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.
94
Quality
47%
Does it follow best practices?
Impact
99%
1.76xAverage score across 10 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/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 explicit 'when to use' guidance, which is a strength. However, it uses second person voice ('You should'), lacks comprehensive trigger terms for visual design work, and could be more specific about the concrete actions it performs beyond 'create'.
Suggestions
Add more natural trigger terms users would say: 'graphic', 'illustration', 'banner', 'flyer', 'infographic', 'visual artwork'
Rewrite in third person voice: 'Creates beautiful visual art...' instead of 'You should use this skill'
List more specific concrete actions: 'generate layouts, compose graphics, apply typography and color schemes'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (visual art, .png/.pdf) and some actions (create poster, art, design), but lacks comprehensive specific actions like 'generate layouts', 'apply color palettes', or 'compose graphics'. Uses second person 'You should use' which violates voice guidelines. | 2 / 3 |
Completeness | Clearly answers both what ('Create beautiful 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 keywords users would say ('poster', 'piece of art', 'design'), but missing common variations like 'graphic', 'illustration', 'banner', 'flyer', 'infographic', 'visual', or 'artwork'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of .pdf could conflict with PDF manipulation skills, and 'design' is broad enough to overlap with UI/UX design skills. The 'static piece' qualifier helps but 'visual art' remains somewhat generic. | 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.
This skill is conceptually rich but severely over-engineered for its purpose. It reads more like an artistic manifesto than actionable technical guidance, with excessive repetition of quality/craftsmanship themes and no concrete implementation details for actually generating PDF/PNG files. The verbose, philosophical tone undermines token efficiency while providing insufficient executable guidance.
Suggestions
Reduce content by 60-70% by removing redundant craftsmanship reminders and philosophical elaboration that Claude can infer from concise examples
Add concrete code examples showing how to actually generate PDF/PNG files using specific libraries (e.g., reportlab, PIL, cairo)
Split into multiple files: keep SKILL.md as a brief overview, move philosophy examples to EXAMPLES.md, and canvas generation details to CANVAS.md
Add validation steps: how to verify output dimensions, check text doesn't overlap boundaries, confirm file was generated correctly
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~200 lines with significant redundancy. Repeats 'craftsmanship' and 'masterpiece' concepts excessively as instructed within the skill itself. Contains unnecessary meta-commentary and explains concepts Claude already understands (what a design philosophy is, how to be creative). | 1 / 3 |
Actionability | Provides conceptual guidance and examples of design philosophies, but lacks concrete executable code or specific tool commands. References './canvas-fonts' directory but doesn't show how to use it. No actual PDF/PNG generation code or library usage shown. | 2 / 3 |
Workflow Clarity | Has a clear two-step process (philosophy creation → canvas creation) with numbered steps, but lacks validation checkpoints. No verification steps for checking output quality programmatically, no error recovery guidance, and the 'final step' refinement process is vague. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files for detailed guidance. All content is inline despite being lengthy. Could benefit from separating philosophy examples, canvas creation details, and multi-page instructions into separate referenced files. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- duclm1x1/Dive-Ai
- Commit
20ba150
- 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.