Menu

Individual skill

northstar-payer-ops-json

0upvotes

Use this skill for Northstar Health Plan payer-operations tasks that require a strict JSON answer from the shared task environment, including prior authorization determinations, pharmacy appeals, manufacturer assistance intake, peer-to-peer summaries, payment integrity claim repricing, and UM-finance margin queues. Use it whenever a task mentions Northstar, payer operations, authorization cases, appeals, claims, service margins, policies, criteria, or answer_template JSON.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_014/fewshot/cc/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 JSON

Use this skill to solve Northstar payer-operations tasks by querying the running environment, applying the applicable business precedence rule, and returning only the JSON object required by the provided answer template.

## Core workflow

1. Read the task prompt, `input/payloads/task_context.json`, and `input/payloads/answer_template.json` before querying data.
2. Resolve the task environment base URL from the prompt or the task's environment access file. Use only the listed HTTP endpoints and the SQL endpoint. Do not inspect environment source files, generated data files, database files, manifests, or setup scripts.
3. Use targeted SQL queries keyed by the target case, claim, appeal, queue, document, or row IDs from the prompt and task context. Avoid broad list endpoints unless you only need endpoint shape.
4. Treat the answer template as the output contract: required keys, enums, ordering, precision, null handling, and whether extra fields are allowed all come from the template.
5. Build a basis audit for every answer. The audit should explain the source-precedence rule, the records that directly control the result, and the records or gaps that explain exclusions, missing information, denial, route priority, or stale evidence.
6. Return valid JSON only. Do not include markdown fences, explanations, citations, or comments outside the JSON.

## Data access
Back to top