Individual skill
synthetic-clinic-protocol-json
Produce protocol-bound structured JSON answers for synthetic clinic decision-support tasks. Use when a task provides a clinic runtime base URL, a target case identifier, and an answer_template.json requiring fields such as assessment, disposition, labs, medications, care-management routing, observation-window gates, evidence IDs, and safety checks.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_016/fewshot/fewshot_attempt_03/SKILL.md
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
- engineering 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
Read excerpt
# Synthetic Clinic Protocol JSON
## Core Workflow
1. Read the task prompt and `input/payloads/answer_template.json` before calling the runtime.
2. Extract the target `case_id`, `task_id`, required keys, exact enum values, nullability, ordering rules, numeric precision, and any required constants from the template.
3. Read the runtime access file for the base URL and allowed endpoints. Use only that base URL for network calls.
4. Fetch the target case first:
- `GET /api/cases/{case_id}` when available.
- Otherwise `GET /api/cases` and filter exactly by `case_id`.
5. Use the case's `patient_id` as the primary join key. Fetch the patient and all relevant clinical collections:
- patients, observations, medications, allergies, problems, imaging, care registry, SDOH, and protocols.
6. Filter runtime data strictly to the target patient and target case. Treat records for other patients or other cases as distractors unless a protocol explicitly says otherwise.
7. Select the applicable protocol from the prompt and case type, then fetch its detail. Common protocol families include adult respiratory infection/CAP, pediatric head injury, potassium replacement, observation-window interpretation, and care-management routing.