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 ...
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill canvas-design67
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 95%
↑ 1.90xAgent success when using this skill
Validation for skill structure
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 covers both what the skill does and when to use it, earning strong marks for completeness. However, it lacks specificity in concrete actions and could benefit from more diverse trigger terms to capture the full range of user requests for visual content creation.
Suggestions
Add more specific concrete actions like 'compose layouts, apply typography, generate illustrations, design infographics'
Expand trigger terms to include common variations: 'graphic', 'illustration', 'banner', 'flyer', 'visual content', 'artwork'
Clarify distinction from other design skills by emphasizing 'static visual art' vs UI/web design
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (visual art, .png/.pdf) and mentions some actions (create poster, art, design), but lacks comprehensive specific actions like 'compose layouts', 'apply color theory', or 'generate illustrations'. | 2 / 3 |
Completeness | Clearly answers both what ('Create beautiful visual art in .png and .pdf documents using design philosophy') 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', 'art', 'design'), but missing common variations like 'graphic', 'illustration', 'banner', 'flyer', 'visual', 'artwork', or 'image creation'. | 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 '.png and .pdf' output formats help distinguish it somewhat. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily philosophical and aspirational but lacks the concrete, executable guidance needed for consistent results. The extensive repetition about 'craftsmanship' and 'masterpiece quality' wastes tokens without providing actionable steps. The workflow is present but would benefit from specific validation checkpoints and concrete code examples for PDF/PNG generation.
Suggestions
Reduce verbosity by 60%+ - remove repeated exhortations about 'craftsmanship' and 'museum quality' and replace with specific, measurable criteria (e.g., 'margins minimum 0.5 inches', 'maximum 3 colors')
Add executable code examples for PDF/PNG generation using specific libraries (e.g., reportlab, PIL/Pillow, or cairo)
Include a concrete validation checklist: 'Before finalizing: [ ] All elements within margins [ ] No overlapping text [ ] Color palette ≤ N colors [ ] Font files loaded successfully'
Move the philosophy examples to a separate EXAMPLES.md file and link to it, keeping SKILL.md as a concise overview
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive repetition of concepts like 'craftsmanship,' 'masterpiece,' and 'museum quality.' Many paragraphs explain abstract concepts Claude already understands (what visual design is, what art movements are). The document could be reduced by 60-70% without losing actionable content. | 1 / 3 |
Actionability | Provides some concrete guidance (output .md/.pdf/.png files, use ./canvas-fonts directory, two-step process) but lacks executable code examples. Instructions are largely abstract and philosophical rather than specific commands or copy-paste ready implementations. | 2 / 3 |
Workflow Clarity | Has a clear two-step sequence (philosophy creation → canvas creation) with a refinement pass, but lacks validation checkpoints. No explicit verification steps for checking output quality, file validity, or error recovery. The 'FINAL STEP' refinement is vague about what constitutes 'pristine.' | 2 / 3 |
Progressive Disclosure | Content is monolithic with everything in one file. References to ./canvas-fonts directory exist but no links to separate reference files for examples, templates, or detailed guidance. The philosophy examples could be in a separate file. Structure exists but organization could be improved. | 2 / 3 |
Total | 7 / 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 | |
- 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.