Individual skill
ehr-quality-json-packets
Create normalized JSON packets for EHR quality-governance tasks that require querying a read-only task API. Use for duplicate chart merge readiness, referral coordination, care transition handoff packets, ServiceRequest quality checks, ICD-10 and service-code validation, and referral batch audits where the prompt provides an answer_template.json and IDs such as patient, referral, duplicate candidate, provider, ServiceRequest, or batch identifiers.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/deepagents/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
- engineering 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 prompt and `input/payloads/answer_template.json` before querying.
2. Extract all identifiers from the prompt and payloads: patient IDs, duplicate candidate IDs, referral IDs, ServiceRequest IDs, provider IDs, batch IDs, requested service line, requested recipient, and required output sections.
3. Query the task API for direct records and supporting evidence. Use `scripts/ehr_quality_fetch.py` when it helps collect a bundle quickly, or use `curl`/Python directly.
4. Build the answer from live API evidence and the template only. Do not use memorized train-case values, hidden assumptions, or narrative explanations outside JSON.
5. Conform exactly to the requested schema. Preserve required keys, enum strings, booleans, nullability, and date format. Sort arrays whenever the template says set semantics, sorted ascending, or stable ordering.
6. Before finalizing, recompute all summary counts and readiness fields from the emitted arrays and blocking issues.
## API Collection
Use the base URL supplied by the task prompt or environment. The helper accepts `--base-url`; otherwise set `TASK_ENV_BASE_URL`.