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.

94

1.75x
Quality

Does it follow best practices?

Impact

98%

1.75x

Average score across 10 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill lays out a clear two-phase creative workflow with strong stylistic direction, but it is verbose, lacks any executable/technical guidance for actually producing .pdf/.png output, and relies on a monolithic single file with a missing referenced font directory.

Suggestions

Add concrete, actionable guidance for producing output: name specific libraries/tools (e.g. reportlab or Pillow for .pdf/.png), and give a minimal copy-pasteable rendering skeleton so the canvas step is executable rather than abstract.

Add an explicit validation feedback loop (e.g. render then verify dimensions/margins/overlap programmatically, fix, re-render) so the workflow has real checkpoints instead of soft reminders.

Tighten the repeated craftsmanship and 'minimal text' exhortations into a single stated principle, and split the five philosophy examples into a referenced file to reduce token cost and enable progressive disclosure.

DimensionReasoningScore

Conciseness

The body has real directional content but is heavily padded with repeated exhortations (craftsmanship is stressed in 4-5 places, 'minimal text' restated 5+ times, 'visual not text' repeated), and the CRITICAL GUIDELINES even instructs repetition; it could be tightened significantly, matching the 'mostly efficient but includes unnecessary explanation' anchor rather than the lean anchor.

2 / 3

Actionability

Guidance is almost entirely abstract ('express it on a canvas', 'push aesthetics to the frontier') with no executable code, no rendering libraries (e.g. reportlab, PIL), and no concrete commands; it describes and coaches rather than instructing, matching the vague/abstract anchor.

1 / 3

Workflow Clarity

A clear two-step sequence (Design Philosophy Creation, Canvas Creation) plus a FINAL STEP refinement pass is present, but validation/verification is only soft and implicit ('Check carefully that nothing overlaps', 'Double-check that formatting is flawless') with no real validate-fix-retry feedback loop, matching the 'steps listed but validation gaps' anchor.

2 / 3

Progressive Disclosure

Sections are organized with clear headers, but everything lives in one ~130-line monolithic SKILL.md with no split reference files, and the one referenced path ('the ./canvas-fonts directory') does not exist as a bundle; content such as the five philosophy examples could be separated, matching the 'some structure but content that should be separate is inline' anchor.

2 / 3

Total

7

/

12

Passed

Description

80%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states capability and explicit use-when triggers with natural user terms and a distinct niche. Its main weakness is the second-person voice ('You should use this skill'), which violates the third-person guideline and lowers the specificity score.

Suggestions

Rewrite in third person to avoid the 'You should use this skill' phrasing (e.g., 'Use when the user asks to create a poster, piece of art, design, or other static piece'), which would restore the specificity score.

List a few more concrete, distinct actions (e.g., 'compose layouts, render vector graphics, typeset labels') to strengthen the specificity dimension beyond the single 'create' verb.

DimensionReasoningScore

Specificity

Names the domain (.png/.pdf, poster, art) and a couple of high-level actions ('Create beautiful visual art', 'create original visual designs'), but these are variations of one action rather than a comprehensive list; additionally the second-person phrasing 'You should use this skill' triggers the voice penalty of -1, dropping it from 2 to 1.

1 / 3

Completeness

It answers both what ('Create beautiful visual art in .png and .pdf documents using design philosophy') and when with an explicit trigger clause ('You should use this skill when the user asks to create a poster, piece of art, design, or other static piece').

3 / 3

Trigger Term Quality

Natural user-facing terms are well covered: 'poster', 'piece of art', 'design', 'static piece', plus '.png' and '.pdf', matching the anchor for good coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

The niche (static visual art / poster / design creation in .png and .pdf) is distinct with specific triggers unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

10

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
boisenoise/skills-collections
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.