argos-eye
Locate described image targets in Claude Code and return verified coordinates.
- Stars
- 0
- Forks
- 0
- Updated
- Updated Apr 21, 2026
Locate described image targets in Claude Code and return verified coordinates.
Provide an image path and a natural-language target, and the skill iteratively crops and rechecks the region before returning a bounding box, center point, confidence, and saved evidence. It can report that no target was found instead of inventing a coordinate; screenshot capture and UI interaction remain the caller’s responsibility.
Resource types
Use cases
Platforms
Runtime
Turn detailed business processes into reusable, tested AI skills.
Define portable task-specific sub-agents in Markdown for several coding assistants.
Capabilities
Public GitHub facts last synced Jul 10, 2026.
Find, create, run, and improve agent skills from real execution feedback.
Reduce LLM token use by pruning context, caching prompts, and routing models.