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.Provides prompting guidance for single-reference edits with strong prompt control and consistent outputs. Covers the image-plus-prompt schema and when to route to another image editing or generation model.
Provides prompting and invocation guidance for GPT Image 2 text-to-image and editing endpoints. Covers embedded text, logos, multilingual typography, fixed image sizes, and instructions for preserving existing content.
Covers image creation and editing with emphasis on text, logos, multilingual typography, and instruction precision. Includes fixed output sizes, preservation language for edits, and guidance on choosing alternative models.
Uses the GPT Image 2 edit endpoint through RunComfy. Covers multilingual text editing, layout and typography precision, preservation language, up to ten reference images, and selection of alternative editing models.
Provides RunComfy prompting and schema guidance for GPT Image 2 editing. Covers multilingual text changes, up to ten reference images, preservation of existing content, and precise layout and typography.
Provides text-to-video prompting and schema guidance for HappyHorse 1.0. Covers synchronized audio, character consistency across shots, language support, duration, aspect ratio, resolution, and alternative model selection.
Covers synchronized audio, 1080p output, character consistency across shots, and multilingual prompts. Provides duration, aspect ratio, and resolution guidance, plus routing advice for alternative video models.
Routes single-image and batch editing requests to models suited to identity preservation, multilingual text, reference composition, or masked region edits. Includes model-specific prompting patterns and CLI invocation.
Selects Nano Banana, GPT Image 2, Flux Kontext, or Z-Image Turbo Inpaint according to editing needs. Covers identity preservation, multilingual text changes, reference composition, masked regions, and single or batch image edits.
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 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.
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.
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