メニュー
Generate a bitmap for the Cowart canvas via Vetta generate_image, then insert or replace via Cowart MCP. Use when the user asks to create, fill, replace, or place an AI-generated image on a Cowart canvas.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/openvetta/open-vetta --skill cowart-image-genコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Drive a real Chrome browser to do things on the web - navigate, read pages that need a login, click, fill and submit forms, take screenshots, and extract data from an interactive page. Use when the user wants the agent to actually operate a site (sign in, click through, submit, export, check an order/dashboard/admin page), not when a summary from search results is enough. Runs the agent-browser CLI through a plugin-managed shim.
Build and edit design documents (.vetd) on the Vetta design canvas — app screens, landing pages, slides, posters, infographics. Use when the user asks for a UI design, mockup, screen, deck, or poster, or attaches a design frame/element from the canvas. Frames are real React (TSX) routes, not pictures. Do NOT use for ordinary front-end work in the user's own codebase — building, styling or reworking pages of a real app is that repo's job, and none of the vetd_* tools or canvas rules here apply to it.
Inspect, diagnose, create, edit, connect, and run Vetta content-creation node workflows. Use when the user asks to build or modify a content workflow, refers to selected canvas nodes, wants to understand workflow or generation status, needs an image/video generation failure diagnosed, or asks the agent to operate the content-creation canvas.
SOC 職業分類に基づく
SKILL.md を表示中
| name | cowart-image-gen |
| description | Generate a bitmap for the Cowart canvas via Vetta generate_image, then insert or replace via Cowart MCP. Use when the user asks to create, fill, replace, or place an AI-generated image on a Cowart canvas. |
| Intent | Tool |
|---|---|
| Brand-new image / fill AI image holder / invent a scene | generate_image |
| Revise an existing image or annotation screenshot | edit_image (use cowart-image-edit skill) |
Do not use an imagegen skill or ad-hoc scripts. After the bitmap exists on disk, place it with Cowart MCP insert_cowart_image.
Cowart MCP tools should be available (plugin cowart-vetta enabled). Prefer opening the canvas first (open_cowart_canvas).
Read selection with MCP get_cowart_selection (projectDir = user workspace).
If exactly one selected shape is an AI image holder (isAiImageHolder or meta.cowartAiImageHolder), use holder size (props.w / props.h) as the generation contract.
Call generate_image to produce the bitmap. Resolve the real local output path.
Call MCP insert_cowart_image with projectDir and that image path:
replaceAiImageHolder: true).generate_image prompt when replacing a holder.