Menu

Individual skill

ehr-quality-packet

0upvotes

Build normalized JSON for read-only EHR quality-governance tasks from a prompt, answer_template.json, and a task environment. Use for duplicate-chart merge readiness, referral coordination and audits, care transition packets, ServiceRequest validation, ICD-10/service-code/provider checks, active clinical list reconciliation, document/audit evidence selection, and schema-conforming JSON-only outputs.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/deepagents/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 Packet

## Core Workflow

1. Read the task prompt, every input payload, and the provided `answer_template.json` before querying anything. Treat the template as the output contract: preserve required keys, field names, allowed enum values, nullability, booleans, dates, and ordering rules.
2. Determine the base URL from the task environment instructions or the prompt placeholder. Use only the documented read-only endpoints.
3. Extract all stable IDs and scope terms from the prompt and payloads: patient IDs, duplicate candidate IDs, referral IDs, batch IDs, provider IDs, ServiceRequest IDs, diagnosis codes, service codes, and requested service line.
4. Fetch evidence from the API and reconcile it against the template. Use patient-scoped clinical endpoints as authoritative for current active conditions, medications, allergies, encounters, documents, immunizations, disclosures, and ServiceRequests.
5. Read [Decision Rules](references/decision_rules.md) before choosing merge dispositions, referral readiness, care-transition risks, ServiceRequest quality status, batch audit queues, tiers, or summary counts.
6. Return one JSON object only. Do not include Markdown, comments, procedural notes, citations, or keys copied from the template that are descriptive instructions rather than answer fields.

## Helpful Collection Script

Use `scripts/fetch_ehr.py` when it is faster than manual `curl` calls. It accepts a base URL plus optional IDs and prints a JSON evidence bundle:
Back to top