Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Routes RunComfy outpainting requests across Nano Banana, GPT Image 2, Flux Kontext, and other edit models. Supports prompt-based extensions, reference-style matching, and expansion around existing images.
Routes image-to-video requests to models for general animation, audio-driven lip-sync, or multimodal references. Supplies model-specific prompts and CLI calls to turn still images into video.
Selects HappyHorse for general animation, Wan for voiceover-driven lip-sync, or Seedance for multimodal references. Supplies model-specific prompts and CLI calls to turn still images into video.
Provides CLI access to a range of AI models and applications for media generation, language model calls, and web search. Also supports 3D creation and automated Twitter activity.
Covers Kling 3.0 video generation across Standard, Pro, and 4K tiers. Supports text and image inputs, synchronized audio, and consistent character identity across multiple shots.
Covers Kling 3.0 text-to-video and image-to-video generation through RunComfy. Supports six endpoints across three rendering tiers, with synchronized audio and consistent character identity across shots.
Routes lip-sync tasks for portraits, existing video, or generated speech scenes to suitable RunComfy endpoints. Supports audio-driven avatars, mouth synchronization on footage, and script-based generation.
Routes requests across OmniHuman, Sync Labs, Kling, and Creatify. Supports portrait-plus-audio avatars, mouth synchronization in existing footage, and generated speech videos from scripts.
Provides model-specific prompting for rapid image iteration, typography, predictable framing, and optional web-grounded context. Covers resolution tiers, safety-tolerance settings, CLI invocation, and alternative model selection.
Covers rapid iteration, in-image typography, framing, and optional web-grounded context. Includes resolution-tier pricing, safety-tolerance settings, and guidance on selecting alternative image models.
Uses Nano Banana 2's RunComfy edit endpoint for background swaps, spatially localized edits, and identity preservation. Covers batch editing of up to twenty inputs, schema guidance, and alternative models.
Provides RunComfy guidance for background replacement and localized edits described with spatial language. Covers subject identity preservation, multi-image batch editing, the input schema, and alternative model selection.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name