Individual skill
clinic-protocol-json
Produce exact schema-conformant JSON for synthetic clinic decision-support tasks that require reviewing a runtime patient case, FHIR-like clinical records, observations, medications, allergies, imaging, registry or social-context data, and applicable protocol material. Use for protocol-bound triage, medication, lab-window, care-routing, safety-check, and evidence-provenance outputs driven by an answer_template.json.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_016/reflect-3/reflect-3_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
- data 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 provided answer template before retrieving facts. Treat the template as the output contract: include every required top-level and nested key, use only allowed enum values, preserve required object shapes, and add no extra keys unless the template explicitly permits them.
2. Identify the target case, patient, clinical domain, requested decision, and any target dates, windows, codes, or current-time anchors.
3. Retrieve the target case record first, then gather only supporting records needed by the prompt and template: patient demographics, findings, observations, active medications, active allergies, problems, imaging, registry facts, social-context facts, and the relevant protocol.
4. Build a compact fact table before drafting JSON. Track value, status, effective time, patient id, code, interpretation, and source id for each fact that may affect a required field.
5. Apply the protocol before clinical intuition. Use protocol thresholds, controlled codes, authoritative statuses, routing criteria, ordering rules, and follow-up timing conventions as the primary source of truth.
6. Draft the JSON from the template outward, then validate exact enums, timestamps, numeric precision, array ordering, duplicate removal, allowed nulls, and consistency between assessment fields, safety checks, and evidence.
## Record Selection
- Match records to the target patient unless the template specifically asks for excluded or distractor records.