菜单
Validate the GenAI stack (services, authentication, models, notebooks, GPU). Arguments: [all|services|auth|models|notebooks|vram] [--local] [--remote] [--quick]
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | validate-genai |
| description | Validate the GenAI stack (services, authentication, models, notebooks, GPU). Arguments: [all|services|auth|models|notebooks|vram] [--local] [--remote] [--quick] |
Validate the complete GenAI infrastructure.
Target: $ARGUMENTS
all: Complete validation (default)services: Docker services connectivityauth: ComfyUI authentication tokensmodels: Available models inventorynotebooks: GenAI notebook executionvram: GPU/VRAM availabilitypython scripts/genai-stack/validate_stack.py # Full validation
python scripts/genai-stack/validate_notebooks.py # Notebook execution
python scripts/genai-stack/check_vram.py # GPU check
python scripts/genai-stack/list_models.py # Model inventory
python scripts/genai-stack/list_nodes.py # ComfyUI nodes
python scripts/genai-stack/docker_manager.py # Docker management
| Notebooks | Service | Requirement |
|---|---|---|
| 01-1, 01-3 | OpenAI API | OPENAI_API_KEY |
| 01-4, 02-3 | SD Forge | Local or myia.io |
| 01-5, 02-1 | ComfyUI Qwen | COMFYUI_AUTH_TOKEN, ~29GB VRAM |
| 02-4 | Z-Image/vLLM | ~10GB VRAM |
# MyIA.AI.Notebooks/GenAI/.env
LOCAL_MODE=false
COMFYUI_API_URL=https://qwen-image-edit.myia.io
COMFYUI_AUTH_TOKEN=your_token
OPENAI_API_KEY=sk-...
ZIMAGE_API_URL=https://z-image.myia.io
Detect cell-ordering / enchainement problems in Jupyter notebooks (canonical-order slippage, misplaced or forgotten cells). Arguments: [target] [--severity HIGH|MED|LOW] [--json]
Resume multi-agent coordination session. Reads memory, RooSync inbox, GitHub issues, and produces a situational briefing with recommended actions. Arguments: [--dispatch] [--focus <topic>] [--reply-all]
Iterate on a GenAI notebook against the self-hosted stack via the genai-stack CLI (config dirs, auth, subdomains, quantization, GPU/VRAM). Arguments: <notebook|service> [--service comfyui|forge|vllm] [--quant int4|fp8] [--validate] [--bg]
Train an ML model in the QuantConnect ML-Training-Pipeline with thermal-safe GPU usage and rigorous validation. Arguments: <architecture|script> [--dry-run] [--seeds 0,1,7,42,99] [--folds 5] [--bg]
Execute iterative improvement workflow for QuantConnect strategies. Arguments: [strategy|issue#] [--iterations=N] [--no-backtest] [--commit]
Review and merge student exercise PRs during TP sessions. Arguments: <repo-url> [--class <class-id>] [--timeslot <HH:MM-HH:MM>] [--dry-run]