Individual skill
clinic-protocol-cds
Solve synthetic clinic protocol decision-support tasks — retrieve a case + protocol from the clinic runtime, apply the protocol's rules to derive a single structured JSON answer that conforms to the task's answer template. Use for tasks that name a clinic case id (CASE-...) and a runtime environment, ask for a protocol-bound assessment / decision-support / routing / lab-window result, and require a JSON object matching a provided answer_template.json.
experiments/claude_code_glm_5_2_max/reports/skills/task_group_016/reflect-3/reflect-3_attempt_03/SKILL.md
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 · 9,010 bytesSKILL.mdcore · 9,010 bytesSKILL.mdcore · 9,010 bytesSKILL.mdcore · 9,010 bytesreferences/case_type_derivations.mddoc · 5,802 bytes
Read excerpt
# Clinic Protocol Decision-Support
These tasks give you a **case id** (of the form `CASE-...`), a **clinic runtime environment** (access details are provided separately for each run), and an **answer template** (`input/payloads/answer_template.json`). Your job is to return **exactly one JSON object** that conforms to the template, derived by applying the matching **protocol** to the case data.
## Core procedure
1. **Read the prompt and template first.** Identify the target `case_id`, the required top-level keys, every field's type/enum/allowed values, nullability, precision, and any ordering rules. The template is the contract — every enum value, key name, and precision note is enforced.
2. **Fetch the case record** from the runtime environment: the case detail endpoint returns the case, patient, `findings`, `observations`, `imaging`, `medications`, `allergies`, `problems`, `sdoh`, and `care_registry` together. Do not call piecemeal endpoints when the bundled case view exists.
3. **Fetch the matching protocol.** The protocols list shows protocol ids; pick the one whose scope matches the case type (respiratory/CAP, pediatric head injury, potassium repletion, care-management routing, observation-window). The protocol body holds the authoritative rules and controlled codes.
4. **Derive each field from the protocol + case data**, not from generic clinical memory. The protocol is the source of truth for thresholds, codes, dose formulas, follow-up timing, and gates.
5. **Emit exactly one JSON object** — no markdown, no comments, no extra top-level keys, no prose. Use `null` only where the template explicitly permits it.
## How to read the case record
