Install any skill in seconds. Free to start, no credit card required.
Get Started Free →openai/prior-auth-packet-builder
Build a concise prior authorization packet from local case files and payer policy docs.
Passed 6 of 15 test cases with the skill, and 3 of 15 without it.
and 3 more in the full report
6 fixed4 passed either way13 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
In output/policy_findings.md, we need to document primary care referral validation. What exact H2 section heading is specified for referral evaluation?
| Checked | Without skill | With skill |
|---|---|---|
| Uses exact heading ## Referral in output/policy_findings.md. | Missed | Passed |
The instructions your model reads when the skill loads.
Use this skill when a case requires prior authorization review, referral validation, imaging review, or payer-specific policy checks.
case/scenario.json and case/transcript.txt.policies/ for payer, prior auth, referral, imaging, and PPO guidance:
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.rg launcher or bootstrap failure is not evidence that there are no policy matches.output/policy_findings.md with these exact headings:
## Case summary## Matched policy files## Prior authorization## Referral## Missing information
Cite each matched policy by its filename.output/human_review_checklist.md with:
finalize_policy_packet only after both artifacts exist.grep -RniE fallback only when rg cannot complete the search.finalize_policy_packet succeeds.test cases passed, vs 3 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.