canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
63
47%
Does it follow best practices?
Impact
89%
1.48xAverage score across 3 eval scenarios
Failed to scan
The risk profile of this skill
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/canvas-design/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 adequately communicates the skill's purpose and includes an explicit 'when to use' clause, which is a strength. However, it suffers from some vagueness ('design philosophy', 'other static piece') and could benefit from more specific trigger terms and concrete capability listings. The second-person voice ('You should use') is present but the description also uses third-person imperative, so the impact is moderate.
Suggestions
Expand trigger terms to include common variations like 'illustration', 'graphic', 'flyer', 'banner', 'infographic', 'visual artwork' to improve matching coverage.
Replace vague phrases like 'using design philosophy' and 'other static piece' with concrete capabilities such as 'applying color theory, typography, and layout principles' and specific output types like 'flyers, banners, infographics'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (visual art/design) and some actions (create posters, art, designs), but 'using design philosophy' is vague and the specific capabilities like file format handling aren't well elaborated beyond mentioning .png and .pdf. | 2 / 3 |
Completeness | Clearly answers both 'what' (create visual art in .png and .pdf documents) and 'when' ('when the user asks to create a poster, piece of art, design, or other static piece'), with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some natural terms users would say like 'poster', 'piece of art', 'design', and file formats '.png' and '.pdf', but misses common variations like 'illustration', 'graphic', 'flyer', 'banner', 'infographic', 'visual', or 'artwork'. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to visual art creation, but 'design' is broad and could overlap with UI design, web design, or presentation skills. The 'static piece' qualifier helps but 'other static piece' is vague enough to cause potential conflicts. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a creative and ambitious vision for guiding Claude to produce visual art, and the philosophy examples provide useful creative direction. However, it is severely undermined by extreme verbosity and repetition (especially around craftsmanship emphasis), lacks concrete executable guidance for actually generating PDF/PNG output, and presents all content as a monolithic document with no progressive disclosure. The skill reads more like an inspirational manifesto than actionable technical instructions.
Suggestions
Cut repetitive emphasis on craftsmanship, museum quality, and minimal text to single mentions each—the current 5-6 repetitions waste significant token budget without adding information.
Add concrete, executable code examples showing how to generate PDF/PNG output (e.g., using Python with reportlab, PIL/Pillow, or cairo), including canvas dimensions, font loading from ./canvas-fonts, and file export.
Extract the philosophy examples into a separate EXAMPLES.md file and reference it from the main skill, reducing the main file to a concise overview with clear navigation.
Add explicit validation checkpoints (e.g., 'Verify all elements are within canvas bounds by checking coordinates against page dimensions' with specific code) rather than just stating 'nothing overlaps' as a principle.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The instruction to emphasize 'expert craftsmanship' is itself repeated at least 5-6 times across different sections. Concepts like 'minimal text,' 'visual expression,' and 'museum quality' are restated redundantly throughout. The skill could be condensed to roughly 1/3 its length without losing any actionable information. | 1 / 3 |
Actionability | Provides some concrete guidance (philosophy examples, structural approach, font directory reference), but lacks executable code or specific tool commands for generating PDFs/PNGs. The canvas creation section is largely aspirational prose rather than concrete steps—there's no code showing how to actually render the output, what libraries to use, or what canvas dimensions to target. | 2 / 3 |
Workflow Clarity | The two-step workflow (philosophy creation → canvas creation) is clearly identified, and there's a refinement pass at the end. However, there are no validation checkpoints, no error recovery steps, and the 'deducing the subtle reference' step is vaguely positioned between the two main steps without clear sequencing. The 'final step' refinement lacks concrete criteria for when the work is 'done.' | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files for detailed guidance. The philosophy examples alone take up significant space and could be in a separate EXAMPLES.md. Everything is inline with no clear navigation structure—section headers exist but the content within each is dense and poorly delineated. | 1 / 3 |
Total | 6 / 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
- Lingjie-chen/MT5
- Commit
3069d33
- 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.