Menu

Individual skill

ehr-quality-json-packets

0upvotes

Solve read-only EHR quality-governance tasks by querying the allowed API endpoints and returning schema-conformant normalized JSON packets.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/naive/fewshot_attempt_02/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 11, 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 JSON Packets

Use this skill when a task asks for a normalized JSON answer built from the shared read-only EHR quality environment, especially duplicate-chart review, referral coordination, care-transition packets, ServiceRequest quality checks, or referral-batch audits.

## Operating Rules

1. Read the task prompt and `input/payloads/answer_template.json` before querying the environment.
2. Treat the template as the contract. Emit exactly the requested top-level keys, nested keys, data types, enum values, nullability, and ordering rules.
3. Use only the base URL supplied in the task environment instructions and only documented HTTP GET endpoints. Do not POST, mutate state, call hidden endpoints, or rely on unstated evaluator behavior.
4. Extract all stable identifiers from the prompt and payloads first: patient IDs, duplicate candidate IDs, referral IDs, batch IDs, ServiceRequest IDs, provider IDs, service codes, and ICD-10 codes.
5. Build a source ledger while working. For every final field, know which API record supplied it. Include evidence IDs only when the template asks for them and the records are directly relevant.
6. Return JSON only. Do not include markdown, comments, narrative explanations, or procedural notes in the final answer.

Useful command pattern:
Back to top