Individual skill
ehr-governance-packet-builder
Build normalized-JSON deliverables for EHR quality-governance queue tasks from a read-only EHR API. Use when a prompt gives case objects (patient / duplicate-candidate / referral / ServiceRequest / batch IDs), points to a read-only EHR environment (a base URL in environment_access.md), and asks for JSON conforming to an input/payloads/answer_template.json. Covers duplicate-chart merge-readiness packets, referral coordination packets, care-transition packets, duplicate + ServiceRequest reviews, and referral batch audits.
experiments/claude_code_opus_4_8_xhigh/reports/skills/task_group_015/self/self_attempt_03/SKILL.md
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
- engineering 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 · 8,078 bytesreferences/api_reference.mddoc · 4,723 bytesreferences/normalization_rules.mddoc · 7,487 bytesreferences/task_archetypes.mddoc · 3,650 bytes
Read excerpt
# EHR governance packet builder
You are given a task folder that contains a `prompt.txt`, a `input/payloads/answer_template.json`, sometimes
extra request payloads, and an `environment_access.md`. Your job is to query a read-only EHR
"quality-governance" API and emit **one normalized JSON object** that conforms exactly to the answer template.
No prose, no SOP/narrative text — JSON only.
Every task in this family is the same shape: *read the contract, gather evidence from the API, normalize it,
classify a disposition/readiness, and assemble stable IDs into the template's structure.* The templates and
case objects change; the operating rules below do not.
## 1. Read the contract before touching the API
1. **`prompt.txt`** — extract the case objects (the IDs you must center on): patient_id(s), duplicate