Create Canvas logo

Create Canvas

OrganizationPopular
microsoft
create-canvas

Create a project Copilot extension canvas for the current workspace.

Overview

Publishermicrosoft
Repositoryvscode
Skill namecreate-canvas
Stars
193.3K
Forks
44K
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by microsoft on GitHub. Read the source before you install it.

Installation

Install the Create Canvas AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/microsoft/vscode/tree/main/extensions/copilot/assets/prompts/skills/create-canvas
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/microsoft/vscode.git /tmp/vscode
mkdir -p .claude/skills
cp -r /tmp/vscode/extensions/copilot/assets/prompts/skills/create-canvas .claude/skills/create-canvas
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Canvas in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Create Canvas on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Create Canvas is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Create a working canvas extension in the current workspace. Do the implementation rather than only returning a sample.

Clarify only when needed

The extension scope is fixed: create a project extension under .github/extensions/<name>/.

If the requested canvas purpose is unclear, ask what it should display or let the user do. If durable state is required but its identity or lifetime is ambiguous, ask whether the state belongs in a workspace artifact or private extension storage.

Inspect first

Before writing:

  1. Check for existing .github/extensions/ conventions and reusable UI/server helpers.
  2. Choose a short kebab-case extension folder name and a stable canvas ID.
  3. Identify the domain identity for durable state, such as a file path, document ID, or record ID. instanceId identifies a panel, not its data.

Implement

Create .github/extensions/<name>/extension.mjs.

  • Use ES modules and import createCanvas, CanvasError, and joinSession from @github/copilot-sdk/extension.
  • Do not create a package.json or install @github/copilot-sdk; the runtime resolves it automatically.
  • Never write to stdout with console.log. Use session.log() for diagnostics.
  • Bind embedded HTTP servers to 127.0.0.1 on an ephemeral port.
  • Return an HTTP URL from open(). Do not place credentials or private state in the URL.
  • Treat open() as idempotent. Reopening the same instanceId must reuse or safely replace its live server and reload state from the stable domain identity.
  • Use process.env.VSCODE_CANVAS_DATA_DIR for private durable extension data. Validate that it is an absolute path, create a child directory for the extension, and fail explicitly when it is unavailable.
  • Store repo-owned artifacts at a sensible workspace path when the user expects them to be versioned or directly editable.
  • Use semantic HTML, keyboard-accessible controls, visible focus, labels, and ARIA status text. The page has no privileged VS Code bridge; use ordinary same-origin HTTP endpoints or server-sent events.
  • Escape untrusted values before inserting them into HTML and validate every HTTP and action input.

Declare the canvas with:

  • a short single-sentence description;
  • an optional inputSchema;
  • agent-facing actions[];
  • an open handler;
  • an onClose handler that stops instance-owned servers.

Rules:

  • If the canvas takes no input, omit inputSchema. If it declares an object schema, callers must open it with an object such as {}, not null.
  • Action names must not start with canvas..
  • Every action must have a handler and its own JSON Schema when it accepts input.
  • Return raw action results. Throw new CanvasError(code, message) for expected failures.
  • Do not rely on closing the VS Code canvas tab to call onClose; tab closure hides presentation only. Preserve the live instance so a later agent reopen can show the same state.

Keep extension.mjs focused on wiring. Put substantial HTML, CSS, client JavaScript, schemas, storage, and domain logic in sibling modules or asset files.

Validate

  1. Run node --check .github/extensions/<name>/extension.mjs and the smallest relevant extension tests.
  2. Call extensions_reload after creating or modifying the extension. This stops and restarts all extension providers; previously open canvases are rehydrated after their providers reconnect.
  3. After reload, do not claim success until the runtime confirms the canvas:
    • call list_canvas_capabilities for the canvas ID;
    • call open_canvas with a stable instanceId and schema-valid input;
    • call at least one invoke_canvas_action when actions exist.
  4. Close the canvas tab, ask the agent to reopen the same instance, and confirm the state is preserved.

Summarize the files created, the canvas and action IDs, where state is stored, and the reload and runtime verification results.

Frequently asked questions

What does the Create Canvas AI skill do?

Create a project Copilot extension canvas for the current workspace.

Why use Create Canvas on TypingMind?

Because you install it once and use it with any model. Create Canvas is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Create Canvas in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/microsoft/vscode/tree/main/extensions/copilot/assets/prompts/skills/create-canvas. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Create Canvas?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Create Canvas?

As many as you like. As long as a model supports skills, you can use Create Canvas with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Create Canvas AI skill free?

Yes. It is published on GitHub by microsoft under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇