菜单
Discover and cache all installed ComfyUI models, custom nodes, and system capabilities. Works online (API queries) and offline (directory scanning). Use before generating workflows to verify available resources.
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 | comfyui-inventory |
| description | Discover and cache all installed ComfyUI models, custom nodes, and system capabilities. Works online (API queries) and offline (directory scanning). Use before generating workflows to verify available resources. |
| user-invocable | true |
| metadata | {"openclaw":{"emoji":"📦","os":["darwin","linux","win32"],"requires":{"bins":["pwsh"]},"primaryEnv":"COMFYUI_PATH"}} |
Discovers what's installed in the user's ComfyUI instance and caches results for workflow validation.
Every workflow generation MUST be preceded by an inventory check. This prevents:
Query the live server for authoritative information.
1. System info:
curl http://127.0.0.1:8188/system_stats
Extracts: GPU name, total VRAM, free VRAM, ComfyUI version.
2. Installed nodes:
curl http://127.0.0.1:8188/object_info
Returns all registered node classes with their input/output specifications.
3. Installed models (per type):
curl http://127.0.0.1:8188/models/checkpoints
curl http://127.0.0.1:8188/models/loras
curl http://127.0.0.1:8188/models/vae
curl http://127.0.0.1:8188/models/controlnet
curl http://127.0.0.1:8188/models/clip
curl http://127.0.0.1:8188/models/clip_vision
curl http://127.0.0.1:8188/models/upscale_models
curl http://127.0.0.1:8188/models/diffusion_models
When ComfyUI isn't running, scan the filesystem directly.
Requires: ComfyUI installation path (e.g., C:\ComfyUI)
Scan directories:
{ComfyUI}/models/checkpoints/ → .safetensors, .ckpt
{ComfyUI}/models/loras/ → .safetensors
{ComfyUI}/models/vae/ → .safetensors, .pt
{ComfyUI}/models/controlnet/ → .safetensors, .pth
{ComfyUI}/models/clip/ → .safetensors
{ComfyUI}/models/clip_vision/ → .safetensors
{ComfyUI}/models/upscale_models/ → .pth, .safetensors
{ComfyUI}/models/diffusion_models/ → .safetensors
{ComfyUI}/models/ipadapter/ → .safetensors, .bin
{ComfyUI}/models/instantid/ → .bin
{ComfyUI}/models/insightface/ → .onnx + folders
{ComfyUI}/models/facerestore_models/ → .pth
{ComfyUI}/models/ultralytics/bbox/ → .pt
{ComfyUI}/custom_nodes/ → folder names = node packages
Custom node detection: List directories under custom_nodes/. Each directory name corresponds to a node package (e.g., ComfyUI_IPAdapter_plus, ComfyUI-Impact-Pack).
Save results to state/inventory.json:
{
"last_updated": "2026-02-06T12:00:00Z",
"mode": "online",
"comfyui_version": "0.3.10",
"system": {
"gpu": "NVIDIA RTX 5090",
"vram_total_gb": 32,
"vram_free_gb": 28
},
"models": {
"checkpoints": ["flux1-dev.safetensors", "RealVisXL_V5.0.safetensors"],
"loras": ["sage_character.safetensors"],
"vae": ["ae.safetensors", "wan_2.1_vae.safetensors"],
"controlnet": ["instantid_controlnet.safetensors"],
"clip": ["t5xxl_fp16.safetensors", "clip_l.safetensors"],
"clip_vision": ["CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors"],
"upscale_models": ["4x-UltraSharp.pth"],
"diffusion_models": ["wan2.1_i2v_720p_14b_bf16.safetensors"],
"ipadapter": ["ip-adapter-faceid-plusv2_sd15.bin"],
"instantid": ["ip-adapter.bin"],
"insightface": ["inswapper_128.onnx"],
"facerestore": ["codeformer.pth"],
"detection": ["face_yolov8m.pt"]
},
"custom_nodes": [
"ComfyUI-Manager",
"ComfyUI_IPAdapter_plus",
"ComfyUI_InstantID",
"ComfyUI-Impact-Pack",
"ComfyUI-AnimateDiff-Evolved",
"ComfyUI-VideoHelperSuite"
]
}
Given a workflow JSON, validate against inventory:
For each node:
1. Check class_type against known node classes
2. If missing: identify which custom_node package provides it
3. Suggest install: "Install via ComfyUI-Manager: {package_name}"
For each model reference:
1. Check filename against inventory models of that type
2. If missing: look up in references/models.md for download link
3. Report: "Missing: {filename} - Download from {url} -> {path}"
| Node Class | Package |
|---|---|
| ApplyInstantID | ComfyUI_InstantID |
| IPAdapterUnifiedLoader | ComfyUI_IPAdapter_plus |
| FaceDetailer | ComfyUI-Impact-Pack |
| ReactorFaceSwap | ComfyUI-ReActor |
| AnimateDiffLoaderWithContext | ComfyUI-AnimateDiff-Evolved |
| VideoHelper* | ComfyUI-VideoHelperSuite |
| ControlNetApply* | comfyui_controlnet_aux |
| UltimateSDUpscale | ComfyUI_UltimateSDUpscale |
| VHS_* | ComfyUI-VideoHelperSuite |
| RIFE* | ComfyUI-Frame-Interpolation |
scan-inventory.ps1 or API re-querycomfyui-workflow-builder before generating workflowscomfyui-character-gen (via agent wrapper) for model selectioncomfyui-troubleshooter when diagnosing missing model errorsstate/inventory.json for all skills to referenceBuild identity-preserving character generation workflows and pipelines in ComfyUI. Selects the optimal identity method (InfiniteYou, FLUX Kontext, PuLID, InstantID, IP-Adapter) based on use case requirements. Handles face preservation, likeness transfer, cross-domain conversion (3D to photo), multi-reference consistency, iterative character editing, and character variation generation. Triggers on requests to generate consistent characters, preserve identity across images, create face-swapping workflows, or convert 3D renders to photorealistic portraits. Does NOT cover general image generation without identity preservation, model training/LoRA fine-tuning, animation, technical explanations, or workflow debugging.
Guided conversational interview to understand a user's creative vision before generating model-appropriate image prompts. Asks clarifying questions about subject, mood, style, and technical preferences (4-7 exchanges), then synthesizes positive prompt, negative prompt, recommended settings table, and pipeline recommendation. Formats prompts for the target model (SDXL tag-style, FLUX natural language, SD1.5 weighted tokens). Triggers on "I want to create...", "help me make an image of...", "I have an idea for...", "help me craft a prompt", "write me a prompt for...", or any request for help describing a creative vision. Does NOT cover workflow building, prompt debugging/fixing, technical explanations, model training, code generation, or identity-preserving character generation.
Generate videos using ComfyUI with Wan 2.2, FramePack, or AnimateDiff. Handles image-to-video, text-to-video, talking heads, and motion-controlled animation. Use when creating any video content from character images or text descriptions.
Plan and orchestrate end-to-end video production pipelines in ComfyUI with validation gates and error recovery. Handles img2vid, txt2vid, vid2vid, and multi-shot video production. Produces pipeline plans with correct step ordering (generate, validate, animate, validate, concat), model selection, retry strategies (seed randomization, parameter adjustment, model fallback), and VRAM-aware resource management. Use when asked to make a video, animate images, create a multi-shot video, set up a video pipeline, or orchestrate video production in ComfyUI. Does NOT cover still image generation, prompt writing, workflow building for non-video tasks, video editing in external tools, model training, installation, or hardware recommendations.
Generate, build, create, or design ComfyUI workflow JSON from natural language descriptions. Produces valid node graphs with correct class_types, connections, output indices, and model-appropriate settings. Handles txt2img, img2img, inpainting, ControlNet, LoRA stacking, upscaling, and face detailing pipelines. Does NOT cover ComfyUI installation, custom node development, Python scripting, model training, hardware advice, or architectural explanations.
Connect to a running ComfyUI instance, queue workflows, monitor execution, and retrieve results. Supports both online (REST API) and offline (JSON export) modes. Use when executing ComfyUI workflows or checking server status.