Individual skill
ehr-quality-packets
Produce normalized JSON packets for EHR quality governance tasks involving duplicate-chart review, referrals, care transitions, ServiceRequests, and referral batch audits.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_015/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
- 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
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Read excerpt
# EHR Quality Packets
Use this skill when a task asks for a normalized JSON packet from a read-only EHR/referral quality environment. The goal is to reconcile case objects against chart evidence and return only the fields required by the task's answer template.
## Core Workflow
1. Read the prompt and answer template before collecting data. Extract every referenced patient, referral, duplicate candidate, ServiceRequest, provider, code, batch, and recipient identifier.
2. Collect the exact records named in the prompt, then collect directly related chart lists, documents, encounters, providers, service codes, disclosures, immunizations, and diagnosis-code metadata as needed by the requested packet.
3. Treat environment records as authoritative over narrative assumptions. Use stable record IDs and normalized keys from the records rather than display text.
4. Build the response from the template outward. Do not add explanatory prose, procedural notes, or fields not requested by the template.
5. Sort arrays that represent sets alphabetically. Preserve date or relevance order only when the template or prompt asks for "latest", "recent", "top", or an ordered handoff sequence.
## Normalization Rules
