Individual skill
northstar-payer-ops
Solve Northstar Health Plan payer-operations tasks by querying the provided environment and returning schema-conforming JSON for prior authorization, pharmacy appeals and assistance intake, claim repricing, peer-to-peer closure, service-margin queues, and mixed UM-finance triage. Use when prompts mention Northstar payer operations, UM nurse determination summaries, appeals coordinators, payment integrity correction packets, P2P summaries, queue analysis, answer_template.json, or the task environment SQL/API endpoints.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_014/fewshot/deepagents/fewshot_attempt_02/SKILL.md
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.
- agent Repository topic
- ai Repository topic
- benchmark Repository topic
- llm Repository topic
- self-evolving Repository topic
- self-learning Repository topic
- skills Repository topic
- finance Derived category
- operations Derived category
- data Derived category
- data-databases Derived category
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
## Core Workflow
1. Read the user prompt, `input/payloads/task_context.json`, and `input/payloads/answer_template.json`.
2. Extract the target business IDs, reporting date or period, SQL base URL, bearer token, required output keys, enum choices, ordering rules, and numeric precision from those files.
3. Query only the running environment endpoints named by the prompt or context. Do not inspect local environment source, SQLite files, generated data, manifests, hidden tests, or broad distractor records when a target ID is known.
4. Treat `answer_template.json` as the output contract. Return exactly one JSON object, use only requested keys unless the template permits extras, and use enum strings exactly as listed.
5. Build a `basis_audit` for every answer when requested: choose the matching `source_precedence`, list direct controlling environment records, list gaps/exceptions/stale records, and order the precedence trail from highest-priority controlling source to lower-priority exceptions.
## Environment Access
Use the base URL and token supplied by the prompt or task context. The SQL endpoint accepts JSON with an `sql` key: