CtrlK
BlogDocsLog inGet started
Tessl Logo

canva-automation

Automate Canva tasks via Rube MCP (Composio): designs, exports, folders, brand templates, autofill. Always search tools first for current schemas.

Install with Tessl CLI

npx tessl i github:Lingjie-chen/MT5 --skill canva-automation
What are skills?

64

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

83%

30%

Bulk Design Export for Print Production

Design export async workflow

Criteria
Without context
With context

RUBE_SEARCH_TOOLS first

0%

0%

List designs tool

0%

100%

Pagination loop

100%

100%

Export job creation

0%

100%

Export job polling

50%

100%

Poll interval

100%

100%

Success/failed check

100%

100%

Download URL expiry awareness

30%

30%

job_id propagation

100%

100%

Defensive response parsing

50%

100%

Without context: $0.4132 · 1m 32s · 23 turns · 26 in / 5,522 out tokens

With context: $0.4683 · 1m 41s · 23 turns · 29 in / 5,607 out tokens

76%

44%

Product Image Integration for Social Media Campaign

Asset upload and design creation

Criteria
Without context
With context

RUBE_SEARCH_TOOLS first

0%

0%

Connection verification

0%

0%

ACTIVE status check

0%

0%

Upload job creation

0%

100%

Upload status polling

0%

100%

Upload before design

100%

100%

Design creation tool

0%

100%

Async status values

100%

100%

job_id tracking

50%

100%

Defensive response parsing

42%

100%

Without context: $0.5788 · 2m 29s · 32 turns · 32 in / 8,370 out tokens

With context: $0.4359 · 1m 53s · 22 turns · 25 in / 6,189 out tokens

80%

7%

Automated Product Promotion Card Generator

Brand template autofill pipeline

Criteria
Without context
With context

RUBE_SEARCH_TOOLS first

0%

0%

Brand template list tool

60%

100%

Template ID resolution

100%

100%

Autofill tool used

66%

100%

Case-sensitive placeholders

100%

100%

Autofill async polling

100%

100%

job_id used for polling

100%

100%

Exponential backoff or rate limiting

16%

0%

Brand-template-only enforcement

100%

100%

Success/failed handling

100%

100%

Without context: $0.4899 · 1m 59s · 28 turns · 34 in / 6,610 out tokens

With context: $0.4779 · 1m 54s · 20 turns · 434 in / 6,786 out tokens

Evaluated
Agent
Claude Code

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.