Individual skill
cedar-ridge-intake-reconciliation
Reconcile Cedar Ridge intake coordination tasks into controlled JSON outputs. Use when Codex must prepare roster access verification, specialty referral readiness, dialysis transfer intake, chronic-care enrollment panels, or referral-to-chart activation files from task prompts, answer templates, and Cedar Ridge patient/chart/document/coverage/ICD/capacity data.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_013/reflect-3/reflect-3_attempt_02/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
- data 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 · 8,902 bytes
Read excerpt
# Cedar Ridge Intake Reconciliation
## Core Workflow
1. Read the prompt and answer template before analyzing records. Treat the template as the contract for top-level keys, item keys, enums, ordering, nullability, and summary count buckets.
2. Identify the target cohort from the prompt/template: roster, referral batch, transfer batch, program code, or explicit patient/referral/transfer IDs.
3. Gather only target rows and directly related records: patient demographics, coverage, PBM, preferred pharmacy, lifestyle, ICD metadata, documents, chart artifacts, clinical history, and capacity as relevant to the template.
4. Normalize every output value to the template enums exactly. Do not invent reason codes, statuses, summary keys, or explanatory fields.
5. Apply the template ordering literally. Sort ID lists ascending unless the template specifies another order; sort unordered reason-code sets deterministically for readability.
6. Recompute summaries from the finished per-patient or per-referral rows. Include all required zero-count keys when the template names fixed count buckets.
7. Return JSON only when the task asks for JSON. Before finalizing, verify required top-level keys, cohort completeness, ID ordering, controlled values, and count reconciliation.
## Access Verification
