Individual skill

ehr-governance-packet

Build a normalized JSON quality-governance packet from the read-only EHR governance API. Use for any task that hands you a prompt.txt plus an input/payloads/answer_template.json and asks you to produce JSON about duplicate-chart merge readiness, referral coordination, care-transition handoff, duplicate/ServiceRequest validation, or referral-batch audit, driven by a base URL described in environment_access.md.

experiments/claude_code_opus_4_8_xhigh/reports/skills/task_group_015/self/self_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: Yes
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
security 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 · 9,009 bytes
references/api_map.mddoc · 5,170 bytes
references/task_playbooks.mddoc · 7,373 bytes

Read excerpt


# EHR Quality-Governance Packet Builder

## What this is

These tasks all follow one shape: a short `prompt.txt` names some case objects
(patient IDs, a duplicate-candidate ID, a referral or batch ID, a ServiceRequest
ID, a recipient provider), and an `input/payloads/answer_template.json` fixes the
exact JSON you must return. Your job is to gather evidence from a **read-only EHR
API**, apply the reconciliation/validation rules below, and emit JSON that
conforms to the template *exactly* — no prose, no SOP narrative, no extra keys.

The template is the contract. Read it first and last: it dictates every key,
every enum vocabulary, every required literal value, and every sort order. When
this document and a template disagree, the template wins.