Individual skill

clinic-protocol-json

Produce exact JSON answers for synthetic clinic protocol decision-support tasks that provide a runtime environment, a target case, patient clinical data, protocol material, and an answer_template.json schema. Use for respiratory, pediatric head injury, potassium replacement, observation-window, care-management, and similar clinic cases that require environment-backed facts, controlled enums, evidence identifiers, safety checks, and no prose outside JSON.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_016/fewshot/codex/fewshot_attempt_02/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.

agent Repository topic
ai Repository topic
benchmark Repository topic
llm Repository topic
self-evolving Repository topic
self-learning Repository topic
skills Repository topic
data 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 · 8,855 bytes
SKILL.mdcore · 8,855 bytes

Read excerpt


# Clinic Protocol JSON

## Core Workflow

Use the task's `answer_template.json` as the output contract before reasoning about the case.

1. Extract the required top-level keys, expected constants, allowed enum values, nullable fields, numeric precision, and ordering rules.
2. Read the runtime access file supplied with the task. Set `BASE_URL` from it and use only the listed endpoints.
3. Retrieve the target case with `GET $BASE_URL/api/cases/{case_id}`. Treat this detail endpoint as the primary bundle: case, patient, findings, observations, imaging, allergies, medications, problems, care registry, and SDOH.
4. Retrieve `GET $BASE_URL/api/protocols`, then read the protocol whose title or scope matches the case type. Use `GET $BASE_URL/api/protocols/{protocol_id}` for the body.
5. Fill only fields requested by the template. Do not add narrative, markdown, comments, or extra keys.
6. Validate the final object against the template manually: key presence, enum spelling, nullability, numeric precision, evidence IDs, and required safety booleans.

Prefer case-detail records over broad endpoint lists. Use broad endpoints only to recover missing linked data, then filter by target `patient_id`, `case_id`, code, status, and time window as the template requires.