Agent Skills

cli-anything-gimp

Command-line interface for Gimp - A stateful command-line interface for image editing, built on Pillow. Designed for AI agents and pow...

Install

npx skills add https://github.com/hkuds/cli-anything --skill cli-anything-gimp
SKILL.md

cli-anything-gimp

A stateful command-line interface for image editing, built on Pillow. Designed for AI agents and power users who need to create and manipulate images without a GUI.

Installation

This CLI is installed as part of the cli-anything-gimp package:

pip install cli-anything-gimp

Prerequisites:

  • Python 3.10+
  • gimp is recommended for native batch rendering, but layered compositions can still render through the built-in Pillow path when GIMP is unavailable or when deferred draw operations are present

Usage

Basic Commands

# Show help
cli-anything-gimp --help

# Start interactive REPL mode
cli-anything-gimp

# Create a new project
cli-anything-gimp project new -o project.json

# Run with JSON output (for agent consumption)
cli-anything-gimp --json project info -p project.json

REPL Mode

When invoked without a subcommand, the CLI enters an interactive REPL session:

cli-anything-gimp
# Enter commands interactively with tab-completion and history

Command Groups

Project

Project management commands.

Command Description
new Create a new project
open Open an existing project
save Save the current project
info Show project information
profiles List available canvas profiles
json Print raw project JSON

Layer

Layer management commands.

Command Description
new Create a new blank layer
add-from-file Add a layer from an image file
list List all layers
remove Remove a layer by index
duplicate Duplicate a layer
move Move a layer to a new position
set Set a layer property (name, opacity, visible, mode, offset_x, offset_y); negative offsets are accepted naturally
flatten Flatten all visible layers
merge-down Merge a layer with the one below it

Canvas

Canvas operations.

Command Description
info Show canvas information
resize Resize the canvas (without scaling content)
scale Scale the canvas and all content proportionally
crop Crop the canvas to a rectangle
mode Set the canvas color mode
dpi Set the canvas DPI

Filter Group

Filter management commands.

Command Description
list-available List all available filters
info Show details about a filter
add Add a filter to a layer
remove Remove a filter by index
set Set a filter parameter
list List filters on a layer

Media

Media file operations.

Command Description
probe Analyze an image file
list List media files referenced in the project
check Check that all referenced media files exist
histogram Show histogram analysis of an image

Export Group

Export/render commands.

Command Description
presets List export presets
preset-info Show preset details
render Render the project to an image file; deferred draw ops are applied at render time

Session

Session management commands.

Command Description
status Show session status
undo Undo the last operation
redo Redo the last undone operation
history Show undo history

Draw

Drawing operations (applied at render time).

Command Description
text Draw text on a layer (by converting it to a text layer)
rect Draw a rectangle (stored as drawing operation)

Examples

Create a New Project

Create a new gimp project file.

cli-anything-gimp project new -o myproject.json
# Or with JSON output for programmatic use
cli-anything-gimp --json project new -o myproject.json

Interactive REPL Session

Start an interactive session with undo/redo support.

cli-anything-gimp
# Enter commands interactively
# Use 'help' to see available commands
# Use 'undo' and 'redo' for history navigation

Export Project

Export the project to a final output format.

cli-anything-gimp --project myproject.json export render output.png --overwrite

Layered Composition Workflow

For overlay-heavy compositions:

cli-anything-gimp --project poster.gimp-cli.json layer set 0 offset_x -48
cli-anything-gimp --project poster.gimp-cli.json layer set 0 offset_y 24
cli-anything-gimp --project poster.gimp-cli.json draw text --layer 0 --text "Launch Night" --x 96 --y 120 --size 72 --color "#f6f1e8"
cli-anything-gimp --project poster.gimp-cli.json export render output.png --overwrite

Notes:

  • layer set now accepts negative offset_x and offset_y values in both command mode and REPL mode.
  • draw text and draw rect are render-time operations. Treat the exported image, not only the project JSON, as the thing to review.
  • For projects with deferred draw ops, expect the Pillow render path to be the stable default even if GIMP is installed.

State Management

The CLI maintains session state with:

  • Undo/Redo: Up to 50 levels of history
  • Project persistence: Save/load project state as JSON
  • Session tracking: Track modifications and changes

Output Formats

All commands support dual output modes:

  • Human-readable (default): Tables, colors, formatted text
  • Machine-readable (--json flag): Structured JSON for agent consumption
# Human output
cli-anything-gimp project info -p project.json

# JSON output for agents
cli-anything-gimp --json project info -p project.json

For AI Agents

When using this CLI programmatically:

  1. Always use --json flag for parseable output
  2. Check return codes - 0 for success, non-zero for errors
  3. Parse stderr for error messages on failure
  4. Use absolute paths for all file operations
  5. Verify outputs exist after export operations
  6. Review rendered outputs after offset, draw, blend-mode, or filter changes instead of trusting saved project state alone

More Information

  • Full documentation: See README.md in the package
  • Test coverage: See TEST.md in the package
  • Methodology: See HARNESS.md in the cli-anything-plugin

Version

1.0.0

Related skills

ai-image-generationgenmedia-labs713KGenerate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-secoai-image-generation101-skills547KGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stnano-banana-2prime-skills424KGenerate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream insteimage-editprime-skills424KEdit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers