image-compress — community image-compress, embedease-ai, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for AI Agents needing efficient image compression capabilities, particularly those utilizing README files with size constraints. 一款开箱即用的 AI 智能客服系统,人工客服,客户转化

congwa congwa
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The image-compress skill by congwa is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for AI Agents needing efficient image compression capabilities, particularly those utilizing README files with size constraints.

Core Value

Empowers agents to compress images to optimal formats like avif, webp, png, and jpg, ensuring file sizes are under 100KB for seamless integration into documentation, utilizing tools like sips for macOS and leveraging bash commands for automated scanning and compression.

Capabilities Granted for image-compress

Compressing README images for size optimization
Automating image format conversion to avif or webp for better compression ratios
Scanning documentation for oversized images to ensure compliance with size limits

! Prerequisites & Limits

  • Requires macOS for sips command functionality
  • Limited to specific image formats (avif, webp, png, jpg, gif)
  • 100KB file size limit for compressed images
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

image-compress

Install image-compress, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Image Compress

README 引用的图片不得超过 100KB

检查规则

  1. 扫描 README.md 中所有 ![](path) 引用的图片文件
  2. 检查每个文件大小,超过 100KB 的必须压缩
  3. 推荐格式优先级:avif > webp > png > jpg

检查命令

bash
1# 查找 docs/ 和 images/ 下超过 100KB 的图片 2find docs/ images/ -type f \( -name "*.png" -o -name "*.jpg" -o -name "*.jpeg" -o -name "*.webp" -o -name "*.avif" -o -name "*.gif" \) -size +100k

压缩方式

macOS 内置 sips(png/jpg)

bash
1# 缩小尺寸(保持宽度 1200px 以内) 2sips --resampleWidth 1200 image.png 3 4# 转为 jpg 并降低质量 5sips -s format jpeg -s formatOptions 80 image.png --out image.jpg

ffmpeg(推荐,支持 avif/webp)

bash
1# png → avif(推荐,体积最小) 2ffmpeg -i input.png -c:v libaom-av1 -crf 30 -still-picture 1 output.avif 3 4# png → webp 5ffmpeg -i input.png -quality 80 output.webp 6 7# 批量转换 8for f in docs/screenshots/*.png; do 9 ffmpeg -i "$f" -c:v libaom-av1 -crf 30 -still-picture 1 "${f%.png}.avif" 10done

使用 scripts/check_compress.sh

bash
1bash .windsurf/skills/image-compress/scripts/check_compress.sh

压缩后

  1. 更新 README.md 中的图片路径(扩展名可能变化)
  2. 删除旧的大图片文件
  3. 确认所有图片 < 100KB

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is image-compress?

Perfect for AI Agents needing efficient image compression capabilities, particularly those utilizing README files with size constraints. 一款开箱即用的 AI 智能客服系统,人工客服,客户转化

How do I install image-compress?

Run the command: npx killer-skills add congwa/embedease-ai/image-compress. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for image-compress?

Key use cases include: Compressing README images for size optimization, Automating image format conversion to avif or webp for better compression ratios, Scanning documentation for oversized images to ensure compliance with size limits.

Which IDEs are compatible with image-compress?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for image-compress?

Requires macOS for sips command functionality. Limited to specific image formats (avif, webp, png, jpg, gif). 100KB file size limit for compressed images.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add congwa/embedease-ai/image-compress. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use image-compress immediately in the current project.

Related Skills

Looking for an alternative to image-compress or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI