Skip to main content
skill CX Codex

image-edit · makushingu — Claude Code skill for image editing

image-edit is a Claude Code skill that resizes, crops, converts and compresses images. It activates for requests to edit a single image or process a folder in bulk.

no license ★ 285 updated 2026-11-17

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add makushingu/harness-maxxing --skill image-edit -a claude-code
Open on GitHub

What image-edit does

image-edit runs ImageMagick and ffmpeg commands to modify images. It can change dimensions or formats, crop and compress files, add borders or text, and create thumbnails or contact sheets. It can also remove metadata and extract a frame from a video.

By default, output goes to a new file or an out/ folder, leaving the source untouched. ImageMagick and ffmpeg are required. Ubuntu and Debian systems with ImageMagick 6 use convert, montage and identify; version 7 uses magick, magick montage and magick identify.

What it helps with

  • resize an image while keeping its proportions
  • convert and compress images for the web
  • make thumbnails or a contact sheet from a folder
  • remove image metadata
  • extract a frame from a video

Example prompts for the agent

  • Convert banner.png to a compressed banner.webp.
  • Create a square thumbnail from photo.jpg.
  • Make a contact sheet from the JPG files in this folder.

How to install image-edit

1Skills CLI (Vercel)

npx skills add makushingu/harness-maxxing --skill image-edit -a claude-code

2Manually: put the files in place

~/.claude/skills/image-edit/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/image-edit/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about image-edit

How do I install image-edit in Claude Code?

Run npx skills add makushingu/harness-maxxing --skill image-edit -a claude-code. The skill file is at ~/.claude/skills/image-edit/SKILL.md.

What does image-edit do?

It edits individual images or folders: resizing, cropping, converting and compressing files, adding text, and making thumbnails or contact sheets. It can also strip metadata and extract a video frame.

What does image-edit need to run?

It requires ImageMagick and ffmpeg. Ubuntu and Debian with ImageMagick 6 use convert, montage and identify; version 7 uses magick, magick montage and magick identify.

Similar skills

SKILL.md skills catalog →

image-edit by other authors comes first.

image-edit prime-skills This skill routes image edits to a suitable RunComfy model. Use it for background swaps, text changes, masks, or batch work. CX Codex +1 448,100installs gpt-image-edit prime-skills gpt-image-edit edits images through GPT Image 2 (/edit endpoint of ChatGPT Images 2.0) on RunComfy. Preserves faces and objects, rewrites text in any script (Cyrillic, CJK, Arabic), accepts up to 10 reference images. CX Codex +1 447,000installs fal-image-edit nexu-io fal-image-edit connects image editing workflows via hosted fal.ai models. Useful for background removal, erasing objects, style transfer, and inpainting. CX Codex +1 2,900installs eachlabs-image-edit eachlabs The eachlabs-image-edit skill wires 130+ EachLabs models into your agent for retouching, upscaling, background removal, inpainting, face swap and image analysis. CX Codex +1 807installs venice-image-edit veniceai The venice-image-edit skill guides an agent through editing images with Venice, combining inputs, upscaling, and removing backgrounds. Use it when a task starts with an existing image. CX Codex +1 ★ 176repo stars edit-image Sateezg edit-image modifies existing picture files with OpenAI gpt-image-2 via Codex CLI, altering isolated details, applying brand colors, or generating matching variants. CX Codex +1 ★ 195repo stars video-edit prime-skills This skill routes video edits to the right RunComfy model for restyling, background or packaging swaps, and motion transfer. Use it when edit intent matters. CX Codex +1 450,700installs

From the same set21

The whole set →
pdf-document The pdf-document skill for Claude Code builds formatted PDF documents by writing HTML and CSS and printing them via a headless browser. The agent runs it when requested to generate invoices, quotes, reports, or CVs. CX Codex +1 ★ 285repo stars seo-audit The seo-audit skill for Claude Code conducts a technical SEO audit of your website and generates a prioritized report. The agent checks indexing, meta tags, site speed, and internal links. CX Codex +1 ★ 285repo stars maxxing-mcp maxxing-mcp is a Claude Code skill that manages MCP servers in Harness Maxxing. It activates for server setup, connection checks, OAuth sign-in, and troubleshooting. CX Codex +1 ★ 285repo stars web-scraping The web-scraping skill for Claude Code extracts data from websites into Markdown, CSV, or JSON. It triggers when asked to collect or monitor web content. CX Codex +1 ★ 285repo stars memory memory is a Claude Code skill that saves lasting facts to the appropriate memory file after a substantial exchange. It handles decisions, preferences, and project changes, while skipping one-off questions. CX Codex +1 ★ 285repo stars memory-compaction memory-compaction is a Claude Code skill that shortens and cleans up bloated memory.md files. It triggers automatically when limits are exceeded or upon user request. CX Codex +1 ★ 285repo stars maxxing-tasks maxxing-tasks is a Claude Code skill that reads and edits the Harness Maxxing task board. It activates for requests to add or close a task, or check what is due today. CX Codex +1 ★ 285repo stars maxxing-backup The maxxing-backup skill for Claude Code saves the agent's memory workspace to a private GitHub repository. It runs on a daily schedule or upon specific user commands. CX Codex +1 ★ 285repo stars

Project sponsors

Companies that keep this analytics open