Cal Corum e76527a0a0 Reorganize skills: scope guards, archive deploy, restructure z-image

- Add SCOPE guards to major-domo, paper-dynasty, proxmox skills
  to prevent activation in unrelated projects
- Archive deploy skill (replaced by Gitea workflows + per-project scripts)
- Restructure z-image: remove embedded app code, add SKILL.md
  (app relocated to /mnt/NV2/Development/z-image/ as uv tool)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-28 23:48:02 -06:00

1.5 KiB

Raw Blame History

name	description	allowed-tools
z-image	Generate images from text prompts using the Z-Image Turbo model (Tongyi-MAI) with local GPU inference. USE WHEN user says "generate an image", "create a picture", "make an image of", "z-image", or describes something they want visualized.	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

1.5 KiB Raw Blame History