Menu

Individual skill

ehr-quality-packets

0upvotes

Build normalized JSON for EHR quality-governance tasks that provide a TASK_ENV_BASE_URL and an answer_template. Use for duplicate merge readiness packets, referral coordination packets, care transition handoffs, ServiceRequest/SBAR validation, and referral batch audits that require reading patient, referral, duplicate-candidate, provider, ICD-10, service-code, document, audit, disclosure, immunization, encounter, condition, medication, and allergy endpoints.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/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
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 Packets

Use this skill to solve EHR quality-governance tasks that require a single normalized JSON response from a read-only task API.

## Workflow

1. Read the user prompt and `input/payloads/answer_template.json` first. Treat the template as the output contract: preserve required top-level keys, field names, types, enum spelling, nullability, and ordering notes. Do not include template metadata fields such as `description`, `schema`, `types`, or ordering annotations unless the template explicitly requires them in the final object.
2. Resolve `<TASK_ENV_BASE_URL>` from the task prompt, environment variable, or `environment_access.md` if present. Use only the public task API endpoints needed for the case.
3. Fetch evidence for every ID and batch named in the prompt. Also fetch dependent records referenced by those records, especially patient active lists, providers, ICD-10 entries, service-code entries, documents, encounters, disclosures, immunizations, and audit logs when the requested packet asks for them.
4. Reconcile each answer field against primary evidence, not just summary records. Patient active-list endpoints are authoritative for active conditions, medications, and allergies; duplicate previews and referral rows are starting points to cross-check.
5. Emit JSON only. Use stable IDs and normalized codes rather than narrative explanations. Sort arrays exactly as the template says; if it says a list is a set and gives no special order, sort strings alphabetically/ascending and objects by the ID or code field named in the template.
6. Validate before final: parse with `python3 -m json.tool`, compare keys against the template, verify every enum value is allowed, and check that no explanatory prose surrounds the JSON.

## Context Helper
Back to top