Individual skill
ehr-quality-json
Use this skill for EHR quality-governance tasks that require reading a read-only task environment API and returning normalized JSON packets, especially duplicate-chart merge readiness, referral coordination, care-transition handoffs, ServiceRequest validation, ICD-10/service-code checks, provider contact lookup, and referral batch audits. Use it whenever the prompt mentions EHR, referrals, duplicate candidates, patient active lists, handoff packets, audit queues, ICD validation, or strict answer_template JSON.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/cc/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
Use this skill to solve read-only EHR quality-governance tasks that ask for a normalized JSON answer against an `answer_template.json`.
## Operating Rules
1. Read the user prompt, `input/payloads/answer_template.json`, and any other payload files before querying the API.
2. Extract every explicit ID: patient IDs, duplicate candidate IDs, referral IDs, ServiceRequest IDs, provider IDs, batch IDs, dates, and requested service lines.
3. Use only allowed GET endpoints from the task environment. Do not infer from unavailable source code or hidden evaluator behavior.
4. Treat the template as the output contract. If the template has metadata keys such as `description`, `schema`, `types`, or `required_top_level_keys`, do not emit those metadata keys unless they are actual required answer keys.
5. Return JSON only. Use exact template key names, null where the template permits null, booleans as booleans, and dates as `YYYY-MM-DD`.
6. Sort arrays when the template says they are sets or sorted. For object arrays, follow the template ordering rule; otherwise use stable domain order such as code ascending, ID ascending, or newest-to-oldest for encounter timelines.
7. Do not fabricate missing evidence. Leave fields null, false, empty, or blocked according to the template when the API does not support a claim.
