Agent Skills: detecting-tips-zones

Text-prompted image zone detection using TIPSv2 B/14 on CPU. Produces `focus_targets` / `focus_edges` bbox lists from natural-language labels, ready to feed into `svg-portrait-mode`. Use when you want automatic foreground/background separation from prompts like "dog face" + "wooden floor" instead of hand-annotating bboxes.

UncategorizedID: oaustegard/claude-skills/detecting-tips-zones

Author

oaustegard

https://github.com/oaustegard View all skills

Repository

oaustegard/claude-skills

oaustegardLicense: MIT

1287

Install this agent skill to your local

pnpm dlx add-skill https://github.com/oaustegard/claude-skills/detecting-tips-zones

Skill Files

Browse the full folder contents for detecting-tips-zones.

Download Skill

Loading file tree…

Select a file to preview its contents.