$ loading_
Generate source-grounded encounter summaries from packaged synthetic clinical evidence.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "clinical-notes-summarizer-encounter-summary" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/solutions/clinical-notes-summarizer/manual/skills/encounter-summary/SKILL.md 2. Save it as ~/.claude/skills/encounter-summary/SKILL.md 3. Reload skills and tell me it's ready
Using only the packaged knowledge files, summarize synthetic encounter SYN-ENC-001. Preserve exact identifiers, names, dates, values, statuses, and headings, and output as # Source-Grounded Encounter Summary.
A source-grounded encounter summary with exact patient/date, source note, observations, and a no-clinical-interpretation line.
Please summarize SYN-ENC-999. If the synthetic identifier or evidence is missing, state what is missing and list the known synthetic identifiers. Do not substitute another record.
A fallback response explaining the missing identifier or evidence and listing known synthetic identifiers.
Use the existing synthetic evidence to prepare an encounter summary for SYN-ENC-001. Do not diagnose or recommend treatment; keep only source facts.
The request is routed to the same summary workflow and returns a standardized summary containing source facts only.
Researchers or documentation staff can use it to turn a specified synthetic encounter into a standardized summary while preserving source facts and field ordering.
When a read-only review of synthetic evidence is needed, it produces a summary without clinical interpretation and avoids actions such as diagnosis, recommendations, or record changes.
The README describes a locked workflow for producing encounter summaries from synthetic clinical evidence. It routes semantically equivalent requests to the same task, uses two packaged knowledge files, and extracts facts only for the exact requested synthetic identifier. The output must follow a fixed contract, preserve exact identifiers, names, dates, values, statuses, headings, uncertainty, and ordering, and avoid clinical interpretation. If evidence is missing, it should explain what is missing and list known synthetic identifiers.
Summarize synthetic encounter SYN-ENC-001 using source facts only.
Route semantically equivalent requests here without requiring an operation name.
Use both packaged knowledge files. Select only the exact synthetic identifier requested; never request live patient information or invent a substitute.
# 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.
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.
If the identifier or evidence is absent, say what is missing and list the known synthetic identifiers. Do not substitute another record.
It generates encounter summaries from packaged synthetic clinical evidence. The output must stay strictly grounded in source facts, without clinical interpretation or substitution of another record.
No. The documentation says it should use only the packaged knowledge files and must never request live patient information.
It states whether the identifier or evidence is missing and lists the known synthetic identifiers. It does not automatically substitute another record.
Checks claim-file readiness and compiles evidence for human review.
Analyze client engagement signals across meetings, escalations, billing, and utilization.
Triages fictional insurance claims and summarizes key intake details and priority.
Compare incentive options by synthetic cost, modeled lift, and net value.
Estimate policy-term settlement, coverage limits, and deductibles for claims processing.
Segment a fictional client portfolio and visualize health and churn indicators.
Extract and summarize medication inventories from packaged synthetic clinical evidence.
Extract referral context and missing actions from synthetic clinical note evidence.
Extract a source-coded problem list from synthetic clinical evidence deterministically.
Generate SOAP notes, billing codes, and visit summaries from clinical audio.
Run structured legal client intake and generate organized case summaries.
Summarize conversations, save key points, and review summary history easily.