Image Processing

This handles the bread-and-butter image work you do constantly in web projects: resize hero images, convert logos to WebP, trim whitespace from client-supplied assets, generate OG cards. It ships with a CLI tool (img-process) for standard operations and falls back to generating custom Pillow scripts when you need compositing or watermarks. The OG card generator is genuinely useful, it handles the tedious font discovery and text centering across macOS, Linux, and Windows. Quality defaults are sensible (85 for WebP, 90 for JPG), and it correctly composites RGBA to RGB when saving JPGs so you don't get the pink-background surprise. Pairs well with any image generation workflow where you need to optimize the output for production.

skills.sh installs: 2.5K
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jezweb/claude-skills --skill image-processing --agent claude-code

Installs into .claude/skills of the current project.

Files

Image Processing

Use img-process (shipped in bin/) for common operations. For complex or custom workflows, generate a Pillow script adapted to the user's environment.

Quick Reference — img-process CLI

img-process resize hero.png --width 1920
img-process convert logo.png --format webp
img-process trim logo-raw.jpg -o logo-clean.png --padding 10
img-process thumbnail photo.jpg --size 200
img-process optimise hero.jpg --quality 85 --max-width 1920
img-process og-card -o og.png --title "My App" --subtitle "Built for speed"
img-process batch ./images --action convert --format webp -o ./optimised

Use img-process when: the operation is standard (resize, convert, trim, thumbnail, optimise, OG card, batch). This is faster and avoids generating a script each time.

Generate a custom script when: the operation needs logic img-process doesn't cover (compositing multiple images, watermarks, complex text layouts, conditional processing).