Menu

Individual skill

synthetic-clinic-protocol-cds

0upvotes

Reusable entry instructions for solving protocol-bound clinical decision-support (CDS) tasks against the Harborview Synthetic Clinic REST runtime. Use whenever a task points at a target case id and a <TASK_ENV_BASE_URL> placeholder, ships an answer_template.json output contract, and asks for a single structured JSON result (assessments, risk tiers, dispositions, medication/order plans, lab/observation windows, care-management routing, etc.). Covers runtime access, evidence gathering, protocol application, and strict template conformance.

experiments/claude_code_glm_5_2_max/reports/skills/task_group_016/self/self_attempt_03/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.

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 CDS — Operating Rules

These rules are distilled from the train-task family. They are **generic**: they never hardcode a specific case, patient, medication, dose, or numeric result. Every value in a final answer must come from the live runtime or from protocol material fetched at run time.

## 0. What a task looks like

Every task in this family has the same three inputs:

1. **A prompt** (`prompt.txt`) that names a target `case_id`, references the runtime via a `<TASK_ENV_BASE_URL>` placeholder, and states the clinical question.
2. **An answer template** (`payloads/answer_template.json`) — the hard output contract.
3. **The runtime access file** (`environment_access.md` at the work root) — the **only** source of truth for how to reach the network.

If any of these is missing, or if extra/unexpected files appear in the work directory, **stop** and surface it (do not invent access or fabricate values).
Back to top