Individual skill

synthetic-clinic-protocol-cds

Produce a single protocol-bound JSON decision-support object for a synthetic clinic case. Use when a task names a clinic case id, points to a clinic runtime environment whose access is listed separately, supplies an answer_template.json, and asks you to return only a JSON object driven by clinic protocol rules. Covers respiratory, pediatric head-injury, potassium repletion, care-management routing, and observation-window retrieval task families.

experiments/claude_code_glm_5_2_max/reports/skills/task_group_016/reflect-3/reflect-3_attempt_01/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Instructions only
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.

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

# Synthetic Clinic Protocol Decision Support

This skill solves tasks of the form: given a clinic **case id**, a **runtime environment** (access details provided separately per run), and an **answer template**, return exactly one JSON object whose fields are derived from the case record and the matching **clinic protocol** — not from general medical knowledge alone.

The protocol is the source of truth for thresholds, codes, and allowed enum values. The template is the source of truth for required keys, types, and precision. General clinical reasoning fills the gaps, but never overrides an explicit protocol rule.

## 0. Inputs you receive

- **Task prompt** — names the target `case_id` (and sometimes the target patient/code/window) and lists what the response must contain.
- **answer_template.json** — the schema: `required_top_level_keys`, per-field `type`/`allowed_values`/`required_keys`, `ordering`/`ordering_rule` notes, and `numeric_precision`/`output_rule` notes. Treat it as a strict contract.
- **Runtime environment access** — provided **separately** for the run (base URL, allowed endpoints, any required auth header/token). Do not assume endpoints or credentials; read them from the access material each run.
- **Protocols** — live in the runtime, keyed by `protocol_id`; each has a `body` of rules.

## 1. Procedure