
GIMP Image Editing CLI
Lets an agent edit, layer, filter and export images from the command line via a stateful GIMP-style CLI
- Repository
- HKUDS/CLI-Anything
- Stars
- 58,084
- Licence
- Apache-2.0
- Files
- 1 file
What it does
This skill teaches an AI agent to use a command-line tool called cli-anything-gimp for editing images without a graphical interface. The agent can create project files, add and arrange layers, resize or crop canvases, add text and rectangles, and render the result to a PNG or other image. The tool is built on the Pillow Python imaging library, and it keeps undo and redo history so changes can be reverted.
Great for
- Developers who want an AI agent to batch-process or compose images in scripts
- Designers who want quick layered compositions such as posters without opening GIMP
- Anyone automating repeatable image edits that must be reviewed afterwards
Skip it if
- Users who need full GIMP features such as brushes, painting or advanced selections, since the skill only covers the listed commands (the reason: the commands are a limited subset)
- Workflows where text or rectangles must be verified from the project file alone, since draw operations are only applied at render time (review the exported image instead)
Try asking
- “Create a new image project, add a text layer saying 'Launch Night', and render it to output.png”
- “Resize a canvas to 1080x1080 and set its DPI to 300”
- “Add a photo as a layer, offset it by -48 pixels, apply a filter and export the result”
- “Show a histogram of an image and list the media files referenced in a project”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
cli-anything-gimp.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip cli-anything-gimp.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip cli-anything-gimp.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Use the --json flag and absolute file paths so the agent can parse output reliably
- Always open the exported image to check text and rectangle placement, because draw operations are applied only at render time
- Install the package with pip and confirm the CLI runs with --help before asking the agent to edit images
What's inside
- SKILL.md
Redistributed unmodified from HKUDS/CLI-Anything under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.