Individual skill

cedar-intake-reconciliation

Solve Cedar Ridge Intake Coordination Portal tasks that require querying patients, referrals, transfers, documents, charts, programs, coverage, PBM, pharmacies, ICD metadata, or facility capacity and returning strict JSON for access verification, referral readiness, dialysis transfer review, chronic-care enrollment, or referral-to-chart activation.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_013/fewshot/deepagents/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.

agent Repository topic
ai Repository topic
benchmark Repository topic
llm Repository topic
self-evolving Repository topic
self-learning Repository topic
skills Repository topic
engineering 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

SKILL.mdcore · 11,026 bytes
SKILL.mdcore · 11,026 bytes
scripts/portal_fetch.pyruns · 4,331 bytes

Read excerpt


# Cedar Intake Reconciliation

Use this skill to turn Cedar Ridge portal records into the exact JSON object requested by the task template.

## Core Workflow

1. Read the prompt and `input/payloads/answer_template.json` first. Treat the template as the schema, controlled vocabulary, ordering rule, and count contract.
2. Extract the target identifier from the prompt or template: roster ID, referral batch ID, transfer batch ID, or program code.
3. Query only records scoped to that target and its linked patient IDs. Prefer REST endpoints for direct objects and `POST /query` for joins.
4. Derive fields from portal data, not from prose expectations. Use the rules below only when the template does not define a different rule.
5. Emit JSON only. Include required zero-count keys and empty arrays. Sort rows exactly as the template specifies; otherwise sort IDs ascending and sort artifact/document code arrays alphabetically.

## Portal Access