一键导入
canvas-tools
Canvas node CRUD operations. Provides tools to list, get, create, update, and delete theater canvas nodes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Canvas node CRUD operations. Provides tools to list, get, create, update, and delete theater canvas nodes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Canvas node CRUD operations. Provides tools to list, get, create, update, and delete theater canvas nodes.
专业品牌视觉识别系统设计技能。解析用户logo与品牌设计需求,按照品牌视觉识别系统展示板模板构建结构化英文提示词,调用 generate_image 工具生成包含主标志、配色方案、设计网格、概念草图、灵感板、应用样机等完整元素的专业品牌设计展示板。适用于8K超高细节平面设计作品集品质输出。
专业品牌视觉识别系统设计技能。解析用户logo与品牌设计需求,按照品牌视觉识别系统展示板模板构建结构化英文提示词,调用 generate_image 工具生成包含主标志、配色方案、设计网格、概念草图、灵感板、应用样机等完整元素的专业品牌设计展示板。适用于8K超高细节平面设计作品集品质输出。
专业摄影器材、参数和案例配方指南,用于角色、道具、场景的 AI 图像生成。使用于需要把相机机身、镜头品牌、焦距、光圈、布光、景深、焦外、胶片或电影镜头质感转写成提示词的任务,适用于 GPT-image-2、nanobanana2、nanobananapro、seedream 5.0 等文生图/图生图模型。
专业化妆术与美妆产品指南,用于AI人像图像生成中的面部精致度提升。涵盖底妆体系、眼妆技法、唇妆质感、修容高光、肤质效果等完整美妆知识,适用于GPT-image-2、nanobanana2.0、nanobanana pro等文生图/图生图模型。
专业音乐创作与编曲指南,用于AI音乐生成。涵盖曲风流派、乐器配置、节拍调性、歌词编写、音乐结构设计等核心创作要素,适配 Lyria 3、Suno、Udio 等主流音乐生成模型。
| name | canvas_tools |
| description | Canvas node CRUD operations. Provides tools to list, get, create, update, and delete theater canvas nodes. |
| metadata | {"builtin_skill_version":"1.0"} |
Use this skill when the user asks to view, create, update, or delete content on the theater canvas (nodes).
Loading this skill activates the following tools:
list_canvas_nodes — List all nodes on the canvasget_canvas_node — Get full details of a specific nodeview_node_media — View actual image/video content of a media nodecreate_canvas_node — Create a new nodeupdate_canvas_node — Update an existing nodedelete_canvas_node — Delete a nodeNote: Loading this skill grants access to all node types (text, image, video, storyboard). A theater (canvas) must be active in the current conversation for these tools to work.
The canvas supports these node types (available types depend on agent configuration):
Text nodes for scripts, copy, ads, and other written content. Supports rich text (Markdown).
Fields:
title (string, required) — Node titlecontent (string, Markdown) — Body text. Supports headings (#/##/###), paragraphs, bold (text), italic (text), code blocks, etc. Required when creating; omit when updating if unchanged.tags (array, optional) — Tags for categorizationImage nodes for character designs, scenes, posters, and visual content.
Fields:
name (string) — Image namedescription (string) — Image description (scene, character info, etc.)imageUrl (string) — Image URL path (e.g. /media/xxx.jpg), supports JPEG/PNG/JPGfitMode (string) — "cover" (fill) or "contain" (fit)Video nodes for animations, short films, and motion content.
Fields:
name (string) — Video namedescription (string) — Video description (scene, duration, etc.)videoUrl (string) — Video URL path (e.g. /media/xxx.mp4), supports MP4fitMode (string) — "cover" (fill) or "contain" (fit)Storyboard nodes for shot breakdowns and multi-dimensional table content.
Fields:
shotNumber (string) — Shot number (e.g. "1-1", "2-3")description (string) — Shot descriptionduration (integer) — Duration in secondspivotConfig (JSON) — Multi-dimensional table config with custom field typesList all nodes on the canvas, optionally filtered by type.
Parameters:
node_type (string, optional) — Filter by node type (e.g. "text", "image", "video", "storyboard")Returns a list of node summaries (id, type, position, key fields).
Get full details of a specific node.
Parameters:
node_id (string, required) — ID of the node to retrieveReturns complete node data including all fields, position, and metadata.
Create a new node on the canvas.
Parameters:
node_type (string, required) — Type of node to createdata (object, required) — Node data matching the type's field schemaposition_x (number, optional) — X position. Auto-calculated if omitted.position_y (number, optional) — Y position. Auto-calculated if omitted.Example — create a text node:
create_canvas_node(
node_type="text",
data={
"title": "Chapter 1 Outline",
"content": "# Chapter 1\n\nThe story begins...\n\n## Scene 1\n\nThe protagonist appears.",
"tags": ["outline", "chapter1"]
}
)
Example — create an image node:
create_canvas_node(
node_type="image",
data={
"name": "Hero Portrait",
"description": "Main character, age 18, cheerful personality",
"imageUrl": "/media/generated-image.jpg",
"fitMode": "cover"
}
)
Update an existing node's data.
Parameters:
node_id (string, required) — ID of the node to updatedata (object, required) — Fields to update (partial update supported)Example:
update_canvas_node(
node_id="node-uuid-here",
data={"title": "Updated Title", "tags": ["revised"]}
)
Delete a node from the canvas.
Parameters:
node_id (string, required) — ID of the node to deletelist_canvas_nodes first to see what exists before creating or modifying.update_canvas_node.