cowart-image-edit
Revise a Cowart canvas image from an annotation screenshot using Vetta edit_image, then place the result with Cowart MCP. Use when the user submits a Cowart annotation edit or asks to clean up an annotated screenshot into a revised bitmap beside the original.
Install
npx skillscat add hwy-game/metoai/cowart-image-edit Install via the SkillsCat registry.
Cowart Image Edit (Vetta)
Vetta image tools (required)
| Intent | Tool |
|---|---|
| Modify existing image / apply annotation marks | edit_image |
| Brand-new image with no source to revise | generate_image (use cowart-image-gen skill) |
Do not use an imagegen skill. After edit_image writes a file, place it with Cowart MCP insert_cowart_image.
Workflow
Obtain the annotation screenshot (user attachment or Cowart-exported capture path from the follow-up prompt).
Call
edit_imagewith that screenshot (and original image if available) so the model applies annotated intent and removes annotation chrome (arrows, scribbles, labels) unless the user wants them kept.Place the result with MCP
insert_cowart_imagebeside the original when possible (placement: "right"); do not delete or move the original unless asked.Use
projectDir= active user workspace for all Cowart MCP calls.
Constraints
- Prefer
edit_imagefor the bitmap step, then Cowart MCP for placement. - If selection tools are available,
get_cowart_selectioncan help locate the target image.
Categories
Install
npx skillscat add hwy-game/metoai/cowart-image-edit Install via the SkillsCat registry.