Menu

Individual skill

clinic-protocol-json

0upvotes

Use for synthetic clinic tasks that require protocol-bound clinical decision-support JSON from a runtime environment, especially respiratory/CAP, pediatric head injury, potassium repletion, care-management routing, and observation-window retrieval cases.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_016/fewshot/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

# Clinic Protocol JSON

Use this skill when the user asks for a structured JSON answer for a synthetic clinic case using a runtime environment and an `answer_template.json`.

## Core Workflow

1. Read the user prompt and the full `input/payloads/answer_template.json`. The template is the output contract; preserve required keys, enum spellings, nullability, numeric precision, and ordering rules.
2. Read `environment_access.md` for the base URL and allowed endpoints. Use only those endpoints. Do not mutate the environment or place orders.
3. Extract the target `case_id` and `task_id`. Fetch `GET /api/cases/{case_id}` first; it usually returns the case, patient, findings, observations, medications, allergies, problems, imaging, care registry, and SDOH facts.
4. Fetch `GET /api/protocols` and the protocol matching the case type or prompt. Use aggregate endpoints only when the case detail is incomplete.
5. Build the answer from source data and protocol rules, not from prior examples. Include only stable identifiers that support selected facts.
6. Return exactly one JSON object. No markdown, comments, prose, or extra top-level keys.

Useful protocol mapping:
Back to top