Individual skill
synthetic-clinic-protocol-json
Produce schema-constrained JSON for synthetic clinic protocol tasks. Use when a prompt asks Codex to review a task runtime with FHIR-like cases, patients, observations, medications, allergies, problems, imaging, care registry, SDOH, or protocol records, then return only a structured clinical decision-support, routing, observation-window, or safety-check JSON object.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_016/self/self_attempt_02/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.
Read excerpt
# Synthetic Clinic Protocol JSON
## Core Workflow
1. Read the prompt and the provided answer template before querying the runtime.
2. Extract the target `case_id`, expected `task_id`, required top-level keys, enum domains, nullability, ordering rules, numeric precision, timestamp formats, and any required constants from the template.
3. Use only the runtime access file supplied with the task for network details. Do not use unlisted endpoints, credentials, or external clinical references.
4. Retrieve the target case with `GET /api/cases/{case_id}` first. This detail endpoint usually bundles the case, patient, findings, observations, medications, allergies, problems, imaging, care registry, and SDOH facts needed for the task.
5. Retrieve the protocol index with `GET /api/protocols`, choose the protocol whose title or scope matches the case type and prompt, then retrieve it with `GET /api/protocols/{protocol_id}`.
6. If the case detail is incomplete, use only the listed collection endpoints to cross-check case-linked or patient-linked records. Keep the target patient and case as the primary filter.
7. Build an evidence table before deciding: source id, record type, code/key, status, effective time, value, interpretation, and whether it qualifies.
8. Apply the protocol to qualifying evidence, then encode the result using only template-permitted keys, enums, nulls, precision, and ordering.
9. Return exactly one JSON object. Do not include markdown, explanatory prose, comments, or extra top-level keys unless the template explicitly allows them.
