Individual skill
ehr-quality-governance-packets
Build normalized JSON packets and audits from a read-only EHR quality-governance API. Use for duplicate chart merge readiness, referral coordination, care transition handoffs, ServiceRequest quality review, and referral batch audits where Codex must inspect patient, provider, ICD-10, service-code, document, disclosure, encounter, audit-log, and active clinical-list evidence and return schema-conformant JSON only.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_015/self/self_attempt_01/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.
Read excerpt
# EHR Quality Governance Packets
## Core Workflow
1. Read the task prompt and every input payload before calling the API.
2. Treat the answer template as the output contract: preserve top-level keys, field names, types, enum values, date formats, nullability, and ordering rules.
3. Read `environment_access.md` in the task workspace for the base URL and allowed endpoint list. Use only those endpoints. Do not browse the web for task evidence.
4. Fetch detail records instead of relying only on list summaries. If a list endpoint ignores query parameters, retrieve the list and filter client-side.
5. Cross-check every emitted identifier and coded value against API evidence. Return JSON only, with no prose, comments, Markdown, or reasoning.
## Evidence Collection
Use the endpoints named by the task and template:
