canva-automation
Automate Canva tasks via Rube MCP (Composio): designs, exports, folders, brand templates, autofill. Always search tools first for current schemas.
72
65%
Does it follow best practices?
Impact
79%
1.51xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/canva-automation/SKILL.mdQuality
Discovery
67%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 is concise and specific about what it does (Canva automation tasks) and is highly distinctive due to the Canva + Composio/Rube MCP scope. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill, and it could benefit from more natural user-facing trigger terms beyond the technical action names.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Canva designs, creating graphics, exporting Canva files, or managing Canva brand assets.'
Include more natural user-facing trigger terms such as 'graphic design', 'social media posts', 'create a Canva design', 'download design', or 'Canva template'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: designs, exports, folders, brand templates, autofill. Also includes the operational instruction to 'search tools first for current schemas,' which adds specificity about how the skill works. | 3 / 3 |
Completeness | The 'what' is well-covered (automate Canva tasks including designs, exports, folders, brand templates, autofill). However, there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Canva', 'designs', 'exports', 'folders', 'brand templates', 'autofill', and 'Composio/Rube MCP'. However, it misses common user variations like 'create a design', 'download from Canva', 'graphic design', or 'social media graphics' that users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Very clearly scoped to Canva via Rube MCP (Composio), which is a distinct niche. The combination of 'Canva' and 'Rube MCP (Composio)' makes it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 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 is a solid, well-structured skill that clearly documents Canva automation workflows with good sequencing and async operation handling. Its main weaknesses are moderate verbosity (repeated async warnings, parameter details that duplicate what RUBE_SEARCH_TOOLS would return) and lack of concrete executable examples (actual MCP tool call payloads). The content would benefit from being more concise at the top level with detailed workflows split into referenced files.
Suggestions
Add at least one concrete MCP tool call example with actual JSON parameters (e.g., a complete CANVA_CREATE_CANVA_DESIGN_EXPORT_JOB call) rather than just listing parameter names
Consolidate the repeated async polling guidance into the single 'Async Job Pattern' section and reference it from individual workflows instead of restating it in each pitfalls section
Consider splitting the six detailed workflow sections into a separate WORKFLOWS.md file, keeping SKILL.md as a concise overview with the setup, common patterns, quick reference table, and links to details
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some redundancy — pitfalls are repeated across sections (async polling mentioned in nearly every workflow and again in Known Pitfalls), and some parameter descriptions are things Claude could infer from tool schemas after calling RUBE_SEARCH_TOOLS. The instruction to always search tools first partially undermines the need for detailed parameter listings. | 2 / 3 |
Actionability | Tool sequences are clearly named and ordered with specific tool slugs and parameters, which is good. However, there's no executable code — the 'code blocks' are pseudocode sequences rather than actual MCP tool call examples with concrete JSON payloads. For an MCP-based skill, showing an actual tool call with example parameters would be more actionable. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit step ordering, required vs optional annotations, and the async job pattern includes a clear poll-check-extract feedback loop. Export and upload workflows both emphasize polling until completion before proceeding, which serves as validation checkpoints for these asynchronous operations. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a quick reference table, but it's quite long (~180 lines of substantive content) with all detail inline. The six workflow sections could be split into separate files with SKILL.md serving as an overview with links, especially since the skill already references external toolkit docs. | 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 | |
- Repository
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.