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 ACE Step and ACE Step 1.5 for tag-driven music generation with multilingual lyrics. Supports text-to-audio generation, regeneration of a selected time range, and extending tracks before or after existing audio.
Uses the RunComfy CLI for tag-driven music composition and multilingual lyrics with ACE Step and ACE Step 1.5. Supports text-to-audio generation, regeneration of selected time ranges, and extension before or after an existing track.
Enables agents to navigate pages and interact with elements through inference.sh. Supports form filling, clicking, typing, drag-and-drop, uploads, JavaScript execution, data extraction, and browser testing.
Uses the inference.sh CLI to run image, video, 3D, language model, and search applications. Also supports Twitter automation through a range of AI models and services.
Turns a folder of agent logs, code, screenshots, and artifacts into a live workspace accessible from other devices or by teammates. Supports browser viewing, editing, and comments. Anonymous workspaces last 24 hours; an email claim makes them permanent.
Selects among RunComfy models for audio-driven avatars, virtual presenters, dubbed demos, and dialogue scenes. Provides model-specific prompting patterns and CLI calls based on the intended video.
Selects among OmniHuman, Wan, HappyHorse, and Seedance for audio-driven avatars and cinematic video. Provides model-specific prompting and CLI calls for virtual presenters, dubbed demos, character dialogue, and voiceover-driven videos.
Routes text-to-image and image-editing requests across RunComfy's image model catalog. Selects models based on needs such as typography, portraits, rapid iteration, and reference-based brand styling.
Routes text-to-image and image editing requests across FLUX, Nano Banana, GPT Image, Seedream, Qwen, and other models. Matches models to needs such as typography, portraits, iteration speed, and reference-based styling, with prompting guidance and CLI calls.
Routes music tasks to ElevenLabs Music or ACE Step models based on the desired output. Covers vocal and instrumental generation, multilingual lyrics, audio inpainting, and track extension with model-specific prompts and CLI calls.
Selects music models for vocal songs, background tracks, multilingual lyrics, and budget-sensitive generation. Supports regenerating track sections and extending music, with model-specific prompts and RunComfy CLI commands.
Selects RunComfy video models based on requirements such as character consistency, audio, cinematic motion, speed, and duration. Provides model-specific prompting patterns and CLI calls for text-to-video, image-to-video, and video extension.
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