Routes your face swap request to one of five RunComfy models based on what you're actually trying to do. Single still with precise composition control goes to GPT Image 2 Edit, batch identity preservation to Nano Banana 2, audio-driven character animation to Wan 2-2 Animate, motion transfer to Kling Motion Control Pro. The skill itself is thin wrapper around runcomfy CLI invocations, but the routing logic saves you from reading five model cards. The consent section is blunt and necessary: you're responsible for rights and disclosure, the API will run whatever you feed it. Useful if you work with synthetic media regularly and want Claude to pick the right endpoint instead of always defaulting to the first thing that says "face swap."
npx skills add https://github.com/agentspace-so/runcomfy-agent-skills --skill face-swap