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.Covers YouTube thumbnail dimensions, contrast, safe zones, text placement, and mobile preview optimization. Includes facial expression psychology and A/B testing to support click-through optimization.
Supports element references, clicks, typing, forms, drag-and-drop, uploads, JavaScript execution, screenshots, and video recording. Applies to web automation, data extraction, testing, research, and agent browsing.
Provides CLI access to image, video, language, search, and 3D tools across numerous model providers. Supports generating media, calling LLMs, searching the web, and automating Twitter workflows.
Creates audio-driven and text-driven avatar videos through the inference.sh CLI. Supports speech synthesis, lip-sync, virtual presenters, explainers, marketing videos, and character dialogue.
Supports text-to-image and image-to-image workflows across GPT-Image-2, FLUX, Gemini, Grok, and other models. Creates illustrations, concept art, product mockups, and marketing graphics, with editing, inpainting, and upscaling capabilities.
Generates videos from text, images, or references using a range of AI models. Supports editing, lip-sync, avatar animation, upscaling, and foley sound for demos, explainers, and social content.
Uses GPT-Image-2.5 and GPT-Image-2 for text-to-image generation, inpainting, mask-based editing, and multi-image references. Supports batch generation and transparent backgrounds for mockups, marketing visuals, and photo manipulation.
Uses HappyHorse 1.0 through inference.sh for text-, image-, and reference-to-video generation and natural-language editing. Supports 720p or 1080p videos up to 15 seconds for realistic scenes, product demos, and social content.
Provides access to image, video, language, search, and 3D apps using a range of models and providers. Supports generating media, running language models, gathering web results, and automating social tasks.
Creates text- or audio-driven avatars with 30 voices, 10 languages, and 720p or 1080p output. Supports dynamic backgrounds and full-body control for presenters, explainers, product demos, educational content, and marketing.
Runs Python through inference.sh with libraries such as NumPy, Pandas, Matplotlib, Pillow, OpenCV, and browser automation tools. Supports data processing, web scraping, image and video work, 3D processing, PDF generation, and API calls.
Turns React/Remotion component code into videos using Remotion animation and composition APIs. Supports configurable resolution, frame rate, duration, and codec for motion graphics and data-driven video generation.
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