Individual skill
ehr-quality-json-packets
Produce normalized JSON for read-only EHR quality-governance tasks by querying task-environment APIs and reconciling duplicate candidates, referrals, ServiceRequests, care-transition packets, documents, providers, ICD-10 codes, and active clinical lists. Use whenever a prompt asks for an EHR/referral/duplicate/merge-readiness/care-transition/audit packet that must conform exactly to an answer_template.json.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/opencode/fewshot_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.
Browse files
Read excerpt
# EHR Quality JSON Packets
Use this skill for read-only EHR quality tasks where the answer must be one normalized JSON object derived from a task environment API and a local `answer_template.json`.
## First Pass
1. Read the user prompt, `input/payloads/answer_template.json`, every other payload file, and `environment_access.md` if present.
2. Extract the explicit identifiers: patient IDs, candidate IDs, referral IDs, ServiceRequest IDs, provider IDs, batch IDs, service line, requested date, and requested packet type.
3. Treat the template as the output contract. Preserve required top-level keys, nested keys, JSON types, enum spelling, date format, nullability, and any ordering rules.
4. Use the API as the source of truth. Do not infer final values from identifier names, examples, or general medical knowledge when an endpoint can verify them.
5. Return JSON only. Do not include markdown, comments, prose, citations, or procedural notes outside the JSON object.
## API Collection Pattern