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.Uses Veo 3.1 standard or fast extension endpoints with a source clip and a prompt describing what happens next. Supports longer clips and chained narratives while maintaining motion, lighting, and subject identity.
Routes video region edits to prompt-driven video editing, identity-stable restyling, or sequential frame editing. Supports object removal, cleanup, and region replacement with matching motion.
Uses the RunComfy CLI for region edits across video frames. Selects Wan 2.7, Lucy Edit Restyle, or Seedream 4.0 based on prompt-driven edits, identity preservation, or sequential frame inpainting.
Extends a video's spatial canvas to add surrounding environment or convert between vertical and horizontal formats. Uses RunComfy video editing and points to dedicated ComfyUI outpainting workflows when seam quality matters.
Extends a video's spatial canvas and adds surroundings beyond the original frame. Uses Wan 2.7 for prompt-driven extension and routes to dedicated ComfyUI outpainting workflows when seam quality matters.
Covers Wan 2.7 text-to-video generation, multi-reference conditioning, audio-driven lip-sync, transitions, and prompt expansion. Provides duration, resolution, aspect-ratio, CLI, and alternative model guidance.
Covers Wan 2.7 text-to-video generation, multi-reference conditioning, audio-driven lip-sync, transitions, and prompt expansion. Explains duration, resolution, and aspect-ratio settings and when to use alternative video models.
Provides AI-powered search, direct answers, and content extraction through Tavily and Exa. Supports research, fact-checking, content aggregation, RAG pipelines, and agent workflows.
Provides browser automation through inference.sh with element references, navigation, clicking, typing, drag-and-drop, file uploads, and JavaScript execution. Supports scraping, form filling, screenshots, video recording, testing, and research.
Uses the inference.sh CLI to run AI applications for image and video creation, LLM calls, search, 3D, and Twitter automation. Supports models and services including FLUX, Veo, Gemini, Claude, Tavily, Exa, and OpenRouter.
Supports text-to-avatar and audio-driven video using models such as P-Video-Avatar, OmniHuman, Fabric, and PixVerse. Includes speech tools for virtual presenters, explainers, dubbing, marketing videos, UGC ads, and game character dialogue.
Supports text-to-image, image-to-image, inpainting, LoRA, upscaling, and text rendering with models including GPT-Image-2, FLUX, and Gemini. Applies to illustrations, product mockups, concept art, social graphics, and marketing visuals.
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