Menú
How to delegate clinical tasks to specialist agents. Always use sub-agent runtime with explicit agentId — never ACP. Never call FHIR via web_fetch.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
| name | clinical-delegation |
| description | How to delegate clinical tasks to specialist agents. Always use sub-agent runtime with explicit agentId — never ACP. Never call FHIR via web_fetch. |
| metadata | {"openclaw":{"requires":{"bins":["python3"]}}} |
When you delegate work to specialist agents, you must use the sub-agent runtime, not ACP.
Do not use web_fetch or any HTTP tool to call FHIR APIs from the coordinator. The coordinator does not have the correct FHIR base URL in context when it invents URLs. Specialist agents (patient-data, labs-vitals, medications, analyst) have the configured FHIR endpoint and write Python that runs on the server.
The only FHIR server in use is https://r4.smarthealthit.org. Never use placeholder domains like fhir.example.com.
Use sessions_spawn with:
patient-data, labs-vitals, medications, analyst, or molecularruntime: "acp". Omit runtime or use runtime: "subagent" so the request goes to the correct clinical agent.{ "agentId": "patient-data", "task": "Find the first patient and return demographics and active conditions.", "mode": "run" }
{ "agentId": "labs-vitals", "task": "Get latest HbA1c and eGFR for patient abc123", "mode": "run" }
{ "agentId": "analyst", "task": "Run care gap analysis for diabetic patients with A1c > 9%", "mode": "run" }
"runtime": "acp" without agentId — causes "ACP target agent is not configured"| agentId | Use for |
|---|---|
| patient-data | Find patients, get demographics, list conditions |
| labs-vitals | Labs, vitals, BP, observations |
| medications | Active medications, drug classes |
| analyst | Python analysis, care gaps, charts |
| molecular | Drug molecular structure, OpenFold3 NIM 3D visualization |
Configure NVIDIA MIG (Multi-Instance GPU) partitions on the DGX Station GB300, including enabling MIG mode, choosing a profile layout, creating instances, and retrieving MIG UUIDs. Use when the user asks to partition the GB300, set up MIG, run multiple models in isolation on one GPU, or reconfigure existing MIG instances.
Diagnose common DGX Station GB300 issues — CUDA crashes, wrong-GPU targeting, vLLM/SGLang container bugs, MIG state problems, NVLink/Fabric Manager errors, X/Vulkan failures, HuggingFace auth, and port conflicts. Use when the user reports a GPU error, inference server crash, MIG problem, or any unexplained DGX Station failure.
Deploy an SGLang inference server on an NVIDIA DGX Station GB300 with the cu130 container, RadixAttention prefix caching, and structured JSON output support. Use when the user asks to serve a model with SGLang, start an SGLang endpoint, or needs structured-output inference on DGX Station.
Deploy a vLLM inference server on an NVIDIA DGX Station GB300 with validated container, GPU targeting, and tuning parameters. Use when the user asks to serve a model with vLLM, start a vLLM endpoint, or set up OpenAI-compatible inference on DGX Station.
Teaches the analyst agent how to write correct, robust Python analysis code for FHIR clinical data using pandas, matplotlib, and scipy.
Prepare a complete clinical case summary for a patient from FHIR endpoints. Use when asked to summarize a patient, compile a case, or prepare for tumor board.