Cal Corum e02eb28e98 refactor: rename skill dirs to verb-based names to reduce autocomplete redundancy

Plugin:skill pairs now read as noun:verb commands instead of repeating
the plugin name. Also added concise descriptions to all SKILL.md frontmatter.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-19 13:57:19 -05:00

1.4 KiB

Raw Blame History

name	description	allowed-tools
generate	Generate images from text prompts using local GPU inference	Bash(z-image:*)

Z-Image - Local AI Image Generation

When to Activate This Skill

"Generate an image of..."
"Create a picture of..."
"Make me an image"
"z-image [prompt]"
User describes something visual they want generated

Tool

Binary: z-image (in PATH via ~/bin/z-image) Script: ~/.claude/skills/z-image/generate.py Model: Tongyi-MAI/Z-Image-Turbo (diffusers, bfloat16, CUDA) venv: ~/.claude/skills/z-image/.venv/

Usage

# Basic generation
z-image "a cat sitting on a cloud"

# Custom output filename
z-image "sunset over mountains" -o sunset.png

# Custom output directory
z-image "forest path" -d ~/Pictures/ai-generated/

# More inference steps (higher quality, slower)
z-image "detailed portrait" -s 20

# Disable CPU offloading (faster if VRAM allows)
z-image "quick sketch" --no-offload

Defaults

Steps: 9 (fast turbo mode)
Guidance scale: 0.0 (turbo model doesn't need guidance)
Output: zimage_TIMESTAMP_PROMPT.png in current directory
VRAM: Uses CPU offloading by default to reduce VRAM usage

Notes

First run downloads the model (~several GB)
Requires NVIDIA GPU with CUDA support
Output is always PNG format
After generating, use the Read tool to show the image to the user

1.4 KiB Raw Blame History