prior-auth-packet-builder
Build a concise prior authorization packet from local case files and payer policy docs.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 3.1w
- Forks
- 5.0k
01 前言 Front Matter
- name
- prior-auth-packet-builder
- description
- Build a concise prior authorization packet from local case files and payer policy docs.
02 资源文件 3
- 参考文档references/backends.md14.1 KB
- 参考文档references/examples.md20.7 KB
- 参考文档references/json_generation.md14.6 KB
03 SKILL.md 正文
Prior Auth Packet Builder
Use this skill when a case requires prior authorization review, referral validation, imaging review, or payer-specific policy checks.
Workflow
- Inspect
case/scenario.jsonandcase/transcript.txt. - Search
policies/for payer, prior auth, referral, imaging, and PPO guidance:- Run the preferred search and fallback as one shell command:
rg -n -i 'prior authorization|prior-auth|imaging|referral|billing|PPO|Blue Cross' policies || grep -RniE 'prior authorization|prior-auth|imaging|referral|billing|PPO|Blue Cross' policies. - An
rglauncher or bootstrap failure is not evidence that there are no policy matches.
- Run the preferred search and fallback as one shell command:
- Read only the most relevant policy files.
- Create
output/policy_findings.mdwith these exact headings:## Case summary## Matched policy files## Prior authorization## Referral## Missing informationCite each matched policy by its filename.
- Create
output/human_review_checklist.mdwith:- what a human reviewer should verify
- what to tell the patient
- what queue should own the case
- Call
finalize_policy_packetonly after both artifacts exist.
Rules
- Use targeted searches over broad file reads.
- Use the targeted
grep -RniEfallback only whenrgcannot complete the search. - Only cite policy files you actually inspected.
- Keep outputs concise and operational.
- The workflow is complete only when
finalize_policy_packetsucceeds. - If referral status is pending and prior auth is unclear, recommend human review.
04 同仓库更多 Skills
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
test-coverage-improver
Measure Python SDK coverage or address measured coverage gaps. Use for coverage audits and metric regressions, not routine test additions.
sensitive-logging-audit
Audit or fix sensitive-data exposure in Python SDK diagnostics, exceptions, logging, and telemetry.
runtime-behavior-probe
Plan controlled runtime probes when explicitly invoked; execute only after the required probe approval.