compress-images — Claude Code skill for WebP image compression
Compresses images into WebP with cwebp and updates content references. Use it when preparing smaller image files for a website.
npx skills add rameerez/claude-code-startup-skills --skill compress-images -a claude-codeWhat compress-images does
The skill processes images in a supplied directory, or uses app/assets/images/content/ when you don’t pass a path. It moves source files into an originals/ subfolder and writes WebP versions beside it. The originals stay available for another compression pass.
It starts cwebp at quality 70 and a width of 1200 pixels. If a result exceeds the 100KB target, the skill lowers quality and can then reduce the width to 1000 pixels. It checks the resulting file sizes, changes content references to .webp, and reports before-and-after sizes. cwebp must be available in the environment; otherwise the compression commands cannot run.
What it helps with
- convert JPG and PNG files to WebP
- reduce image file sizes for a website
- keep source images before compression
- change content references to WebP files
Example prompts for the agent
- Compress the images in
app/assets/images/content/, keep the originals, and update the content references. - Convert the images in
public/imagesto WebP and report their sizes before and after. - Compress the images in this folder for the website.
How to install compress-images
1Skills CLI (Vercel)
npx skills add rameerez/claude-code-startup-skills --skill compress-images -a claude-code2Manually: put the files in place
~/.claude/skills/compress-images/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/compress-images/
1Skills CLI (Vercel)
npx skills add rameerez/claude-code-startup-skills --skill compress-images -a codex2Manually: put the files in place
.agents/skills/compress-images/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rameerez/claude-code-startup-skills --skill compress-images -a cursor2Manually: put the files in place
.cursor/skills/compress-images/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rameerez/claude-code-startup-skills compress-images2Manually: put the files in place
.github/skills/compress-images/SKILL.md1Skills CLI (Vercel)
npx skills add rameerez/claude-code-startup-skills --skill compress-images -a gemini-cli2Platform CLI
gemini skills install https://github.com/rameerez/claude-code-startup-skills --path skills/compress-imagesManually: put the files in place
.devin/skills/compress-images/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add rameerez/claude-code-startup-skills --skill compress-images -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about compress-images
How do I install compress-images in Claude Code?
Run npx skills add rameerez/claude-code-startup-skills --skill compress-images -a claude-code. The skill file is at ~/.claude/skills/compress-images/SKILL.md.
What does compress-images do?
It uses cwebp to create WebP files, keeps source images in originals/, and updates references in content files.
What does compress-images need to run?
The compression commands use cwebp, so it must be available in the environment. Without it, the skill cannot convert the images.
Source text
SKILL.md · MIT
--- name: compress-images description: Compress images for web/SEO performance using cwebp. Use when optimizing images for faster page loads, reducing file sizes, or converting JPG/PNG to WebP format. argument-hint: "[directory]" allowed-tools: Bash(cwebp:*), Bash(ls:*), Bash(mkdir:*), Bash(mv:*) --- # Image Compression Skill Compress all images in `$ARGUMENTS` (or `app/assets/images/content/` if no path provided) to WebP format, optimized for SEO performance (target: under 100KB per image). ## Process 1. **Create originals folder** - Create `originals/` subfolder inside the target directory and move source files there. Never destroy source files. 2. **Compress each image** (JPG, PNG, GIF) from `originals/` to the parent directory as `.webp` 3. **Iterate until all images are under 100KB** - check sizes after each pass, re-compress any that exceed the target 4. **Report results** with before/after sizes 5. **Update references** in content files from old extensions to `.webp` ## File Structure ``` target-directory/ ├── originals/ # High-quality source files preserved here │ ├── hero.jpg │ └── feature.png ├── hero.webp # Compressed, web-optimized └── feature.webp ``` ## Iterative Compression Algorithm **IMPORTANT:** Keep compressing until ALL images are under 100KB. Check sizes after each pass and re-compress any that exceed the target. ### Step 1: Initial pass (q 70) ```bash cwebp -q 70 -resize 1200 0 originals/image.jpg -o image.webp ls -lh image.webp # Check size ``` ### Step 2: If still over 100KB, reduce quality progressively ```bash # Try these in order until under 100KB: cwebp -q 60 -resize 1200 0 originals/image.jpg -o image.webp cwebp -q 50 -resize 1200 0 originals/image.jpg -o image.webp cwebp -q 45 -resize 1200 0 originals/image.jpg -o image.webp cwebp -q 40 -resize 1200 0 originals/image.jpg -o image.webp cwebp -q 35 -resize 1200 0 originals/image.jpg -o image.webp ``` ### Step 3: For stubborn images, also reduce dimensions ```bash # If q 35 at 1200px is still over 100KB, reduce to 1000px: cwebp -q 30 -resize 1000 0 originals/image.jpg -o image.webp cwebp -q 25 -resize 1000 0 originals/image.jpg -o image.webp ``` ## Real-World Results (Reference) From actual compression run on content images: | Image | Original | First Try | Final | Settings Used | |-------|----------|-----------|-------|---------------| | waves.jpg | 198KB | 33KB | 33KB | q 70, 1200px (1 pass) | | calendar.jpg | 246KB | 42KB | 42KB | q 70, 1200px (1 pass) | | floating.jpg | 230KB | 43KB | 43KB | q 70, 1200px (1 pass) | | cash.jpg | 409KB | 88KB | 88KB | q 70, 1200px (1 pass) | | knot.jpg | 395KB | 96KB | 96KB | q 70, 1200px (1 pass) | | floating-dark.jpg | 414KB | 94KB | 94KB | q 70, 1200px (1 pass) | | keyboard2.jpg | 459KB | 102KB | 102KB | q 70, 1200px (1 pass, acceptable) | | **perpetual.jpg** | 565KB | 130KB | **96KB** | q 40, 1200px (3 passes) | | **keyboard.jpg** | 718KB | 196KB | **98KB** | q 25, 1000px (5 passes) | ### Key Insights 1. **Most images** (under 500KB source) compress fine with default settings (q 70, 1200px) 2. **Large detailed images** (500KB+) often need multiple passes 3. **Very large images** (700KB+) may need both lower quality AND smaller dimensions 4. **Keyboard/tech photos** with fine detail are hardest to compress - expect 4-5 passes 5. **Soft/blurry images** compress much better than sharp detailed ones ## After Compression 1. **Verify ALL files under 100KB**: `ls -lh *.webp` - re-run compression on any exceeding target 2. Update content files referencing old extensions (.jpg, .png) to use .webp 3. Test that images render correctly in the application 4. Original files remain in `originals/` folder for future reference or re-compression
© rameerez · MIT · rameerez/claude-code-startup-skills