Menu

Individual skill

cedar-ridge-intake-audit

0upvotes

Use this skill for Cedar Ridge Intake Coordination Portal tasks that require a JSON audit or activation file from a TASK_ENV_BASE_URL, including new-patient access verification, referral readiness, referral-to-chart activation, dialysis transfer packet review, and chronic-care program enrollment panels. Use it whenever a prompt mentions Cedar Ridge intake rosters, referrals, transfers, program candidates, chart artifacts, ICD metadata, or answer_template.json-controlled output.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_013/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
No
Repository scan complete
No
Skill scan complete
Yes
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

# Cedar Ridge Intake Audit

Use this skill to solve Cedar Ridge portal tasks by deriving a JSON-only answer from the prompt, the provided `answer_template.json`, and the task environment. The examples show that accuracy depends more on schema discipline and blocker precedence than on prose reasoning.

## Core Workflow

1. Read the user prompt and every local payload template before querying the portal.
2. Replace `<TASK_ENV_BASE_URL>` with the provided base URL. Use only the allowed portal endpoints and the read-only SQL endpoint.
3. Fetch only records named or implied by the prompt: roster patient IDs, referral batch IDs, transfer batch IDs, or program candidate codes.
4. Build an intermediate table per patient/referral/transfer/candidate with raw fields, derived blockers, final status, and summary counters.
5. Return one JSON object and no prose. Use only keys and controlled values present in the template.

Prefer the narrow object endpoints for individual records:
Back to top