Individual skill

clinic-protocol-json-assessment

Use when a task asks for a protocol-bound clinical decision-support result over a synthetic FHIR-like clinic runtime and requires returning a single strict-schema JSON object that conforms to a provided answer_template.json (e.g. respiratory/CAP triage, pediatric head-injury triage, potassium repletion, care-management routing, or observation-window retrieval). Covers how to read the record, apply the matching protocol, filter distractors, and emit exactly the required JSON. Not for free-text clinical advice or tasks without a fixed answer template.

experiments/claude_code_opus_4_8_xhigh/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
No
Repository scan complete
No
Skill scan complete
Yes
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

# Clinic protocol → strict-JSON assessment

These tasks give you (1) a prompt naming one target **case id** and pointing at
an `answer_template.json`, and (2) access to a synthetic clinic runtime plus a
matching clinical **protocol**. Your job is to read the record, apply the
protocol's rules, and return **one JSON object** that satisfies the template
exactly — no prose. The runtime is seeded with deliberate distractors; most of
the difficulty is filtering them out correctly.

The runtime access details (base location, any credentials, and the exact set
of available read resources) are supplied **separately for each run** — read
that access list first and use only what it grants. Do not assume or hardcode
locations; treat the runtime as read-only and never mutate it or place orders.
Back to top