Individual skill

synthetic-clinic-protocol-cds

Produce a single schema-conformant JSON clinical decision-support response for a synthetic clinic runtime task. Use when a task points at a target clinic case ID, supplies an answer_template.json schema, and instructs you to query a clinic runtime environment and return only JSON.

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

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 · 8,665 bytes
references/field_families.mddoc · 5,359 bytes
references/runtime_endpoints.mddoc · 2,474 bytes
references/schema_conformance_checklist.mddoc · 3,019 bytes

Read excerpt


# Synthetic Clinic Protocol Decision-Support Skill

This skill generates one structured clinical decision-support (CDS) JSON object per task for the Harborview / synthetic clinic runtime. It is task-agnostic: it reads the task's own prompt and `answer_template.json` to decide what to produce, and reads `environment_access.md` to decide how to reach the runtime. It never hard-codes a task's final values.

## Inputs each task provides

Every task is staged under `train_tasks/<task>/input/` (or an equivalent task directory) with:

1. `prompt.txt` — names the target `case_id`, states what clinical question to answer, and points to `<TASK_ENV_BASE_URL>`.
2. `payloads/answer_template.json` — the JSON schema / contract the answer must satisfy (required keys, enums, ordering rules, null rules, numeric precision, output rules).
3. `environment_access.md` (listed separately) — the runtime base URL, allowed endpoints, and any auth headers for THIS run. Endpoints and tokens can change per run, so always read it fresh; never assume.

## Operating procedure