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.Explains how to preload critical assets that would otherwise be discovered late in the loading waterfall. Covers resources such as fonts, hero images, and key scripts.
Guides creating clients and defining actions with next-safe-action. Covers createSafeActionClient, server errors, and Standard Schema validation using tools such as Zod, Yup, and Valibot.
Uses avatar video and speech models through inference.sh to create virtual presenters and talking characters. Supports explainers, dubbing, marketing videos, UGC ads, virtual influencers, and gaming dialogue.
Supports text-to-image and image-to-image generation, editing, inpainting, upscaling, and text rendering across more than 50 models. Intended uses include illustrations, concept art, product mockups, and marketing graphics.
Supports text-, image-, and reference-to-video generation across more than 40 models. Includes video editing, avatar animation, lip synchronization, upscaling, and foley sound for social content, explainers, and product demos.
Uses inference.sh to render video from React/Remotion component code with support for Remotion APIs. Suitable for programmatic motion graphics, data-driven videos, and exporting React animations as video.
Supports text and media posts, likes, retweets, direct messages, follows, and profile retrieval. Used for content scheduling, social media engagement, audience growth, and Twitter/X integrations.
Creates avatar and talking head videos through inference.sh using models such as P-Video-Avatar, OmniHuman, Fabric, and PixVerse. Supports text-to-avatar, audio-driven animation, lip synchronization, and speech generation for explainers, marketing, dubbing, and game characters.
Generates images through inference.sh using GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve, and other models. Supports text-to-image, image-to-image, editing, inpainting, LoRA, upscaling, and text rendering for artwork, mockups, and marketing visuals.
Uses Veo, Seedance, HappyHorse, Wan, Grok, and other models through inference.sh for text-, image-, and reference-driven video generation. Supports video editing, lip synchronization, avatar animation, upscaling, and foley sound for marketing, explainers, and product demos.
Uses UIZZE's library of more than 800,000 web and iOS screens to guide product-specific interfaces. Supports design, implementation, redesign, critique, required-state coverage, and a final completion gate.
Uses inference.sh to publish tweets and media, schedule content, like and retweet posts, send direct messages, follow users, and retrieve profiles. Supports social media automation, engagement bots, and audience growth.
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