Menu

Individual skill

ehr-quality-packet-json

Generate normalized JSON packets and audits from read-only EHR quality-governance environments. Use when a task asks Codex to inspect EHR/referral/duplicate/service-request evidence through allowed API endpoints and return schema-conformant JSON for duplicate chart review, referral coordination, care transitions, service request quality checks, or referral batch audits.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_015/self/self_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
Instructions only
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

# EHR Quality Packet JSON

Use this skill to produce evidence-grounded, normalized JSON for EHR quality-governance tasks. Treat the prompt and `input/payloads/answer_template.json` as the contract. Do not include prose outside the final JSON.

## Core Workflow

1. Read the task prompt, every file in `input/payloads/`, and `environment_access.md`.
2. Use only the base URL and endpoints listed in `environment_access.md` for network access.
3. Extract all requested stable IDs from the prompt and payloads: patient, duplicate candidate, referral, service request, provider, batch, document, or request IDs.
4. Inspect the primary object first, then fetch all supporting evidence needed by the template:
   - patient demographics and identifiers
   - active conditions, medications, and allergies
   - encounters, documents, immunizations, disclosures, and audit logs
   - duplicate candidates and duplicate details