Individual skill
clinic-runtime-cds
Solve synthetic clinic decision-support tasks that run against a read-only clinic runtime API and require a single JSON object conforming to a per-task answer template. Use for any task whose prompt names a CASE-* id, references a clinic runtime environment / <TASK_ENV_BASE_URL>, and asks to return a JSON object matching input/payloads/answer_template.json.
experiments/claude_code_glm_5_2_max/reports/skills/task_group_016/self/self_attempt_02/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 · 9,261 bytesSKILL.mdcore · 9,261 bytesreferences/case_playbook.mddoc · 8,097 bytesreferences/output_contract.mddoc · 5,167 bytesreferences/runtime_endpoints.mddoc · 4,310 bytes
Read excerpt
# Clinic Runtime Decision-Support Skill
This skill solves a family of structured clinical decision-support (CDS) tasks. Each task points at a target clinic case in a read-only synthetic clinic runtime and demands **exactly one JSON object** that conforms to a per-task `answer_template.json`. The work is: locate the target case in the runtime, gather the relevant chart facts and protocol material, map them onto the template's controlled vocabulary, and emit a schema-valid object.
## When to use
Use this skill when a task has all of:
- A target case identifier (e.g. `CASE-RESP-102`, `CASE-CM-411`) stated in the prompt.
- A reference to a clinic runtime environment / `<TASK_ENV_BASE_URL>`.
- An instruction to return a single JSON object conforming to `input/payloads/answer_template.json`.
Do **not** use this skill for tasks that ask for narrative, free-text, or non-JSON output, or that operate on a different runtime.
## Operating rules (distilled from the training tasks)