Individual skill
ehr-quality-packet-audit
Produce normalized JSON for EHR quality-governance tasks using task-provided schemas and records, including duplicate chart merge readiness packets, referral coordination packets, orthopedic care-transition summaries, ServiceRequest validation, and referral batch audits.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_015/reflect-3/reflect-3_attempt_03/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
- 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.
- 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
Read excerpt
# EHR Quality Packet Audit
## Core Workflow
1. Read the task prompt and answer template first. Treat required keys, enum values, nullability, and ordering rules as the output contract.
2. Gather only the records needed by the template from the task-provided EHR environment: case object, patient demographics, active clinical lists, encounters, documents, disclosures, immunizations, audit entries, providers, referrals, ServiceRequests, and code directories as applicable.
3. Output normalized JSON only. Use stable IDs from records, not prose explanations.
4. Sort arrays when the schema describes set semantics or an explicit sort order. Make summary counts match the emitted arrays exactly.
5. Prefer structured fields over narrative notes when they conflict. Use narrative notes to identify follow-up queues, handoff intent, or risk flags only when structured fields do not already resolve the field.
## Duplicate Review And Merge Packets
- Use the duplicate candidate's preferred target/source only when present and supported by patient canonical status. Leave target/source null when the candidate provides no merge target.
- Use active clinical-list records as authoritative for final active condition, medication, and allergy unions. Treat duplicate previews as incomplete and report active-list keys missing from the preview when the schema asks.