Individual skill

synthetic-clinic-protocol-json

Solve synthetic clinic protocol tasks that require querying a read-only clinic runtime, applying patient/case/protocol evidence, and returning exactly one JSON object matching an answer_template.json schema. Use for respiratory CAP, pediatric head injury, potassium replacement, observation-window lab gates, care-management routing, or similar Harborview Synthetic Clinic decision-support tasks.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_016/fewshot/naive/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
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

SKILL.mdcore · 5,386 bytes
SKILL.mdcore · 5,386 bytes
SKILL.mdcore · 5,386 bytes
scripts/collect_clinic_context.pyruns · 4,882 bytes

Read excerpt


# Synthetic Clinic Protocol JSON

## Core Workflow

1. Read the user prompt, `input/payloads/answer_template.json`, and the run's environment access file before querying anything.
2. Extract the required `task_id`, target `case_id`, output schema, required keys, allowed enum values, ordering rules, nullability, and numeric precision from the template.
3. Query only the allowed read-only clinic runtime endpoints. Never call judge or mutation/order endpoints.
4. Retrieve the target case first, then use its `patient_id`, `case_type`, service/review time, and protocol references to gather relevant patient, observation, medication, allergy, problem, imaging, registry, SDOH, and protocol evidence.
5. Apply the protocol material from the runtime to the target patient's facts. Do not infer unsupported positives or negatives from the few-shot examples.
6. Build the response directly from the template. Return exactly one JSON object with required keys, no markdown, no comments, and no extra narrative.

## Optional Evidence Collector

Use `scripts/collect_clinic_context.py` when you want a deterministic first pass over the runtime data: