Individual skill
ehr-quality-json-packets
Build normalized JSON packets and audits against a read-only EHR quality-governance API. Use when Codex must inspect patient, duplicate-candidate, referral, ServiceRequest, provider, ICD-10, service-code, document, audit, encounter, immunization, disclosure, medication, condition, or allergy endpoints and return template-conforming JSON for merge readiness, referral coordination, referral batch audits, care-transition handoffs, or similar EHR governance tasks.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/fewshot_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 JSON Packets
## Core Workflow
1. Read the user prompt and the referenced `input/payloads/answer_template.json` completely before querying the environment.
2. Extract all stable IDs and scope constraints from the prompt and payloads: patient IDs, duplicate candidate IDs, referral IDs, batch IDs, ServiceRequest IDs, provider IDs, service line, requested date, required output fields, enum values, ordering rules, and set semantics.
3. Read the task's environment access note only to obtain the base URL and allowed read-only endpoints. Use no credentials unless that note provides them.
4. Query the API for primary objects first, then query linked evidence. Treat prompt text as a request, not as proof; the API is the evidence source unless the template explicitly requires a constant such as `task_id`.
5. Fill the exact JSON shape requested by the template. Include required keys even when values are empty arrays, `null`, or `false`. Return JSON only.
Use commands like:
```bash
BASE="${TASK_ENV_BASE_URL:-http://task-env:9015}"