Menu

Individual skill

ehr-packet-generation

0upvotes

Produces normalized JSON packets/audits from a read-only EHR quality-governance and referral API — duplicate-chart merge packets, referral coordination packets, care-transition packets, duplicate-review + ServiceRequest validation, and batch referral audits. Read BEFORE fetching data or filling any answer template.

experiments/claude_code_glm_5_2_max/reports/skills/task_group_015/reflect-3/reflect-3_attempt_01/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 Packet / Audit Generation

These tasks ask for a single normalized JSON object built from records spread across many read-only EHR API
resources (patients, conditions, medications, allergies, encounters, documents, immunizations, disclosures,
referrals, duplicate candidates, service-requests, providers, ICD-10, service-codes, audit-logs). The answer
must conform exactly to a per-task `answer_template.json`. The environment provides an `environment_access.md`
listing the allowed endpoints and a base URL — use those endpoints at run time; do not assume paths from memory.

## Universal workflow

1. **Read the prompt and the answer template end-to-end first.** The template is the contract: it names every
   required key, gives enums, and states ordering / set-semantics rules (e.g. "treated as a set by code",
   "sorted alphabetically", "newest to oldest"). Build the object key-for-key against the template.
2. **Fetch every referenced record.** Identify the IDs named in the prompt (patient_ids, candidate_id,
Back to top