AC 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).
The Canva craft skill — produce on-brand social graphics, carousels, quote cards, infographics, and thumbnails at scale without a designer, and escape the…
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 56/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 12 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1808 tokens
- low No test case covers injection arriving through data
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1000: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 9 headings
- +3Step-by-step instructions: 9 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.