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.
Ask your Agent
Use this Skill: https://skilld.dev/gh/oaustegard/claude-skills/detecting-tips-zones
This session only. Nothing lands on disk.
≈80 tokens on demand. Your agent reads this file only when SKILL.md points to it.
All notable changes to the detecting-tips-zones skill are documented in this file. The format is based on Keep a Changelog.
Source: SKILL.md on GitHub
This skill is safe. It implements image zone detection using the TIPSv2 model. It requires a local clone of an official Google DeepMind repository and standard machine learning libraries. No malicious patterns or security risks were detected.
No alerts
Risk: LOW · No issues
Signed by skilld at 4b31e7d. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub yesterday.
{
"version": "0.1.0"
}