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.

56

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/canva-automation/SKILL.md

The canonical home for this skill is canva-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, actionable catalog of Canva MCP workflows with concrete tool slugs, parameters, and explicit async-polling checkpoints. Its main weaknesses are moderate redundancy across the per-workflow Pitfalls and the consolidated Known Pitfalls/Quick Reference sections, and error-recovery loops that are implied rather than explicit.

Suggestions

De-duplicate the "Known Pitfalls" section against the per-workflow Pitfalls, or convert it into a short cross-reference so the same async/polling/expiry notes aren't stated twice.

Add an explicit error-recovery feedback loop for async jobs (e.g., "On 'failed' status: read the error field, correct the input, and re-initiate the job") to push workflow clarity toward 5.

Replace the prose async-job pattern with a concrete call sequence (tool name + key params per step) so the common case is fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is mostly operational and avoids explaining concepts Claude already knows, but the "Known Pitfalls" section repeats per-workflow pitfalls (async polling, expiring download URLs) and the "Quick Reference" table restates the tool list, so it could be tightened.

3 / 5

Actionability

Concrete tool slugs, specific parameters, enumerated status values ('in_progress', 'success', 'failed'), poll intervals (2-3s), and supported formats give mostly copy-paste-ready guidance for MCP tool invocation, with only minor gaps (e.g., the async pattern is shown as numbered prose rather than a concrete call sequence).

4 / 5

Workflow Clarity

Each workflow is numbered with "When to use", tool sequence, parameters, and pitfalls, plus explicit polling checkpoints ("poll until upload completes", "Confirm connection status shows ACTIVE"); it falls short of 5 because error-recovery feedback loops (what to do on 'failed') are only implied rather than spelled out.

4 / 5

Progressive Disclosure

Content is well-organized into clear sections (Prerequisites, Setup, Core Workflows, Common Patterns, Known Pitfalls, Quick Reference) with no nested-reference anti-pattern; no bundle files exist so all content is appropriately inline, though the >50-line body has minor organization gaps where the reference table could stand alone.

4 / 5

Total

15

/

20

Passed

Description

62%Weight 40%Scale 1-5

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 clearly Canva-specific and lists concrete capability areas, giving it strong distinctiveness and good specificity. It is capped at 3 on completeness because it lacks any explicit "Use when..." trigger guidance, and trigger-term quality is only moderate due to dominant technical jargon.

Suggestions

Add an explicit "Use when..." clause naming natural user triggers, e.g. "Use when the user wants to create, export, or organize Canva designs, or autofill brand templates."

Lead with natural user-facing terms (Canva designs, export to PDF/PNG, autofill templates) and push the Rube MCP/Composio machinery into a subordinate clause so the trigger terms users actually say dominate.

Convert the nominalized capability list into concrete verb phrases ("create and export designs, organize folders, autofill brand templates") for sharper specificity.

DimensionReasoningScore

Specificity

Names the Canva domain and several concrete capability areas ("designs, exports, folders, brand templates, autofill") but they are nominalized nouns rather than explicit verb-phrase actions, leaving minor coverage gaps versus a fully comprehensive action list.

4 / 5

Completeness

The "what" is clear ("Automate Canva tasks ... designs, exports, folders, brand templates, autofill"), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Relevant natural terms (Canva, designs, exports, brand templates, autofill) appear but they sit alongside technical jargon ("Rube MCP (Composio)", "current schemas") and lack the common conversational phrasings or synonyms a user would naturally say.

3 / 5

Distinctiveness Conflict Risk

"Canva" is a clear, narrowly-scoped niche with distinct triggers and minimal overlap risk with other skills; the description is unlikely to fire for the wrong skill.

5 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.