Menu

Individual skill

northstar-payer-ops

0upvotes

Resolve Northstar Health Plan payer-operations tasks against the shared task environment and return exact JSON outputs. Use for prior authorization, pharmacy appeal, peer-to-peer, claim repricing, payment-integrity, rate-schedule, and therapy margin queue prompts that provide an answer_template.json and Northstar environment access.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_014/fewshot/cc/fewshot_attempt_03/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 Ops

Use this skill to produce a single JSON answer for Northstar payer-operations tasks. The task prompt, `input/payloads/task_context.json`, and `input/payloads/answer_template.json` are the output contract.

## Core Workflow

1. Read the prompt, task context, and answer template before querying the environment.
2. Identify the target business object: case ID, appeal ID, claim ID, P2P case, or queue row IDs.
3. Use only the network environment named in the task. If the prompt shows a placeholder base URL, resolve it from the task's environment access note. Use the task-provided bearer token for SQL.
4. Query narrowly. Prefer target-specific business endpoints such as `GET /api/cases/{case_id}`. Use `POST /sql/query` with JSON body `{"sql": "..."}` only for tables and IDs needed by the target.
5. Do not list unrelated records, inspect task-environment source files, or infer from records outside the requested target and its linked records.
6. Fill exactly the keys required by the answer template. Respect enum choices, list ordering, null handling, date formats, and numeric precision from the template.
7. Return JSON only, with no markdown or narrative.
Back to top