Individual skill

ehr-quality-packet

Prepare normalized EHR quality-governance JSON packets using a read-only FHIR-aligned REST API. Use when the task requires gathering patient data, reconciling clinical lists, validating codes against ICD-10, comparing duplicate candidates, assembling referral coordination or care-transition packets, auditing referral batches, or producing any structured quality-governance output against a provided answer template. Triggers on tasks that mention EHR, FHIR, duplicate merge, referral coordination, care transition, quality governance, clinical reconciliation, or packet assembly with an answer_template.json payload.

experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_015/fewshot/codex/fewshot_attempt_01/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Instructions only
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
data 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 · 6,315 bytes
agents/openai.yamlasset · 242 bytes
references/api_endpoints.mddoc · 4,737 bytes
references/care_transition.mddoc · 3,641 bytes
references/duplicate_merge.mddoc · 3,397 bytes
references/duplicate_sr_review.mddoc · 2,817 bytes
references/referral_audit.mddoc · 4,047 bytes
references/referral_coordination.mddoc · 3,507 bytes

Read excerpt


# EHR Quality Packet

Prepare normalized quality-governance JSON packets from a read-only EHR REST API.

## Core Workflow

Every task follows the same three-stage pipeline:

1. **Read the answer template** from `input/payloads/answer_template.json`. The template defines every required key, allowed enum value, array ordering rule, and field type. Never deviate from the template shape.
2. **Gather evidence** from the API endpoints listed in [API Endpoints](references/api_endpoints.md). Start broad (patient/referral/duplicate detail), then narrow into sub-resources (conditions, medications, allergies, encounters, documents, immunizations, disclosures, audit logs, service requests). Cross-check relevant codes against ICD-10 and service-code directories. Look up providers by ID in the provider directory.
3. **Reconcile and output** normalized JSON matching the template exactly. Apply the reconciliation rules in the relevant packet pattern guide (see references/).

## API Usage Rules