CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

58

1.48x
Quality

39%

Does it follow best practices?

Impact

89%

1.48x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/all-skills/skills/canvas-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

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 both what the skill does and when to use it, earning good marks on completeness. However, it relies on somewhat vague language ('beautiful visual art', 'design philosophy') rather than listing specific concrete capabilities, and the trigger terms could be broader to capture more user phrasings. The use of second person ('You should use') slightly detracts from the expected third-person voice.

Suggestions

Replace vague phrases like 'beautiful visual art' and 'design philosophy' with specific capabilities such as 'Creates posters, illustrations, infographics, and graphic designs with layout composition, color palettes, and typography'.

Expand trigger terms to include common variations like 'illustration', 'graphic', 'infographic', 'flyer', 'banner', 'visual artwork', 'wall art'.

Switch from second person ('You should use this skill') to third person ('Use when...') to match the expected voice convention.

DimensionReasoningScore

Specificity

Names the domain (visual art, design) and some actions (create poster, piece of art, design), but 'beautiful visual art' and 'design philosophy' are vague. It doesn't list multiple concrete specific actions like layout techniques, color palettes, typography, etc.

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 trigger terms like 'poster', 'piece of art', 'design', '.png', '.pdf', and 'static piece', but misses common variations users might say such as 'illustration', 'graphic', 'infographic', 'flyer', 'banner', 'visual', or 'artwork'.

2 / 3

Distinctiveness Conflict Risk

The mention of .png and .pdf output formats and 'static piece' helps distinguish it, but 'design' is very broad and could overlap with UI design, web design, or presentation skills. The phrase 'other static piece' is also quite open-ended.

2 / 3

Total

9

/

12

Passed

Implementation

12%

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 focused on creative philosophy and aesthetic aspiration but critically lacks technical actionability—there are no code examples, library references, or concrete instructions for how Claude should actually generate PDF or PNG files programmatically. The content is extremely verbose and repetitive, particularly around craftsmanship emphasis and minimal-text principles, which are restated in nearly every section. The workflow has a reasonable high-level structure but lacks validation steps and technical specificity.

Suggestions

Add concrete, executable code examples showing how to generate PDF/PNG files (e.g., using reportlab, Pillow, or cairo), including specific commands for shapes, colors, typography, and file output.

Consolidate the repeated craftsmanship and minimal-text instructions into a single, concise principles section rather than restating them throughout every section.

Move the philosophy examples into a separate reference file (e.g., EXAMPLES.md) and link to it from the main skill to reduce the monolithic structure.

Add specific validation steps for the output (e.g., verify file renders correctly, check dimensions, confirm text doesn't overlap) rather than vague instructions to 'double-check.'

DimensionReasoningScore

Conciseness

Extremely verbose and repetitive. The instruction to emphasize craftsmanship is itself repeated numerous times across sections. Concepts like 'minimal text,' 'visual expression,' and 'masterpiece quality' are restated in nearly every section. The skill explains creative philosophy at length rather than providing efficient, actionable instructions. Many paragraphs could be condensed to bullet points.

1 / 3

Actionability

Despite its length, the skill provides no concrete code, commands, or executable examples for actually generating PDF or PNG files. There are no specific library references, no code snippets for canvas creation, no file I/O examples. The guidance is almost entirely abstract and philosophical ('push aesthetics to the frontier,' 'embrace ultimate design freedom') rather than instructing Claude on how to technically produce the output.

1 / 3

Workflow Clarity

There is a discernible multi-step sequence (create philosophy .md → deduce reference → create canvas → refine), and the steps are labeled. However, there are no validation checkpoints, no error recovery steps, and the 'final step' refinement pass lacks concrete criteria for what constitutes 'pristine.' The workflow for the actual technical creation of PDF/PNG files is entirely absent.

2 / 3

Progressive Disclosure

The content is a monolithic wall of text with no references to external files (except a vague mention of './canvas-fonts' directory). All philosophy examples, guidelines, and creation instructions are inlined in a single massive document. There's no separation of concerns—the philosophy examples alone could be a separate reference file, and the canvas creation instructions could be their own document.

1 / 3

Total

5

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
davepoon/buildwithclaude
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.