Individual skill
ehr-quality-packet-builder
Build normalized JSON packets and audits from EHR quality-governance data. Use when Codex must reconcile patient charts, duplicate candidates, referrals, ServiceRequests, provider records, clinical lists, documents, encounters, immunizations, disclosures, ICD/service-code metadata, or batch referral queues into a strict answer template.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_015/reflect-3/reflect-3_attempt_01/SKILL.md
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 11, 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.
Read excerpt
# EHR Quality Packet Builder
## Core Workflow
1. Read the user prompt and the answer template first. Treat the template as the contract for top-level keys, enum values, field names, sort order, and whether arrays are sets.
2. Identify the governing object IDs from the prompt, then gather the minimum supporting records needed for those IDs: primary objects, patient demographics, active clinical lists, provider details, documents, encounters, immunizations, disclosures, diagnosis-code metadata, and service-code metadata.
3. Build the answer from evidence, not narrative assumptions. Prefer directory/lookup records over free text when validating codes, providers, service lines, or contact fields.
4. Emit JSON only. Preserve the template shape, use `null` only when the template permits it, and do not add explanatory keys.
5. Sort ID arrays and normalized-key arrays ascending unless the template gives a different order. Sort encounter handoff lists by the requested clinical rule, commonly newest to oldest.
6. Keep counts synchronized with the arrays they summarize.
## Active Lists
- Include only active clinical records when a field asks for current condition, medication, or allergy keys.