Execute RunComfy model endpoints via CLI with JSON inputs and outputs.
npx skills add https://github.com/runcomfy-com/skills --skill runcomfy-cli
Please help me install this Agent Skill. Skill: runcomfy-cli Source: https://github.com/runcomfy-com/skills/tree/main/runcomfy-cli Command: npx skills add https://github.com/runcomfy-com/skills --skill runcomfy-cli
It removes the friction of installing, authenticating, and operating RunComfy model endpoints by giving you a single command-line workflow for submitting requests, polling status, and downloading outputs.
Run a text-to-image request by telling the agent: runcomfy run openai/gpt-image-2/text-to-image --input '{"prompt":"a small purple cat at sunset, photorealistic"}'.
High-intent search queries and answers about installing and using this skill.
Run text-to-image generation by executing a single CLI command with your input JSON, allowing you to submit model requests and download outputs directly from scripts or the terminal.
Automate job polling for media generation workflows by submitting a no-wait request and checking its status later, supporting consistent terminal-based automation for video and image edits.
Yes, you can use JSON workflows for lip-sync and face swap tasks by passing JSON bodies as input to the command-line interface, enabling scripted and automated execution.
No, you do not need to handle authentication separately for model inference; the workflow includes sign-in once and automates request submission and result download for you.
Limitations of running model inference via a CLI interface include operating within defined tool scopes and handling retryable failure exit codes, requiring inputs strictly as JSON bodies.
LamseyahEliasRun ComfyUI workflows programmatically via REST API and WebSocket.
InternScienceParse Gaussian gjf input files and convert them to XYZ format.
fal-ai-communityGenerate fal.ai workflow JSON definitions from structured node inputs.
EndUser123Bridges OpenAI SDK to Mistral's API with model selection and streaming.
