cowart-image-gen
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.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-13
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- 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.
03 SKILL.md 正文
Cowart Image Gen (Vetta)
Vetta image tools (required)
| 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.
Preconditions
Cowart MCP tools should be available (plugin cowart-vetta enabled). Prefer opening the canvas first (open_cowart_canvas).
Workflow
-
Read selection with MCP
get_cowart_selection(projectDir= user workspace). -
If exactly one selected shape is an AI image holder (
isAiImageHolderormeta.cowartAiImageHolder), use holder size (props.w/props.h) as the generation contract. -
Call
generate_imageto produce the bitmap. Resolve the real local output path. -
Call MCP
insert_cowart_imagewithprojectDirand that image path:- Holder selected → prefer replace the holder (
replaceAiImageHolder: true). - Otherwise insert onto the current page (from view/canvas state).
- Holder selected → prefer replace the holder (
Constraints
- Pass user projectDir, not the plugin root.
- Keep original holders only if the user asks to preserve slots.
- Include target aspect ratio in the
generate_imageprompt when replacing a holder.
04 同仓库更多 Skills
review-canvas
Present a multi-file code review as a Canvas diff artifact. Use when the user asks for a review, 代码评审, 变更审查, or a cross-file summary of changes — not for a single edit (the chat diff card already shows it) or a prose report (report-canvas).
report-canvas
Produce a standalone report, audit board, or long-form analysis as a Canvas artifact. Use when the user asks for a report, 报告, 审计看板, or a deliverable that should live beside chat — not when they only want a short chat answer or to inspect a live web page.
publish-ability
Publish a skill, scene, MCP server, plugin, or bundle to the Vetta ability marketplace. Use when the user asks to upload/publish/submit an ability, put a plugin on the marketplace, share a skill with other users, or migrate an existing package into Vetta.
install-ability
在本机 Vetta 中安装能力——插件(plugin)、Skill/场景(scene)与 MCP 服务器。用户说「装一个插件 / install plugin / 从能力市场安装 / 加一个 MCP server / 配置 MCP / 装个 skill」,或插件装完没生效、需要 reload、pending 版本没应用时使用。不用于安装 npm 依赖、IDE 插件、浏览器扩展,也不用于开发插件(那是 plugin-workbench)或创作 Skill(那是 create-skill)。
database-analysis
Answer business questions from connected databases with read-only queries, then analyze metrics, trends, rankings, breakdowns, and period comparisons. Use for 问数、查数、数据库分析、销量/收入/用户指标、同比环比 or follow-up data questions. Not for application database migrations or modifying records.
create-skill
Create or update Vetta-compatible Agent Skills. Use when the user asks to create a skill, add a SKILL.md workflow, register a skill in skills-manifest.json, package a skill in a Vetta plugin, or add a built-in Vetta skill preset.