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 dedicated inpainting or identity-preserving editing models for object removal, region replacement, and blemish cleanup. Supports binary masks and described target regions when a mask is unavailable.
Uses Z-Image Turbo for mask-driven inpainting and other image editors when a region must be described without a mask. Supports object removal, region replacement, blemish cleanup, and controlled local edits.
Uses Z-Image Turbo Inpainting for mask-driven edits and identity-preserving models when no mask is available. Supports object removal, region replacement, blemish cleanup, and filling image gaps.
Processes images using ImageMagick for resizing, format conversion, metadata retrieval, and batch operations. Supports tasks such as creating thumbnails and resizing wallpapers.
Generate, edit, and process visual artifacts, diagrams, and multimedia assets. Use when creating UI mockups, visual explainers, image transformations, or media layouts (carousel, bento grid).
Uses RunComfy editing models to add content beyond a still image's original boundaries. Selects models based on prose instructions, reference styling, or brand constraints.
Routes image outpainting across RunComfy editing models to add content beyond existing boundaries. Supports prompt-driven expansion, reference-style matching, and changes from square or portrait images to wider compositions.
Routes RunComfy outpainting requests across Nano Banana, GPT Image 2, Flux Kontext, and other edit models. Supports prompt-based extensions, reference-style matching, and expansion around existing images.
Processes web assets by resizing, cropping, trimming whitespace, converting PNG/WebP/JPG formats, and reducing file size. Also creates thumbnails and Open Graph card images using Pillow.
Use when the user wants an image-first website workflow: generate or receive visual references, analyze them, then implement matching frontend code. Do not use for image-only requests, ordinary frontend coding without image references, mobile app screens, or non-visual backend work.
Reconstructs screenshots, scanned or image-based presentations, and PDF decks as object-level editable PPTX files. Preserves speaker notes when supplied and focuses on rebuilding existing slides rather than creating new presentations.
Guides still-to-video conversion using Wan, Seedance, Fabric, and Grok Video. Covers model selection, motion prompting, and camera movement for image animation and product videos.
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