Menu

Individual skill

northstar-payer-ops

0upvotes

Solve Northstar Health Plan payer-operations tasks that require using a task environment to produce structured JSON for authorization determinations, pharmacy appeals, payment-integrity repricing, peer-to-peer summaries, and UM-finance margin queues. Use when prompts mention Northstar, payer operations, prior authorization, appeal disposition, manufacturer assistance intake, claim repricing, P2P, service margin, or an answer_template.json contract.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_014/fewshot/opencode/fewshot_attempt_01/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
121
Repository last updated
Oct 29, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Northstar Payer Operations

Use this skill to produce the exact JSON object requested by Northstar payer-operations prompts. The task environment is the source of truth; local prompt payloads define the target IDs, reporting date or period, credentials, and output schema.

## Workflow

1. Read the user prompt, `input/payloads/task_context.json`, and `input/payloads/answer_template.json`.
2. Extract the target business ID(s), reporting date/period, requester role, service domain, SQL endpoint, bearer token, and any scoped row IDs.
3. Query only the task environment named in the prompt/context. Do not inspect environment source files, generated data files, SQLite files, manifests, setup scripts, test tasks, or answer files.
4. Anchor every lookup on the target IDs. Prefer targeted SQL with `WHERE` filters over broad dumps. Use business endpoints when they expose the exact case, appeal, policy, document, rate schedule, or portal record needed.
5. Build a working evidence map of cases, request lines, appeals, claims, claim lines, authorization records, documents, policies/criteria, rate schedules, P2P events, assistance facts, and finance rows as applicable.
6. Apply the domain rules in [references/northstar_workflow.md](references/northstar_workflow.md).
7. Return one JSON object only. Match the template's required keys, enum values, numeric precision, date precision, null handling, and ordering rules.
Back to top