Menu

Individual skill

cedar-ridge-intake-reconciliation

0upvotes

Reconcile Cedar Ridge Intake Coordination Portal tasks and produce schema-valid JSON for patient access verification, referral readiness or activation audits, dialysis transfer packet reviews, and chronic-care enrollment panels. Use when a task references the Cedar Ridge portal, an environment_access.md base URL, intake rosters, referral batches, transfer batches, program candidates, chart artifacts, ICD metadata, documents, pharmacies, or read-only SQL reconciliation.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_013/fewshot/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
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 Reconciliation

## Core Workflow

1. Read the user's prompt and every file under `input/payloads/`, especially `answer_template.json`.
2. Read `environment_access.md` when present and use only its base URL and listed endpoints for network access. Substitute any `<TASK_ENV_BASE_URL>` placeholder with that base URL. Credentials are normally absent unless the file says otherwise.
3. Identify the target object from the prompt/template: roster, referral batch, transfer batch, program code, or explicit patient/referral/transfer IDs.
4. Query the portal for the complete target cohort before reasoning. Prefer `POST /query` for compact joins, and use detail endpoints such as `/patients/{id}`, `/referrals/{id}`, `/transfers/{id}`, `/chart/{patient_id}`, `/icd/{code}`, `/documents`, and `/pharmacies` to confirm ambiguous fields.
5. Build the JSON strictly from the template: required top-level keys, controlled values, nullability, ordering rules, and summary/count keys. Do not emit prose outside JSON when the task asks for JSON only.
6. Derive every ID, date, count, and row from the current prompt/template/environment. Never reuse literal values from examples or prior tasks.

Useful portal tables exposed through read-only SQL include `patients`, `intake_rosters`, `coverage`, `pbm`, `patient_pharmacy`, `pharmacies`, `lifestyle`, `clinical_history`, `referrals`, `icd_codes`, `documents`, `transfer_requests`, `facility_capacity`, `program_candidates`, and `chart_artifacts`.

## General Validation
Back to top