Routes pose-conditioned generation across three backends depending on what you're making. Video motion transfer (dance onto a new character, sports motion onto a cartoon) hits Kling Motion Control. Still images locked to a pose skeleton go to Z-Image ControlNet LoRA. Audio-driven character animation lands on Wan 2-2. The skill picks the route based on whether you're working with video or stills and photoreal versus stylized. Works through the runcomfy CLI, so you're feeding reference videos or OpenPose skeletons as URLs and getting output directories back. For multi-condition stacks like pose plus depth plus reference, you'll need to jump into the ComfyUI workflows directly since the CLI only handles single-condition runs.
npx skills add https://github.com/agentspace-so/runcomfy-agent-skills --skill controlnet-pose