Menu

Individual skill

cedar-ridge-intake-reconciliation

Complete Cedar Ridge Intake Coordination Portal audit tasks that require strict JSON answers from an answer_template, including patient access verification, specialty referral readiness, referral-to-chart activation, dialysis transfer packet and capacity review, and chronic-care program enrollment reconciliation.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_013/fewshot/codex/fewshot_attempt_03/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
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

Use this skill when a prompt points to the Cedar Ridge Intake Coordination Portal and asks for a JSON object matching an `answer_template.json`.

1. Read the prompt and every payload file first. Treat the template as the output contract: required keys, allowed enum values, ordering, constants, and count keys are authoritative.
2. Extract target identifiers from the prompt and payloads: roster IDs, batch IDs, program codes, patient IDs, referral IDs, transfer IDs, requested dates, and service lines.
3. Gather portal evidence from the task base URL. Use direct endpoints for individual records and `/query` for joins, rosters, coverage, PBM, capacity, and chart artifacts. The helper [scripts/portal_snapshot.py](scripts/portal_snapshot.py) can fetch allowed GET paths and common SQL-backed snapshots.
4. Filter out distractors before reasoning. Keep only records tied to the target roster, batch, program, or explicit IDs, then pull related patient, chart, ICD, document, pharmacy, coverage, PBM, lifestyle, capacity, and clinical-history rows.
5. Build a compact evidence table per patient/referral/transfer. Record source fields beside each normalized output value so every status, reason code, blocker, and summary count is traceable.
6. Apply the reusable Cedar Ridge rules in [references/cedar_ridge_rules.md](references/cedar_ridge_rules.md). Prefer direct portal fields and template wording over assumptions.
7. Assemble JSON only. Sort arrays exactly as the template says, use only controlled values, include empty arrays/zero counts where required, and compute summaries from the emitted rows.
8. Smoke-test the result with [scripts/check_json_shape.py](scripts/check_json_shape.py), then manually verify enum values, ordering, and business logic against the template.