Menu

Individual skill

synthetic-clinic-protocol-json

0upvotes

Use this skill whenever a task asks for a structured JSON clinical decision-support, protocol assessment, care-management routing, potassium/lab gate, respiratory, or pediatric head-injury response from the synthetic clinic runtime environment. It is especially relevant when the prompt mentions Harborview Synthetic Clinic, a CASE-* id, input/payloads/answer_template.json, environment_access.md, or a requirement to return only one JSON object.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_016/fewshot/cc/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

# Synthetic Clinic Protocol JSON

Use this skill to produce protocol-bound JSON from the synthetic clinic runtime. The core task is not free-text medical advice: it is structured extraction, protocol application, and template-conformant serialization.

## Workflow

1. Read the user prompt, `environment_access.md`, and `input/payloads/answer_template.json`.
2. Extract the target `case_id`, the required `task_id` if one is stated or encoded in the template, and the runtime `base_url`.
3. Use only endpoints allowed by `environment_access.md`. Fetch `GET /api/cases/{case_id}` first; it normally bundles the case, patient, findings, observations, imaging, allergies, medications, problems, care registry, and SDOH facts needed for scoring.
4. Fetch `/api/protocols`, select the protocol matching the case type or prompt theme, then fetch `/api/protocols/{protocol_id}`. Apply protocol thresholds and status rules before filling template fields.
5. Build the answer by the template, not by prose intuition. Preserve exactly the required top-level keys, enum spellings, nullability, and numeric precision. Do not add extra top-level keys unless the template explicitly permits them.
6. Return only a JSON object. Do not include markdown, explanations, citations outside `evidence_ids`, or comments.

For detailed field mapping, read [clinical_runtime_protocols.md](references/clinical_runtime_protocols.md). For a deterministic first draft, you may run:
Back to top