Individual skill
ehr-quality-packet-solver
Solve EHR quality-governance tasks that require normalized JSON from a read-only task API, including duplicate-chart merge readiness, referral coordination, care-transition packets, ServiceRequest quality checks, and referral batch audits. Use when prompts mention EHR/referral/duplicate/care-transition/audit endpoints, `<TASK_ENV_BASE_URL>`, or an `answer_template.json` schema.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/naive/fewshot_attempt_01/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
- 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.
- 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.
Read excerpt
# EHR Quality Packet Solver
Use this skill to produce schema-conformant JSON for EHR quality tasks backed by a read-only HTTP API.
## Core Workflow
1. Read the prompt and `input/payloads/answer_template.json` before calling the API.
2. Extract every explicit ID, batch ID, service line, provider ID, candidate ID, referral ID, ServiceRequest ID, and patient ID from the prompt and payloads.
3. Use only documented read-only `GET` endpoints at `<TASK_ENV_BASE_URL>`. If a list endpoint has no documented query syntax, fetch the list and filter locally.
4. Fetch detail records for the extracted objects, then fetch related patient active lists, encounters, documents, immunizations, disclosures, providers, audit logs, ICD-10 entries, and service-code entries as required by the template.
5. Populate only the keys requested by the template. Do not include template metadata fields such as descriptions, ordering hints, or schema descriptions in the final answer unless the template explicitly requires them as answer fields.
6. Return exactly one JSON object and no prose. Parse the final JSON before responding.
Suggested endpoint families: