Individual skill
cedar-ridge-intake-reconciliation
Reconcile Cedar Ridge-style healthcare intake tasks into strict JSON outputs. Use when Codex must audit patient access, referral readiness, dialysis transfer packets, chronic-care program enrollment, or referral-to-chart activation from structured patient, insurance, pharmacy, clinical, document, capacity, ICD, referral, transfer, program, and chart-artifact records.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_013/reflect-3/reflect-3_attempt_01/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
- 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.
- agent Repository topic
- ai Repository topic
- benchmark Repository topic
- llm Repository topic
- self-evolving Repository topic
- self-learning Repository topic
- skills Repository topic
- security 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 · 8,179 bytes
Read excerpt
# Cedar Ridge Intake Reconciliation
## Core Workflow
1. Read the user prompt and answer template first. Treat the template as authoritative for required keys, enum values, nullability, list ordering, and summary count keys.
2. Build a focused working set for only the requested roster, batch, program, or cohort. Join each target row to the relevant patient profile, clinical history, coverage, PBM, pharmacy, lifestyle, ICD metadata, documents, capacity rows, program-candidate rows, and chart artifacts.
3. Normalize every output value to the template enums. Use empty arrays for no issues, `null` only where the template allows it, and compute all summaries from the final normalized patient/referral/transfer rows.
4. Sort rows exactly as requested. Treat issue-code arrays as sets unless the template says otherwise.
5. Before returning, verify totals and cross-field consistency: status counts must match row statuses, blocker sets must match per-row blocker codes, ready lists must contain only rows with no unresolved readiness blocker, and artifact/action lists must match the final disposition.
## Access And Insurance Intake
Classify insurance as valid only when coverage is active on the requested service date, in network, and includes the requested service line. Mark expired, pending, excluded-service-line, or absent coverage with the corresponding controlled blocker code.
