Individual skill

synthetic-clinic-protocol-json

Solve synthetic clinic runtime tasks that ask for a protocol-bound clinical, care-management, observation-window, medication, imaging, or safety decision as one schema-exact JSON object. Use when a prompt provides a clinic task environment URL plus an answer_template.json and asks Codex to retrieve patient/case data, apply clinic protocol material, cite evidence identifiers, and return only controlled JSON.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_016/fewshot/opencode/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
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

# Synthetic Clinic Protocol JSON

Use this skill for read-only synthetic clinic tasks where the answer must be a single JSON object matching a provided `input/payloads/answer_template.json`.

## Core Workflow

1. Read the user prompt and `input/payloads/answer_template.json` before fetching data.
   Extract the `task_id`, target `case_id`, required top-level keys, enum values, nullable fields, numeric precision, ordering rules, and safety-check booleans from the template.

2. Read the task's environment access note for the base URL and allowed endpoints.
   Use only read-only access. Do not mutate the runtime or place orders. `POST /api/query` may be used only as a read-only query mechanism if the task environment exposes it for retrieval.

3. Fetch the target case, patient, and all relevant clinical collections.
   Start with the case record, then gather patient details, observations, medications, allergies, problems, imaging, care registry, social-context data, and protocols as relevant to the task domain. The helper [scripts/fetch_clinic_bundle.py](scripts/fetch_clinic_bundle.py) can fetch the standard GET endpoints into local JSON files.