Menu

Individual skill

northstar-payer-ops

0upvotes

Produce strict JSON determinations, appeal dispositions, payment correction packets, peer-to-peer summaries, and UM-finance queue summaries from the Northstar payer-operations environment. Use when prompts reference Northstar Health Plan, prior authorization or UM nurse review, pharmacy appeals, manufacturer assistance, payment integrity claim repricing, peer-to-peer closure, or service margin queue analysis with provided answer templates and task_context payloads.

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

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 11, 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 turn Northstar payer-operations records into the exact JSON object requested by a task's `answer_template.json`.

## Required Workflow

1. Read the user prompt, `input/payloads/task_context.json`, and `input/payloads/answer_template.json` before querying the environment.
2. Extract the target business IDs, reporting date or period, bearer token, base URL, required output keys, enum choices, precision rules, and ordering rules.
3. Query only records needed for the target IDs. Prefer `GET /api/cases/{case_id}` for case-centered tasks, then use narrow SQL for cross-table records such as service-margin rows or benchmark matches.
4. Keep a source ledger while working: record ID, table or endpoint, role in the decision, whether it is current or stale, and whether it is controlling evidence or an exception/gap.
5. Read [references/workflows.md](references/workflows.md) for domain decision rules, calculations, and `basis_audit` construction.
6. Emit one JSON object only. Match the template keys, enum spellings, date formats, numeric precision, list ordering, and null handling exactly. Do not add narrative text.

## Environment Access
Back to top