$ loading_
Generates a criteria-to-evidence crosswalk from packaged synthetic authorization evidence.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "prior-authorization-criteria-evidence" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/solutions/prior-authorization/manual/skills/criteria-evidence/SKILL.md 2. Save it as ~/.claude/skills/criteria-evidence/SKILL.md 3. Reload skills and tell me it's ready
Produce the criteria-to-evidence crosswalk for SYN-AUTH-001, without deciding medical necessity.
Outputs the fixed title, disclaimer, and itemized criteria-evidence crosswalk.
If the requested synthetic identifier is missing, say what is missing and list the known synthetic identifiers.
Returns missing-item details and the known identifier list, without substituting another record.
Organize the reviewer checks within the read-only synthetic evidence boundary, preserving source order and original fields.
Produces a review output preserving original identifiers, names, dates, statuses, and ordering.
Useful when packaged synthetic evidence needs to be turned into a standard crosswalk. It preserves the original identifiers, fields, values, and order.
Useful for reviewing one specific synthetic record only. It will not request real patient information or substitute another record.
Useful for workflows that must stay read-only and avoid diagnosis, approval, submission, or record changes.
This document describes a read-only synthetic prior-authorization evidence workflow that turns a requested synthetic identifier into a criteria-to-evidence crosswalk. It requires preserving original identifiers, names, dates, values, statuses, and order, while avoiding medical-necessity decisions, submissions, approvals, denials, or record changes. If the record is missing, it should report what is missing and list known synthetic identifiers.
Show the synthetic criteria checklist for SYN-AUTH-001 without deciding medical necessity.
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.
# Criteria-to-Evidence Crosswalk; exact fictional policy title/date, checklist disclaimer, and all reviewer checks.
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 a prior-authorization criteria-to-evidence result from packaged synthetic evidence. It emphasizes read-only behavior, fixed formatting, and preserving source order.
No. The docs explicitly say not to diagnose, recommend treatment, or decide eligibility or authorization; it only outputs synthetic evidence and review information.
State what is missing and list the known synthetic identifiers; do not substitute another record. The visible identifier in the provided material is SYN-AUTH-001.
Identify at-risk client accounts and suggest recovery actions with risk context.
Compare packaged satisfaction and NPS trends to identify declining accounts.
Summarize recovery conversion metrics with benchmarks, forecasts, and assumptions.
Review SIU indicators in claims and return explainable evidence with human review guidance.
Prioritize churn reviews with transparent evidence and suggested next steps.
Analyze loyalty tier thresholds, perks, progress, and tradeoffs without changing status.
Creates a deterministic reconsideration evidence packet from synthetic source files.
Extract referral context and missing actions from synthetic clinical note evidence.
Generate source-grounded encounter summaries from packaged synthetic clinical evidence.
Extract and summarize medication inventories from packaged synthetic clinical evidence.
Extract a source-coded problem list from synthetic clinical evidence deterministically.
Create Evidence reports and dashboards by querying schemas, docs, pages, and code.