Chalk Labs
Need help deploying compress-images?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/rameerez-compress-images
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: marketing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/compress-images
Tools it pre-approves 4
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(cwebp:*),Bash(ls:*),Bash(mkdir:*),Bash(mv:*)
What's inside
- Skill 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.
- License
- MIT
- Allowed tools
- Bash(cwebp:*),, Bash(ls:*),, Bash(mkdir:*),, Bash(mv:*)
- Instructions
- 82 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (1)
- SKILL.md
SKILL.md (first lines)
# 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
From rameerez/claude-code-startup-skills, MIT.
More from rameerez/claude-code-startup-skills
- 0.496score
customer-empathy
rameerez
Deep-dive into customer empathy and user journey thinking.
SkillDFreshness: D★ 31Claude Code +9 - 0.496score
download-video
rameerez
Download videos from social media URLs (X/Twitter, YouTube, Instagram, TikTok, etc.) using yt-dlp.
SkillDFreshness: D★ 31Claude Code +9 - 0.496score
transcribe-video
rameerez
Generate subtitles (SRT/VTT) and plain text transcripts from video or audio files using AWS Transcribe.
SkillDFreshness: D★ 31Claude Code +9 - 0.490score
x-post
rameerez
Post to X (Twitter) from the command line.
SkillDFreshness: D★ 31Claude Code +9
Signals
- Stars
- 31
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Feb 4, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from rameerez
- 0.496score
customer-empathy
rameerez
Deep-dive into customer empathy and user journey thinking.
SkillDFreshness: D★ 31Claude Code +9 - 0.496score
download-video
rameerez
Download videos from social media URLs (X/Twitter, YouTube, Instagram, TikTok, etc.) using yt-dlp.
SkillDFreshness: D★ 31Claude Code +9 - 0.496score
transcribe-video
rameerez
Generate subtitles (SRT/VTT) and plain text transcripts from video or audio files using AWS Transcribe.
SkillDFreshness: D★ 31Claude Code +9 - 0.490score
x-post
rameerez
Post to X (Twitter) from the command line.
SkillDFreshness: D★ 31Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get compress-images running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
compress-images skill. Agent Mart. https://agentmart.dev/skills/rameerez-compress-images (last updated 2026-10-24)