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:davepoon/buildwithclaude --skill canva-automation67
Quality
56%
Does it follow best practices?
Impact
79%
1.51xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/canva-automation/SKILL.mdDiscovery
50%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description effectively communicates specific Canva automation capabilities and is highly distinctive due to explicit platform naming. However, it critically lacks explicit trigger guidance ('Use when...') which would help Claude know when to select this skill, and the trigger terms could be expanded to include more natural user language variations.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user asks to create Canva designs, export graphics, manage Canva folders, or work with brand templates.'
Include natural user phrases as trigger terms such as 'create a graphic', 'design in Canva', 'Canva project', or 'social media design'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'designs, exports, folders, brand templates, autofill' - these are distinct, actionable capabilities within the Canva domain. | 3 / 3 |
Completeness | Describes what it does (automate Canva tasks) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. The instruction to 'search tools first' is operational, not selection guidance. | 1 / 3 |
Trigger Term Quality | Includes 'Canva' as a strong trigger term and domain-specific terms like 'designs', 'exports', 'brand templates', but missing common user phrases like 'create a design', 'Canva graphic', or file extensions users might mention. | 2 / 3 |
Distinctiveness Conflict Risk | 'Canva' and 'Rube MCP (Composio)' are highly specific identifiers that create a clear niche. Unlikely to conflict with other skills due to the explicit platform and integration naming. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive coverage of Canva automation workflows with clear sequencing and good pitfall documentation. However, it lacks executable code examples (relying on tool names and parameter descriptions instead) and could be more concise by consolidating repeated patterns and splitting detailed reference material into separate files.
Suggestions
Add executable code examples showing actual MCP tool calls with concrete parameter values instead of just listing parameter names
Consolidate the async polling pattern explanation into a single reference section and link to it from each workflow instead of repeating the concept
Move the Quick Reference table and detailed parameter lists to a separate REFERENCE.md file to reduce the main skill length
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., repeating async polling patterns across multiple workflows, explaining pagination multiple times). The Quick Reference table at the end duplicates information already covered in workflows. | 2 / 3 |
Actionability | Provides tool names and parameter lists but lacks executable code examples. The 'Async Job Pattern' and 'ID Resolution' sections use pseudocode-style descriptions rather than actual API call examples with concrete syntax. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with numbered steps, explicit [Required]/[Optional] markers, and validation checkpoints (polling for job completion). The async job pattern explicitly describes the feedback loop for error recovery. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but the document is quite long (~200 lines) with all content inline. The toolkit docs link is provided but detailed API reference could be split into separate files for better navigation. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Reviewed
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.