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 requests across RunComfy's video models for text-to-video, image-to-video, and video extension. Selects models based on motion, character consistency, audio, speed, and duration needs, with model-specific prompting and CLI calls.
Generates a canonical pet pose with GPT Image 2 through RunComfy, then assembles nine animation states using ImageMagick transforms. Produces a Codex-compatible spritesheet.webp and pet.json and places them in the custom pets directory.
Routes pose-conditioned generation through RunComfy models for motion transfer, character animation, and still images. Selects a route based on video versus still output and stylized versus photorealistic results.
Routes pose-conditioned requests to Kling motion control, Wan Animate, or Z-Image Turbo ControlNet LoRA. Supports transferring video motion to characters and generating still images from skeleton, depth, or edge control images.
Creates music from style descriptions and structured lyrics using the RunComfy CLI. Supports multilingual vocals, section-level control, and outputs such as backing tracks, jingles, podcast intros, and game loops.
Creates music from style descriptions and structured lyrics, with section-level control and multilingual vocals. Supports tracks from five seconds to five minutes for uses such as jingles, backing tracks, podcast intros, and game loops.
Selects models for still-image face edits, identity-preserving batch swaps, video character replacement, and motion transfer. Routes requests according to the medium, replacement scope, and presence of dialogue or motion.
Selects models for single-image face edits, batch identity swaps, video character replacement, and motion transfer. Matches the route to still versus video, full character versus face-only edits, and dialogue versus silent motion.
Searches skills.sh, clawhub.ai, and GitHub together, comparing candidates using each registry's native popularity metrics. Checks leading candidates for risky skill instructions and flags already installed skills to support capability discovery and installation.
Provides Flux 2 Klein prompting guidance for rapid image generation and multi-reference brand styling. Covers step counts, 9B versus 4B variants, CLI invocation, and when to choose an alternative image model.
Covers fast image generation, multi-reference brand styling, subject-first prompts, and step counts for drafts or polish. Explains the 9B versus 4B trade-off and when to choose another image model.
Uses a single reference image and prompt for localized image editing with Flux Kontext Pro. Includes prompting patterns, input schema guidance, CLI invocation, and alternatives for other editing needs.
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