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.

93

1.75x
Quality

39%

Does it follow best practices?

Impact

98%

1.75x

Average score across 10 eval scenarios

SecuritybySnyk

Failed to scan

The risk profile of this skill

Optimize this skill with Tessl

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

Quality

Content

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 motivational language but critically lacks technical actionability — there are no code examples, library references, or concrete commands for generating PDF/PNG output. The content is extremely verbose and repetitive, particularly around craftsmanship emphasis, which is ironically stated as something to repeat deliberately. The workflow has a reasonable high-level structure but lacks validation steps and concrete implementation details.

Suggestions

Add concrete, executable code examples showing how to generate PDF and PNG files (e.g., using reportlab, Pillow, or cairo), including font loading from `./canvas-fonts`.

Eliminate repetitive motivational language about craftsmanship — state it once clearly rather than repeating it 6+ times across sections.

Extract the philosophy examples into a separate reference file (e.g., PHILOSOPHY_EXAMPLES.md) to reduce the main skill's length and improve progressive disclosure.

Add validation checkpoints to the workflow, such as verifying the output file renders correctly, checking that text doesn't overlap, and confirming canvas dimensions before final output.

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. Much of this content is motivational padding rather than operational guidance.

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 visual output.

1 / 3

Workflow Clarity

There is a discernible multi-step sequence: 1) Create design philosophy (.md), 2) Deduce subtle reference, 3) Create canvas (.pdf/.png), 4) Refine. However, there are no validation checkpoints, no error recovery steps, and the 'final step' refinement pass lacks concrete criteria for what constitutes 'done.' The sequence is present but lacks the rigor needed for reliable execution.

2 / 3

Progressive Disclosure

The content is a monolithic wall of text with no references to external files (despite mentioning a `./canvas-fonts` directory). Everything is inline in one massive document. The philosophy examples, canvas creation instructions, multi-page options, and refinement steps could all be separate referenced files. No bundle files are provided to support the content.

1 / 3

Total

5

/

12

Passed

Description

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 'Use when' clause with some trigger terms. However, it relies on vague language like 'beautiful visual art' and 'design philosophy' rather than listing specific concrete capabilities. The trigger terms cover some common user phrases but miss several natural variations, and the scope is broad enough to potentially conflict with other design-related skills.

Suggestions

Replace vague phrases like 'beautiful visual art' and 'design philosophy' with specific concrete actions such as 'compose layouts, select color palettes, arrange typography, create illustrations'.

Expand trigger terms to include natural variations users might say: 'illustration', 'graphic', 'infographic', 'flyer', 'banner', 'wall art', 'visual artwork'.

Use third person voice consistently ('Creates visual art...') instead of second person ('You should use this skill') to align with description conventions.

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 specific concrete actions like layout techniques, color palette selection, or typography work.

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 terms users would say like 'poster', 'piece of art', 'design', '.png', '.pdf', but misses common variations like 'illustration', 'graphic', 'infographic', 'flyer', 'banner', 'visual', 'artwork', or 'image creation'.

2 / 3

Distinctiveness Conflict Risk

Somewhat specific with the focus on static visual art and .png/.pdf output, but 'design' is broad and could overlap with UI design, web design, or presentation skills. The phrase 'other static piece' is quite open-ended.

2 / 3

Total

9

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
ComposioHQ/awesome-claude-skills
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.