Agent Skills: image-read
Read (not generate) images via a subagent so the pixel payload stays out of the parent conversation. Dispatches Haiku by default, escalates to Sonnet/Opus when the caller flags ambiguity or needs load-bearing detail.
UncategorizedID: idvorkin/chop-conventions/image-read
11
Install this agent skill to your local
Skill Files
Browse the full folder contents for image-read.
Loading file tree…
Select a file to preview its contents.