Imagemagick Cli logo

Imagemagick Cli

Community
Yuki001
imagemagick-cli

Comprehensive ImageMagick 7 command-line image processing for inspecting, converting, resizing, cropping, compositing, masking, drawing, annotating, color correction, quantization, filtering, morphology, distortion, animation, montage, comparison, metadata, batch automation, and advanced pixel analysis. Use whenever a task mentions ImageMagick, `magick`, `identify`, `mogrify`, raster image conversion or batch image manipulation, or when a reproducible CLI pipeline is preferable to a GUI or language binding. Also use for debugging ImageMagick commands, porting ImageMagick 6 `convert` syntax to version 7, choosing coder/delegate options, and safely processing untrusted or large images. Do not use merely to edit an existing SVG as vector source or when the user explicitly requests a different image tool.

Overview

PublisherYuki001
Repositorygame-dev-skills
Skill nameimagemagick-cli
Stars
104
Forks
13
Bundled files
17
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 17 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Yuki001 on GitHub. Read the source before you install it.

Installation

Install the Imagemagick Cli AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Yuki001/game-dev-skills/tree/main/skills/imagemagick-cli
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Yuki001/game-dev-skills.git /tmp/game-dev-skills
mkdir -p .claude/skills
cp -r /tmp/game-dev-skills/skills/imagemagick-cli .claude/skills/imagemagick-cli
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Imagemagick Cli in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Imagemagick Cli on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Imagemagick Cli is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ImageMagick CLI

Use ImageMagick 7 to build, run, and verify reproducible image-processing commands. Keep the main workflow short; load the bundled reference that matches the requested operation.

Workflow

  1. Resolve magick and run magick -version. Use scripts/resolve-imagemagick.ps1 on Windows or scripts/resolve-imagemagick.sh on Linux/macOS when discovery is uncertain. If ImageMagick cannot be found, tell the user to download and install it from https://imagemagick.org/download.
  2. Inspect the input with magick identify -ping or magick identify -verbose when metadata, alpha, profiles, pages, or frames matter.
  3. Read the relevant reference below, construct an ImageMagick 7 command for the user’s shell, and preserve originals unless in-place editing is explicit.
  4. Run the command when requested, check the exit code, then verify the output with identify, compare, and visual inspection as appropriate.

Core rules

  • Use ImageMagick 7 syntax: magick input [operators] output and subcommands such as magick identify, magick mogrify, magick montage, magick compare, and magick stream.
  • Respect sequential evaluation. Put read settings such as -density, raw -size, and decoder -define values before the input they affect.
  • Quote all paths and shell-sensitive geometry. Use parentheses to isolate operations on overlays, masks, clones, or other nested image lists.
  • Treat magick mogrify as destructive unless -path writes to a separate directory.
  • Run -auto-orient before geometry-sensitive work on camera images.
  • Use +repage after crop or trim when later operations should ignore the old virtual canvas.
  • Manage alpha, colorspace, profiles, animation timing, and multi-page scenes deliberately; do not silently discard them.
  • Confirm optional formats, fonts, delegates, policies, compose methods, and kernels with the installed magick -list ... commands.
  • For untrusted or very large inputs, use format allowlists and limits for area, memory, map, disk, time, and threads.
  • Verify outputs instead of relying on file existence alone.

Shell forms

PowerShell:

powershell
$magick = (Get-Command magick -ErrorAction Stop).Source
& $magick "input image.png" -auto-orient -resize "1600x1600>" "output image.jpg"

Pass parentheses as literal arguments:

powershell
& $magick "background.png" "(" "overlay.png" -resize "25%" ")" `
  -gravity southeast -geometry "+24+24" -compose over -composite "result.png"

Bash/zsh:

bash
magick "input image.png" -auto-orient -resize '1600x1600>' "output image.jpg"
magick background.png \( overlay.png -resize 25% \) \
  -gravity southeast -geometry +24+24 -compose over -composite result.png

Prefer PowerShell over cmd.exe for complex Windows commands. In cmd batch files, use ^ for continuation and double % characters.

Command references

  • references/cli-foundations.md — evaluation order, settings and operators, stacks, geometry grammar, pseudo-images, streams, shell quoting, and IM6-to-IM7 conversion.
  • references/inspect-formats-metadata.md — identify, percent escapes, EXIF/profiles, format prefixes, multi-image I/O, common and specialist coders, delegates, encrypted images, raw data, and large streams.
  • references/geometry-resize-crop.md — fit/fill/exact resize, thumbnails, resampling filters, density, orientation, crop/page/extent, advanced trim, borders, tiling, and framing.
  • references/color-tone-quantize.md — colorspaces, ICC, channels, alpha, grayscale, levels, histogram operations, thresholds, palettes, and dithering.
  • references/compose-mask-layers.md — compose operators, placement, opacity, alpha/read/write masks, background removal, chroma key, hole filling, regions, clones, layers, watermarks, and shadows.
  • references/draw-text-canvas.md — canvases, gradients, patterns, fonts, label/caption/annotate, Pango, form filling, gravity, symbols, MVG, paths, and text effects.
  • references/filters-effects-morphology.md — blur, sharpen, denoise, convolution, edge/Hough detection, morphology kernels and pattern matching, deskew, CLAHE, shade, and photographic effects.
  • references/distort-map-fx.md — affine/SRT, perspective, lens correction, control points, virtual pixels, displacement/absolute/variable-blur maps, -evaluate, -function, -fx, and sparse color.
  • references/animation-montage-compare.md — frame metadata, coalesce/disposal, animation edits/merging/optimization, video palettes/deinterlacing, contact sheets, metrics, diffs, and subimage search.
  • references/batch-performance-security.md — safe PowerShell/Bash batching, mogrify, naming, resource limits, concurrency, policies, temporary files, and failure logs.
  • references/advanced-analysis.md — histograms, pixel enumeration, connected components, convex hull, classification heuristics, kernels, FFT/HDRI, raw streaming, and calculated options.
  • references/photo-thumbnail-effects.md — digital-photo cleanup, selective focus/anonymization, multiple exposures, green screen, sketch/vignette work, thumbnail decoration, reflections, and constructed lighting effects.
  • references/options-index.md — on-demand alphabetized CLI option signatures. Search for the exact option; do not read the index end to end.
  • references/defines-index.md — on-demand -define keys grouped by coder or operation. Search for the coder/prefix or exact key; do not read the index end to end.

For large indexes, search before reading the entire file:

text
options-index.md:  ^### -resize\b
defines-index.md:  png:|jpeg:|compare:|connected-components:

Verification patterns

bash
magick identify -format '%f|%m|%wx%h|%z-bit|%[colorspace]|%[channels]|%n\n' output.png
magick identify -format '%s|%T|%D|%wx%h|%[page]\n' animation.gif
magick compare -metric RMSE expected.png actual.png null:

Comparison metrics commonly write to stderr, and a nonzero compare status can mean that images differ. Capture the metric and diagnostic text separately in automation.

Response style

  • State assumptions that affect pixels, cropping, transparency, metadata, colorspace, or animation behavior.
  • Give commands for the user’s actual shell.
  • Explain only the non-obvious ordering or operators.
  • Warn before destructive mogrify use.
  • Include verification for batch, lossy, animated, color-managed, multi-page, or security-sensitive work.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Imagemagick Cli AI skill do?

Comprehensive ImageMagick 7 command-line image processing for inspecting, converting, resizing, cropping, compositing, masking, drawing, annotating, color correction, quantization, filtering, morphology, distortion, animation, montage, comparison, metadata, batch automation, and advanced pixel analysis. Use whenever a task mentions ImageMagick, `magick`, `identify`, `mogrify`, raster image conversion or batch image manipulation, or when a reproducible CLI pipeline is preferable to a GUI or language binding. Also use for debugging ImageMagick commands, porting ImageMagick 6 `convert` syntax...

Why use Imagemagick Cli on TypingMind?

Because you install it once and use it with any model. Imagemagick Cli is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Imagemagick Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Yuki001/game-dev-skills/tree/main/skills/imagemagick-cli. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Imagemagick Cli?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Imagemagick Cli?

As many as you like. As long as a model supports skills, you can use Imagemagick Cli with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Imagemagick Cli AI skill free?

It is published on GitHub by Yuki001. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇