Individual skill
synthetic-clinic-json-protocol
Solve synthetic clinic runtime tasks that require reading a prompt, task-provided answer template, and environment_access.md, querying read-only clinic API endpoints, applying protocol material to patient/case data, and returning one schema-exact JSON object. Use for clinical decision-support, lab-window, medication, respiratory, head-injury, care-management, and similar protocol-bound structured-answer tasks.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_016/fewshot/naive/fewshot_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 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.
Read excerpt
# Synthetic Clinic JSON Protocol
Use this skill to produce a strict JSON answer for a synthetic clinic task. Treat the prompt, the task payload template, environment access instructions, and live read-only clinic data as the only authority.
## Required Workflow
1. Read the user prompt and the task-provided answer template before querying data.
2. Read `environment_access.md` for the base URL, required headers, and allowed endpoints. Use only listed read-only business endpoints. Do not call judge, scoring, mutation, order-entry, or unlisted endpoints.
3. Extract the target task id, case id, requested clinical domain, required output keys, constants, enum values, numeric precision, ordering rules, nullable fields, and safety booleans from the prompt and template.
4. Build an internal answer skeleton from the template. Do not invent keys. If the template forbids extra keys, return exactly the required top-level keys.
5. Retrieve the target case first, then retrieve the patient and all data needed by the case and protocol: observations, medications, allergies, problems, imaging, care-registry entries, social-context records, and protocol documents. Prefer case-linked ids when present; otherwise filter collection endpoints by patient id, case id, code, date window, protocol name, or domain.
6. Apply the protocol to the retrieved facts. Fill controlled fields with exact enum spellings from the template, not prose.
7. Return one JSON object only. Do not include markdown, comments, citations outside JSON, or explanatory text.
