Menu

Individual skill

ehr-quality-packets

0upvotes

Solve EHR quality-governance tasks that require normalized JSON from a read-only task environment, including duplicate-chart merge readiness, referral coordination, care-transition packets, ServiceRequest quality review, ICD/service-code validation, and referral batch audits. Use when prompts mention an EHR/referral quality API, duplicate candidates, patient active lists, providers, disclosures, documents, audit logs, or answer templates for normalized packet output.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/naive/fewshot_attempt_03/SKILL.md

Read pinned source

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.

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 and the referenced answer template before fetching data. Treat the template as the exact output contract: preserve required top-level keys, enum strings, nullability, object shapes, and ordering notes.
2. Extract all explicit IDs from the prompt: patient, candidate, referral, batch, provider, and ServiceRequest IDs. Use the task environment base URL supplied by the prompt or environment file.
3. Fetch only read-only GET endpoints. Prefer exact detail endpoints when an ID is known, then fetch patient-scoped supporting data.
4. Build the answer from API evidence, not from prompt labels alone. When prompt wording conflicts with endpoint details, decide whether the template asks for raw source status or a normalized quality-review status.
5. Return JSON only. Do not include prose, comments, markdown fences, or fields not present in the template.

Useful fetch pattern:

```bash
BASE="${TASK_ENV_BASE_URL%/}"
Back to top