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.
$npx -y skills add oaustegard/claude-skills --skill detecting-tips-zonesInstalls into the current project.
Run `npx skills use "https://github.com/oaustegard/claude-skills" --skill "oaustegard/claude-skills/detecting-tips-zones"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/oaustegard/claude-skills" that are relevant to the current task. Run `npx skills add "https://github.com/oaustegard/claude-skills"` and select the relevant skills, then follow their instructions.