicitly detects and reports rather than silently failing.