
GIMP Image Editing CLI
Lets an agent create and edit images from the command line using layers, filters, text and export, without a GUI
- Repository
- HKUDS/CLI-Anything
- Stars
- 58,084
- Licence
- Apache-2.0
- Files
- 1 file
What it does
This skill teaches an AI agent to drive a command-line tool that edits images without opening the GIMP app. The agent can create a project file, add and arrange layers, resize or crop the canvas, apply filters, draw text or rectangles, and export a finished PNG or similar image. It can ask for machine-readable JSON output so it can read results reliably, and it can undo or redo steps.
Great for
- Developers who want an AI agent to batch-process or compose images in scripts
- Designers prototyping poster or overlay layouts that an agent assembles from existing files
- Agent builders who need a scriptable, stateful image editing tool
Skip it if
- Users who need the full GIMP interface or advanced manual retouching, since this is a Pillow-based tool, not the GIMP application itself
- Critical or legal image work without human review, because text and rectangle draws are applied at render time and saved project files can differ from the final output
Try asking
- “Create a new poster project, add a background image as a layer, and export it as output.png”
- “Place the text 'Launch Night' on layer 0 at a set position with a given size and colour, then render the result”
- “Crop the canvas to 1200x630 and set the DPI to 300”
- “List the available filters and apply one to layer 1”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
skills.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip skills.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip skills.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
- Ask the agent to use --json output and to check that the exported file exists before reporting success
- Review the exported image itself after text, rectangle, offset or filter changes, not just the project JSON
- Use absolute file paths and keep backups of original images before the agent overwrites outputs
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.