Individual skill

synthetic-clinic-cds

Produce strict JSON clinical decision-support answers for synthetic clinic runtime tasks. Use when a prompt provides a target case id, an answer_template.json schema, and task environment API access for protocol-bound assessments such as respiratory infection, pediatric head injury, potassium replacement, care-management routing, or observation-window lab gates.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_016/fewshot/deepagents/fewshot_attempt_02/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.

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

SKILL.mdcore · 4,750 bytes
SKILL.mdcore · 4,750 bytes
scripts/collect_context.pyruns · 4,741 bytes

Read excerpt


# Synthetic Clinic CDS

## Workflow

1. Read the task prompt, the runtime access file, and `input/payloads/answer_template.json` before fetching data or drafting an answer.
2. Extract the target `case_id`, the required `task_id`, any requested time window or target code, and every required key, enum, nullability, ordering rule, and precision rule from the template.
3. Fetch the target case from the runtime API, then resolve the patient and gather case-scoped facts from patients, observations, medications, allergies, problems, imaging, care registry, SDOH, and the applicable protocol records. Use [scripts/collect_context.py](scripts/collect_context.py) when a local context bundle is useful:

```bash
python skill/scripts/collect_context.py --base-url "$TASK_ENV_BASE_URL" --case-id "$CASE_ID" > context.json
```

4. Treat the API records and protocol material as authoritative. Do not use training-example constants, memorized thresholds, or unsupported clinical assumptions.
5. Fill exactly the required JSON object. Do not include markdown, comments, narrative text, extra top-level keys, or enum values outside the template.