Image Editing

slack-gif-creator is a code-first skill for creating Slack-friendly animated GIFs with Python helpers for frame building, optimization, and validation. Use it to install dependencies, build loops with GIFBuilder, and export emoji or message GIFs that fit Slack size, timing, and color constraints.

baoyu-compress-image is an Image Editing skill that compresses images to WebP by default, with PNG or JPEG support and automatic tool selection across sips, cwebp, ImageMagick, and sharp. It fits file-size reduction, format conversion, and batch image optimization workflows.

Use the remotion skill to turn Stitch project screens into polished walkthrough videos with transitions, zooms, and text overlays. It includes install steps, example files, and a repeatable remotion guide for video editing and render-ready compositions.

snipgrapher turns source code into polished, syntax-highlighted PNG, SVG, and WebP snippet images with reusable themes, profiles, and CLI-driven renders. Use the snipgrapher skill when you need consistent assets for docs, changelogs, social posts, or snipgrapher for UI Design. It supports install, config, batch, and watch workflows for repeatable output.

screenshot-optimization is a conversion-focused skill for planning and improving App Store screenshots and preview videos. Use it to shape the hook, sequence, and messaging of each slot for UI Design and store listing work. It helps founders, marketers, and designers turn rough ideas into a clear screenshot strategy.

nanobanana is a Python CLI skill for Google Gemini 3 Pro Image that supports text-to-image, image editing, aspect ratios, 2K/4K output, and batch generation with simple local scripts.

videoagent-image-studio is a unified image generation skill for Node-based agents. It offers one CLI flow for Midjourney, Flux, Ideogram, Recraft, SDXL, and more, with proxy-backed setup, model selection guidance, and normalized outputs for automation.

compress-images automates image optimization for web and SEO performance. It moves source JPG, PNG, or GIF files into an originals/ folder, converts them to WebP, iterates until files are under 100KB, and updates content references for a safer batch workflow.

generate-image is a skill for generating or editing images with AI models like FLUX.2 Pro and Gemini 3.1 Flash Image Preview through OpenRouter. Use it for photos, illustrations, concept art, visual assets, and image edits when you want a repeatable workflow instead of a one-off prompt. For diagrams, flowcharts, and schematics, use scientific-schematics instead.

transform-upscale-image-with-transloadit is an AI image editing skill for enlarging existing images with Transloadit. It uses a deterministic CLI workflow for local files, supports 2x or 4x upscaling, and can apply face enhancement when portraits need cleaner detail.

transform-remove-background-with-transloadit is a focused Image Editing skill for removing a local image background and saving a transparent PNG with the official `@transloadit/node` CLI. It uses a minimal `/image/bgremove` steps file, explicit input and output paths, and clear credential lookup so you can run the workflow with less guesswork.

transform-generate-image-with-transloadit is a one-off image generation skill for creating a local image file from a text prompt or prompt plus reference images using Transloadit via the transloadit CLI. Use it for fast, prompt-driven image generation with clear output-path control and optional model selection.

The seo-images skill analyzes image SEO and performance for SEO Content, product pages, editorial posts, and other image-heavy pages. It checks alt text, file size, formats, responsive delivery, lazy loading, CLS risk, image SERP visibility, and optimization options like WebP/AVIF and IPTC/XMP metadata. Use it when you need a practical, prioritized image audit.