Canva

Organization

social-media-skills

canva

The Canva craft skill — produce on-brand social graphics, carousels, quote cards, infographics, and thumbnails at scale without a designer, and escape the "Canva look." Use when someone wants to design in Canva, make social graphics, set up a Brand Kit, batch-produce graphics (Bulk Create), resize one design for every platform (Magic Resize), use Canva's AI (Magic Studio), or asks why their posts look like a template. Uses the SCALE framework. Reads brand-profile + design-and-templates + voice-builder first. The agent specs, and creates designs directly where the Canva MCP/Connect APIs are connected; the human approves every visual; the export publishes via WoopSocial. Never strips watermarks, impersonates another brand, or uses unpermitted likeness; AI-disclosure + accessibility floor apply. Distinct from design-and-templates (the brand system this executes), image-prompt + the image tools (dedicated generation), ai-image-editing (the edit router), and capcut/descript (video editing).

Overview

Publisher	social-media-skills
Repository	`skills`
Skill name	`canva`
Stars	215
Forks	44
Bundled files	5
License	MIT
Links	Skill source Repository Homepage

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.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by social-media-skills on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/social-media-skills/skills/tree/main/skills/canva
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.

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/social-media-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/canva .claude/skills/canva

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Canva 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 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 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

The on-brand-at-scale design tool skill — start from the Brand Kit, customize past the template, automate the repeatable, layer in AI while keeping it editable, and export right. The agent specs (and can drive Canva via its connector), the human approves every visual, and WoopSocial publishes the finished file. (Ships with tools/integrations/canva.md.)

The POV: Canva's job is on-brand volume — the enemy is the "Canva look"

Canva in 2026 is not a template toy; it's a five-surface design platform (editor, Sheets, Code, Video 2.0, Affinity) whose AI reads your Brand Kit before it generates — and the agent can operate it directly through its MCP connector. Two top-1% moves separate expert use from everyone else's. (1) Brand Kit first: locking colors/fonts/logos/voice before generating is the difference between ~20% and ~80% on-brand first drafts — most users skip it and hand-fix every design forever. (2) The automation layer is where the leverage is: Bulk Create (one master template + a CSV = 60 graphics in one run) is the most underrated feature in the product — "almost nobody uses" it. And the craft edge: templates are scaffolding, not the finished design — the recognizable "Canva look" (untouched layout, default fonts, familiar stock) is the tell that costs you credibility, and de-templating (swap the stock, change the bones, apply the brand) is the fix. Honest trade-off throughout: dedicated generators beat Dream Lab on pure image quality; Canva wins on the integrated brand-aware workflow.

Read these first

brand-profile + design-and-templates — the brand system this executes.
voice-builder — any copy on the designs (Magic Write is a second-pass editor, not the voice).

The framework: SCALE

(Depth: references/the-scale-framework.md.)

S — Start from the Brand Kit: lock colors/fonts/logos/voice before generating; on Teams, lock templates + approvals so scale can't drift.
C — Customize past the template: replace every stock element, change the layout bones, apply brand type + color, strip decorations — if a stranger can name the template, keep going.
A — Automate the repeatable: Bulk Create (CSV → variants), Magic Resize (one master → every size), Magic Switch (formats + 150+ languages), Connect APIs/MCP for direct agent operation.
L — Layer in AI, keep it editable: Dream Lab / Canva AI 2.0 / Magic Layers as editable material; Magic Write as second-pass; dedicated generators (→ image-prompt) when pure quality matters; AI-disclosure where required.
E — Export right + hand to publish: correct format/size per platform, legibility floor, alt text → the finished file → scheduling-and-queue → WoopSocial.

The reality (verify-quarterly)

2026 Canva: Canva AI 2.0 (Apr 2026; editable design objects; the Canva Design Model + partner models), Magic Layers (Mar 2026; AI image → editable layers; ~9M uses in month one; US/UK/CA/AU rollout), Dream Lab (Leonardo-powered), Bulk Create, Magic Resize/Switch (150+ languages), Sheets/Charts, Video 2.0, and the unified Affinity app free (since Oct 2025; AI features behind Pro). The agent can operate Canva via the MCP server / AI Connector (Claude since Jul 2025; Brand-Kit-aware since Jan 2026; also ChatGPT/Copilot) and the Connect APIs (Design Editing GA, Resize, Data Connectors). Plans: Pro ≈ $12–15/mo; credit figures conflict across sources — check the in-app tracker (added Mar 2026). Honest trade-offs: Midjourney-class tools beat Dream Lab on image quality; pro prepress still needs Adobe. Attribute all; verify-quarterly. Full detail: references/canva-2026-reality.md. The weekly loop, the Bulk Create pattern, the de-templating checklist, and two worked examples: references/workflows-and-templates.md.

Honest scope (never violate)

The agent specs/drafts and — where the Canva MCP/Connect APIs are connected — creates/resizes/adapts directly; otherwise exact steps for the human. The human approves every visual (the agent never fabricates "that looks great"). Canva renders; WoopSocial publishes the finished export (10 platforms, validation, queue; measurement: the platforms' native analytics); Canva's own Content Planner exists — the split is a stack choice, stated honestly. WoopSocial does not generate or edit designs.
Licensing/IP: no watermark-stripping, template-ripping, brand impersonation, or unpermitted likeness (real or AI lookalike); AI-disclosure (EU AI Act; C2PA) for generated visuals; accessibility floor (WCAG contrast, sizes, ≤2 fonts, alt text); never fabricate credits, capabilities, or metrics — verify in-app. (Full scope: references/scope-and-connections.md.)

Distinct from its siblings (route correctly)

canva (this) = the brand-aware design workflow/tool craft · design-and-templates = the brand visual system this executes · image-prompt / ideogram / nano-banana / flux = dedicated image generation (drops into this workflow) · ai-image-editing = the edit router (Magic Eraser/Expand/ Grab are the in-Canva equivalents) · infographic-and-data-viz / quote-cards-and-text-graphics / carousel-writer / thumbnail-design = the format crafts this renders · capcut / descript = serious video editing (Video 2.0 covers simple motion).

Where this connects

Reads first: brand-profile + design-and-templates + voice-builder. Renders for: quote-cards-and- text-graphics, infographic-and-data-viz, carousel-writer, thumbnail-design, before-after-and- transformation, story-writer. Pairs with: image-prompt + the image tools (hero imagery), content- recycling (one master → many cuts), Magic Switch (localization). Publishes via: export → scheduling-and-queue → WoopSocial. Tool file: tools/integrations/canva.md. Measure with: native + analytics-and-reporting — never fabricated.

Definition of done

On-brand Canva output produced through the system, not around it: Brand Kit locked first (colors/fonts/logos/ voice; templates + approvals locked on team tiers), templates used as scaffolding and customized past recognition (stock replaced, bones changed, brand type/color applied — a stranger can't name the template), the repeatable automated (Bulk Create for batches with a QA pass on overflow; Magic Resize for the platform set; Magic Switch QA'd for localization), AI layered as editable material with honest trade-offs (dedicated generators for pure quality; Magic Write as second-pass only) and AI-disclosure where required, and exports correct per platform with the legibility floor held (contrast, sizes, ≤2 fonts, safe zones, alt text); agent operation via MCP/Connect APIs only where actually connected (exact human steps otherwise), the human approving every visual, and the finished file published via WoopSocial; licensing/IP clean (no watermark-stripping, template-ripping, impersonation, or unpermitted likeness); no fabricated credits, capabilities, or metrics; and correctly distinguished from design-and-templates, the image-generation tools, ai-image-editing, and the video editors.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Canva AI skill do?

Why use Canva on TypingMind?

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

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

Which AI models can use Canva?

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?

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

Is the Canva AI skill free?

Yes. It is published on GitHub by social-media-skills 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

Grilling

mattpocock

CommunityPopular

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Teach

Teach the user a new skill or concept, within this workspace.

Api Design

Patrones de diseño REST API incluyendo nomenclatura de recursos, códigos de estado, paginación, filtrado, respuestas de error, versionado y rate limiting para APIs de producción.

Accessibility

WCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

canva

The POV: Canva's job is on-brand volume — the enemy is the "Canva look"

Read these first

The framework: SCALE

The reality (verify-quarterly)

Honest scope (never violate)

Distinct from its siblings (route correctly)

Where this connects

Definition of done

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now