Individual skill

ehr-quality-governance

Reusable workflow for solving read-only EHR quality-governance JSON tasks against a task API. Use when prompts ask for normalized duplicate-chart merge readiness packets, referral coordination packets or audits, care transition packets, ServiceRequest quality checks, active-list reconciliation, ICD/service-code validation, provider contacts, evidence ID selection, risk flags, follow-up queues, action tiers, or summary counts from patient/referral/provider/duplicate records.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/deepagents/fewshot_attempt_02/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.

agent Repository topic
ai Repository topic
benchmark Repository topic
llm Repository topic
self-evolving Repository topic
self-learning Repository topic
skills Repository topic
operations 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

SKILL.mdcore · 3,547 bytes
SKILL.mdcore · 3,547 bytes
references/ehr-quality-rules.mddoc · 11,078 bytes

Read excerpt


# EHR Quality Governance

## Overview

Produce normalized JSON answers for read-only EHR quality tasks by reconciling the prompt, answer template, and task API evidence. Treat the template as the output contract and the API as the source of truth for current records.

## Required First Pass

1. Read the task prompt, every file under `input/payloads/`, and especially `answer_template.json`.
2. Read `environment_access.md` only to obtain the base URL and allowed endpoints.
3. Extract requested IDs from the prompt and payloads: patient IDs, duplicate candidate IDs, referral IDs or batch IDs, ServiceRequest IDs, provider IDs, ICD-10 codes, and service codes.
4. Fetch only the evidence needed from allowed GET endpoints. If a list/search endpoint returns more than requested, filter locally by the prompt's IDs, batch, service line, or date.
5. Read [references/ehr-quality-rules.md](references/ehr-quality-rules.md) before classifying any duplicate review, referral packet, care transition, ServiceRequest, or batch audit.
6. Fill the template exactly. Return one JSON object only; do not include prose, markdown, comments, or unrequested keys.