canva-bulk-create

Bulk-create Canva designs from tabular data using a brand template with autofill fields, producing one design per row. Use when users say "bulk create designs from this CSV", "generate one design per row", "create a design for each product", "batch generate from a template", or "autofill a template from a spreadsheet". Accepts any tabular data source — uploaded files, pasted tables, JSON, or URLs.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

68%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.

A well-structured, actionable workflow with concrete tool calls and payloads, clear sequencing, and useful user-facing checkpoints. The main weakness is the absence of a retry/feedback loop for the batch operation, which the rubric caps at workflow_clarity 3.

Suggestions

Add a validate->fix->retry feedback loop for failed rows in Step 5/6 (e.g., retry once after correcting a bad asset ID or field value, then log still-failing rows) to lift workflow_clarity past the batch-operation cap of 3.

Render the final Canva:autofill-design invocation in Step 5 as a complete command block (template_id + data payload + title) instead of prose, to close the actionability gap.

Trim the minor redundancy between Step 4's Image Field Handling patterns and Step 5's per-row instructions, and drop justifications like 'sequential calls are easier to debug', to tighten conciseness toward a 5.

Dimension	Reasoning	Score
Conciseness	The body is efficient and does not explain concepts Claude already knows (no 'what is Canva/CSV' filler), but has minor trims available — e.g. the Step 4 image patterns are re-explained in Step 5 and justifications like 'sequential calls are easier to debug' pad slightly. Not quite the lean-every-token-earns-its-place of a 5.	4 / 5
Actionability	Concrete, copy-paste-ready tool invocations (Canva:search-brand-templates, Canva:get-brand-template-dataset, Canva:upload-asset-from-url) and complete JSON data-payload examples cover the common cases, but the final Canva:autofill-design call in Step 5 is described in prose rather than as a complete command block — a minor gap.	4 / 5
Workflow Clarity	Six steps are clearly sequenced with real checkpoints (preview in Step 1, user-confirmed mapping in Step 4, results report in Step 6), but this is a batch operation and it lacks a validate->fix->retry feedback loop for failed rows — the guidance is to log failures and continue, not retry — which the rubric caps at 3 for batch operations.	3 / 5
Progressive Disclosure	A single well-organized SKILL.md with clear section headers and no nested/buried references; with no bundle files present everything is inline, which is appropriate, though at ~120 lines some content (field-matching rules, image patterns) could optionally live in references, leaving minor organization gaps versus a 5.	4 / 5
	Total	15 / 20 Passed

Description

100%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.

A strong, third-person description that crisply states the capability and supplies explicit, natural trigger phrases plus accepted data sources. It cleanly satisfies the what/when/trigger/specificity criteria with no padding or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Bulk-create Canva designs from tabular data', 'autofill a brand template', 'producing one design per row', and enumerates accepted sources ('uploaded files, pasted tables, JSON, or URLs') — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (bulk-create Canva designs from tabular data via brand-template autofill, one per row) and 'when' (a 'Use when users say...' clause with concrete trigger phrases), matching the score-5 anchor exactly.	5 / 5
Trigger Term Quality	Provides five quoted natural-language phrases users would actually say ('bulk create designs from this CSV', 'generate one design per row', 'create a design for each product', 'batch generate from a template', 'autofill a template from a spreadsheet') with synonyms (CSV, spreadsheet, per row, per product, batch).	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — Canva bulk design creation from tabular data — with distinct, specific triggers that are unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/canva/skills/canva-bulk-create/SKILL.md
Commit: 5fd93af

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.