Canva Edit Design logo

Canva Edit Design

Organization
canva-sdks
canva-edit-design

Make edits to an existing Canva design — change or fix text, replace/insert/delete images and videos, reformat text (size, weight, style, color, alignment, lists, line height), reposition or resize elements, and update the title. Use when the user wants to change, edit, update, fix, translate, replace, or reformat content in a specific Canva design. This is the safe edit engine that other Canva skills (e.g. implement-feedback) build on.

Overview

Publishercanva-sdks
Repositorycanva-skills
Skill namecanva-edit-design
Stars
141
Forks
33
Bundled files
Instructions only
LicenseApache-2.0
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 canva-sdks on GitHub. Read the source before you install it.

Installation

Install the Canva Edit Design 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/canva-sdks/canva-skills/tree/main/plugins/canva/skills/edit-design
  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/canva-sdks/canva-skills.git /tmp/canva-skills
mkdir -p .claude/skills
cp -r /tmp/canva-skills/plugins/canva/skills/edit-design .claude/skills/canva-edit-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Canva Edit Design 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 Canva Edit Design 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 Canva Edit Design 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.

Canva Design Editing

The canonical, safe way to apply edits to an existing Canva design. Every Canva skill that mutates a design should follow this exact protocol: start a transaction → perform operations → commit (with approval). Changes are draft-only until committed and are PERMANENTLY LOST if not committed.

The Transaction Protocol (always these steps, in order)

  1. Canva:start-editing-transaction — pass the design_id. Remember the returned transaction_id and the pages array; both are required by later calls. ALWAYS show the user the thumbnail(s) returned here.
  2. Canva:perform-editing-operations — apply edits. Pass the transaction_id, the pages array from the previous response, the page_index of the first page being changed, and an operations array. Batch multiple operations into a single call wherever possible.
  3. Canva:commit-editing-transaction — save. See the approval gate below. After committing, the transaction_id is invalid; a new edit needs a new transaction.
  4. Canva:cancel-editing-transaction — discard the draft instead of saving (e.g. the user rejects the preview, or you opened a transaction only to inspect the design).

Capabilities — what the API CAN and CANNOT do

CAN (operations on perform-editing-operations)

  • Text content: replace_text (whole element), find_and_replace_text (substring)
  • Text formatting (format_text): font size, weight (normal/bold), style (normal/italic), color, alignment, line height, underline, strikethrough, links, list level/marker
  • Media: update_fill (replace image/video), insert_fill (add image/video), delete_element
  • Layout: position_element, resize_element
  • Metadata: update_title
  • Autofill mapping: update_autofill_field (fixed-page designs only)

CANNOT

  • Change font family/typeface (only size, weight, style)
  • Add new text elements (you can only insert media, not new text boxes)
  • Change background colors or gradients
  • Add, remove, or reorder pages/slides
  • Modify animations, transitions, or element opacity (except on newly inserted fills)
  • Group/ungroup elements, or restyle shapes (only text inside shapes is editable)

When a requested change is in the CANNOT list, tell the user it must be done manually in the Canva editor — don't attempt a workaround.

Responsive pages — restricted operation set

Some pages come back marked is_responsive: true. On those pages, ONLY these operations are allowed: update_title, replace_text, update_fill, delete_element, find_and_replace_text.

Before calling perform-editing-operations, check the pages array. If any operation targets a responsive page with an unsupported op (e.g. format_text, position_element, resize_element, insert_fill), do NOT make the call — tell the user that operation isn't supported on that page and offer an alternative.

The commit approval gate (required)

commit-editing-transaction makes changes permanent. You MUST show the user exactly what changed (and the preview thumbnail) and get explicit approval before committing — e.g. "Here's the preview. Save these changes to your design?" Wait for a clear yes.

  • Do NOT commit without approval.
  • Do NOT tell the user changes are saved before the commit call has succeeded.
  • After a successful commit, give the user a direct link to open the design in Canva.
  • If a commit fails, all changes are lost — start a new transaction to retry.

Note for composing skills: a skill that already collects a single up-front approval for a batch of changes (e.g. canva-implement-feedback) should treat that approval as covering the commit and NOT ask again. Follow that skill's own confirmation rules; the gate above is the default for direct, ad-hoc edits.

Workflow

Step 1: Resolve the design

  • Short link (canva.link/...) → Canva:resolve-shortlink to get the URL.
  • Full Canva URL → extract the design ID (the segment after /design/).
  • Raw design ID (starts with D) → use directly; do NOT search.
  • Nothing provided → ask for the design ID or link.

Step 2: Start the transaction and inspect

Call Canva:start-editing-transaction. Show the thumbnail(s). Use the returned content to locate the exact element_ids you need to target. (If you only needed to look, call cancel-editing-transaction and stop.)

Step 3: Build and perform operations

Translate the user's request into concrete operations. Confirm scope first when a find_and_replace_text string could match in multiple places or contexts — ask which instances they mean. Batch all operations into one perform-editing-operations call when you can.

Step 4: Preview and commit

Show the resulting thumbnail and a plain-language list of what changed. Ask for approval, then commit-editing-transaction. Share the edit link.

Rules

  • Always remember and reuse the transaction_id and pages array within a transaction.
  • Never leave a transaction uncommitted without telling the user their draft was discarded.
  • For destructive ops (delete_element, large find_and_replace_text), confirm scope before performing.
  • Prefer one batched perform-editing-operations call over many small ones.

Frequently asked questions

What does the Canva Edit Design AI skill do?

Make edits to an existing Canva design — change or fix text, replace/insert/delete images and videos, reformat text (size, weight, style, color, alignment, lists, line height), reposition or resize elements, and update the title. Use when the user wants to change, edit, update, fix, translate, replace, or reformat content in a specific Canva design. This is the safe edit engine that other Canva skills (e.g. implement-feedback) build on.

Why use Canva Edit Design on TypingMind?

Because you install it once and use it with any model. Canva Edit Design 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 Canva Edit Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/canva-sdks/canva-skills/tree/main/plugins/canva/skills/edit-design. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Canva Edit Design?

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 Canva Edit Design?

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

Is the Canva Edit Design AI skill free?

Yes. It is published on GitHub by canva-sdks under the Apache-2.0 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 👇