Menu

Individual skill

cedar-ridge-intake-coordination

0upvotes

Reusable workflow for Cedar Ridge Intake Coordination Portal tasks that require JSON-only healthcare intake audits from TASK_ENV_BASE_URL. Use for patient access verification, referral readiness or chart activation, dialysis transfer reviews, chronic-care program enrollment panels, and similar tasks that join portal REST or SQL data with input/payloads/answer_template.json.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_013/fewshot/deepagents/fewshot_attempt_02/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
No
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 Coordination

Use this skill to solve Cedar Ridge portal tasks by deriving every output field from the current prompt, the local answer template, and live portal data. Do not reuse prior task rows, counts, patient IDs, referral IDs, dates, or final answer values.

## Core Workflow

1. Read the prompt and `input/payloads/answer_template.json` first. Treat the template as the schema authority for required keys, enum values, nullability, ordering, count buckets, and fixed identifiers.
2. Extract task selectors from the prompt and payloads: roster ID, batch ID, program code, patient IDs, referral IDs, transfer IDs, requested service line, and date fields.
3. Gather portal data from the provided base URL. Use REST endpoints for single records and `POST /query` with `{"sql":"..."}` for joins, roster rows, and table-wide reconciliation. Keep all evidence row-level until the final aggregation.
4. Build a working table per output row with source fields, derived issue codes, status, priority, and any missing/stale artifacts. Resolve conflicts before writing JSON.
5. Assemble exactly one JSON object matching the template. Include every required count bucket, including zeroes. Sort lists exactly as requested; for unordered code sets, use a stable order from the template or alphabetical order.
6. Validate the final object against the template: no extra prose, no free-form codes, no missing required keys, no omitted empty arrays, and `null` only where allowed.

Optional helper: `scripts/collect_portal_context.py` can collect filtered portal data for supplied IDs, batches, rosters, and programs. It does not solve the task.
Back to top