Individual skill
clinic-protocol-json
Build protocol-bound structured JSON answers for synthetic clinic runtime tasks. Use when Codex must inspect a provided clinical runtime environment and answer from a strict JSON template for respiratory assessment, pediatric head injury triage, potassium replacement or lab-window decisions, care-management routing, or similar FHIR-like case/protocol workflows.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_016/reflect-3/reflect-3_attempt_01/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 11, 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
# Clinic Protocol JSON
## Core Workflow
1. Read the user prompt and the answer template before retrieving data. Treat the template as the contract: required keys, enums, nullability, ordering, and numeric precision all matter.
2. Identify the target case ID from the prompt, then resolve the patient ID from the case record. Do not rely on patient names or case summaries alone.
3. Retrieve the target case, patient context, applicable protocol, and only the clinical domains needed by the template. Prefer targeted case/patient data when available, then use broader resource lists only to find distractors or confirm omissions.
4. Build a small evidence table while reading: source ID, resource type, status, code, time, patient ID, value, and whether it supports or excludes a template field.
5. Apply the protocol before filling disposition, treatment, routing, gate, or follow-up fields. Use protocol thresholds and controlled codes over general clinical intuition.
6. Fill the JSON from high-confidence identifiers and scalar fields first, then coded sets, then evidence IDs and safety checks. Return exactly one JSON object with no markdown or prose.
## Evidence Discipline
- Use only authoritative resource statuses unless the protocol says otherwise. Most observation tasks reward `final` results and exclude `preliminary`, `canceled`, and `entered-in-error`.