Menu

Individual skill

clinic-protocol-cds

0upvotes

Use when a task asks you to produce a structured JSON clinical-decision-support answer for a synthetic Harborview clinic case and gives you an input/payloads/answer_template.json to conform to, backed by a read-only clinic runtime API (endpoints listed in an environment_access file). Covers all five case families — adult respiratory / CAP, pediatric head injury, potassium repletion, care-management routing, and observation-window retrieval — by pulling the case bundle, applying the matching protocol, and emitting exactly one template-conformant JSON object with no prose.

experiments/claude_code_opus_4_8_xhigh/reports/skills/task_group_016/fewshot/fewshot_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
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 CDS

Answer a single synthetic-clinic decision-support task by grounding every field
in the runtime record and the matching protocol, then returning **exactly one
JSON object** that conforms to the task's `answer_template.json`.

## What each task gives you

- `input/prompt.txt` — names a **target case id** (e.g. `CASE-RESP-102`), the case
  family in prose, and the fields to populate. It references
  `<TASK_ENV_BASE_URL>` for the runtime and says the environment access is
  "listed separately".
- `input/payloads/answer_template.json` — a **schema descriptor** (not a fill-in
  form). It defines `required_top_level_keys`, per-field `type`, `allowed_values`
Back to top