Individual skill
ehr-quality-packets
Use when producing normalized JSON packets or audits from a read-only EHR quality-governance API, including duplicate-chart merge readiness, referral coordination, care-transition handoffs, ServiceRequest quality checks, ICD-10/service-code validation, active-list reconciliation, document/audit evidence selection, provider contacts, follow-up queues, action tiers, and summary counts.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/fewshot_attempt_02/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 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 Packets
## Core Workflow
1. Read the user prompt, every file under `input/payloads/`, and especially `answer_template.json`.
2. Read `environment_access.md` for the task environment base URL and allowed endpoints. Use only that base URL for network access; do not use outside medical knowledge or other network sources.
3. Extract all requested IDs and filters from the prompt and payloads: patient IDs, duplicate candidate IDs, referral IDs, batch IDs, ServiceRequest IDs, provider IDs, service lines, and requested output sections.
4. Fetch evidence from the API. Prefer object-detail endpoints when an ID is known. If a search/list endpoint returns more than the requested scope, filter locally by the requested ID, `batch_id`, patient, service line, or date.
5. Build the response directly from the template shape. Preserve required top-level keys, required constants, enums, nullability, and date formats. Do not include prose outside the JSON object.
6. Sort arrays with set semantics alphabetically or by the ordering rule in the template. Deduplicate normalized keys and IDs before output.
Useful endpoint families:
- Duplicate review: `/api/duplicates/candidates`, `/api/duplicates/{candidate_id}`, patient detail, active conditions/medications/allergies, documents, and `/api/audit-logs`.