Use when working with ComfyUI workflows in Video Production Buddy, including comfyui_image/comfyui_video, custom workflow_json/workflow_path inputs, output_node selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
SkillScore92Maintained
Automatic
◆AI Engineer pack
Last verified 8/17/2026
What it changes
Passed 21 of 23 test cases with the skill, and 16 of 23 without it.
Without skill68%
With skill92%
Checks it passed that the model alone missed
The output includes workflow_model_stack in the tool payload metadata.
The response specifies placing text encoders under ComfyUI/models/text_encoders/.
The response names COMFYUI_SERVER_URL as the environment variable for overriding the server address.
and 4 more in the full report
6 fixed17 passed either way2 still failing0 broke
Pass-rate lift
+24 pp
Tokens
+4%
Agent turns
0%
Response time
-65%
Model gemini-3.6-flashMeasured 8/17/2026v123 of 25 cases passed with skill · 23 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
My local generation service host is running on a remote server at `http://192.168.1.50:8188` instead of the default local host address. Which environment variable must be configured to redirect backend communication?
What was checked, without and with the skill
Checked
Without skill
With skill
The response names COMFYUI_SERVER_URL as the environment variable for overriding the server address.
Missed
Passed
case-12 · gemini-3.6-flash · 8/17/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md50 linessingle file
ComfyUI Workflows in Video Production Buddy
Use this skill before calling comfyui_image or comfyui_video, and when converting a community ComfyUI workflow into a Video Production Buddy tool call.
Server Contract
ComfyUI must be running before the tool can generate. The default server is http://localhost:8188; override it with COMFYUI_SERVER_URL.
Health and hardware status come from GET /system_stats.
Jobs are submitted to POST /prompt, completed outputs are read from GET /history/{prompt_id}, and artifact bytes are downloaded with GET /view.
Export workflows with ComfyUI's API-format JSON, not the UI layout format. If a downloaded workflow will not submit, re-export it from ComfyUI with API format enabled.
Choosing a Workflow
Use bundled workflows when the requested operation matches and the local machine has the required models and VRAM.
Use a custom workflow_json or workflow_path when the user needs a community recipe, a lower-VRAM model, a different style family, or custom nodes.
For 8GB-12GB GPUs, prefer lower-footprint workflows such as Wan 2.1 1.3B, LTXV FP8 or quantized workflows, or Wan 2.2 GGUF/quantized community workflows. The bundled Wan 2.2 14B FP8 video workflows are a 16GB-class path, not a provider-wide floor.
Do not promise that arbitrary custom workflows will fit a machine. The workflow, quantization, resolution, frame count, and offload settings determine the real resource envelope.
Output Node Contract
Custom workflows must pass output_node.
Pick the node that writes the artifact, usually SaveImage, SaveVideo, VHS_VideoCombine, or another terminal saver node.
Pass the node ID as a string, for example "108". Do not pass the class name.
If a workflow has multiple savers, choose the final deliverable node, not previews or intermediates.
Templated vs Fixed Nodes
Identify templated nodes before execution: prompt text, seed, dimensions, frame count, source image, sampler settings, and output filename prefix.
Fixed nodes are model loaders, VAEs, text encoders, LoRA loaders, schedulers, and graph wiring. Do not mutate those unless the workflow author intended that customization.
For community workflows, inspect each loader node and note every required model or custom node before running. Missing models should be handled through the tool's structured missing_models payload when available.
Model and LoRA Setup
Use ComfyUI Manager or the workflow author's model links when available, and respect model licenses.
Place models in the folders expected by the loader nodes: diffusion models under ComfyUI/models/diffusion_models/, text encoders under ComfyUI/models/text_encoders/, VAEs under ComfyUI/models/vae/, and LoRAs under ComfyUI/models/loras/.
For LoRA stacks, use LoraLoader or LoraLoaderModelOnly chains in the workflow. Record each LoRA name plus strength_model and strength_clip when applicable.
The current ComfyUI tools do not inject LoRAs into arbitrary graphs. To use LoRAs, provide a workflow that already contains the LoRA loader chain and pass model-stack provenance.