Individual skill

ehr-quality-governance

Use for read-only EHR quality-governance tasks that require querying a task environment API and returning strict normalized JSON for duplicate reviews, merge readiness, referral coordination, ServiceRequest validation, care-transition packets, or referral batch audits using patient, provider, ICD-10, document, audit, and active-list evidence.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_015/fewshot/codex/fewshot_attempt_03/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: 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
security 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 · 4,546 bytes
agents/openai.yamlasset · 220 bytes
references/evidence-playbook.mddoc · 7,015 bytes
scripts/fetch_ehr_evidence.pyruns · 5,022 bytes

Read excerpt


# EHR Quality Governance

## Core Rules

- Treat the prompt, `answer_template.json`, and any request payload as the output contract. Return JSON only, with exactly the requested shape, enum values, nullability, and ordering.
- Derive every answer value from the current task environment. Do not reuse IDs, dates, names, codes, or packet values from examples.
- Use only read-only endpoints made available by the task environment. Prefer the base URL from `TASK_ENV_BASE_URL`; if absent, read the task's environment access file.
- Read [references/evidence-playbook.md](references/evidence-playbook.md) before solving. It contains the reusable reconciliation and classification rules.
- Use [scripts/fetch_ehr_evidence.py](scripts/fetch_ehr_evidence.py) when it helps collect common EHR records consistently. The script is optional; direct `curl`/HTTP requests are fine when faster.

## Workflow

1. Parse the task.
   - Extract patient IDs, duplicate candidate IDs, referral IDs, ServiceRequest IDs, provider IDs, batch IDs, requested service line, and any named payload files.