Menu

Individual skill

northstar-payer-ops-json

0upvotes

Produce strict JSON determinations and operations packets for Northstar Health Plan payer-operations tasks using the shared task environment. Use when the prompt asks for prior authorization or UM review, pharmacy appeal or assistance intake, peer-to-peer closure, payment integrity claim repricing, benchmark selection, or service margin queue summaries that must conform to an input/payloads/answer_template.json schema.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_014/fewshot/cc/fewshot_attempt_02/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 JSON

## Core Workflow

1. Read `input/prompt.txt`, `input/payloads/task_context.json`, and `input/payloads/answer_template.json` before querying anything.
2. Extract the target identifiers, reporting date or period, requester role, answer schema, endpoint base URL, and SQL bearer token from the task files. If the prompt contains a placeholder base URL, use the task environment access note supplied with that task.
3. Query only the documented environment endpoints. Do not inspect task-environment source files, generated databases, SQLite files, manifests, or setup scripts.
4. Start with the exact target IDs from `task_context.json`, then follow linked `case_id`, `member_id`, `policy_id`, `claim_id`, appeal, document, and queue row IDs. Avoid broad table dumps.
5. Build the answer directly from environment records and the template. Do not rely on local memos except for scope, target IDs, dates, definitions, and output constraints.
6. Return exactly one JSON object and no markdown or narrative text.

Use `scripts/northstar_sql.py` for SQL requests when helpful:

```bash
Back to top