CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

canvas-design

These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/canvas-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

48%Weight 40%Scale 1-5

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

The skill establishes a clear two-phase creative workflow with a genuine validation checkpoint in Export Verification, but it is heavily padded — the craftsmanship and minimal-text directives are each repeated many times — and its core canvas-creation step leans on abstract exhortation rather than concrete mechanism. With no reference files in the bundle, all guidance is inlined in a single long document. Trimming repetition and adding one concrete rendering path would substantially improve it.

Suggestions

State the craftsmanship mandate once in the CRITICAL GUIDELINES section and the minimal-text rule once in ESSENTIAL PRINCIPLES instead of repeating each 4-6 times across the body.

Move the five philosophy examples and the font/licensing guidance into a references/ file (e.g., references/philosophy-examples.md), keeping SKILL.md as a lean overview with well-signaled one-level-deep links.

Add a minimal executable rendering example in Export Verification (e.g., a short Python PDF/PNG snippet with explicit page dimensions) so the canvas step has a concrete starting mechanism.

DimensionReasoningScore

Conciseness

The body is noticeably padded: the craftsmanship mandate is stated four separate times ("stress multiple times that the final work should appear as though it took countless hours", "Repeatedly emphasize... meticulously crafted", "everything screams expert-level craftsmanship"), the minimal-text rule is restated ~6 times ("Minimal text as visual accent", "never lengthy", "never explanatory blocks"), and filler like "Take a moment to gather thoughts and clear the mind" and "Embrace ultimate design freedom and choice" adds no instruction. It does not explain concepts Claude already knows, so it stays above a 1.

2 / 5

Actionability

The philosophy step is concrete ("Name the movement (1-2 words)", "4-6 paragraphs", five worked examples, "Search the `./canvas-fonts` directory") and Export Verification lists specific checks ("inspect text clipping, margins, overlap, contrast and glyph coverage"), but the core canvas-creation step is largely abstract ("craft a masterpiece", "Push aesthetics to the frontier", "Think like a jazz musician") with no concrete rendering mechanism or example. Instruction-only format is not penalized per se, but key executable details are missing.

3 / 5

Workflow Clarity

A clear two-phase sequence is present ("1. Design Philosophy Creation (.md file)" / "2. Express by creating it on a canvas"), followed by an explicit refinement pass ("Take a second pass... refine/polish further") and an Export Verification section acting as a validation checkpoint ("render a preview, inspect text clipping, margins, overlap..."). Not a 5 because the checkpoints are prose-only with no error-recovery loop or executable validation command, and the Multi-Page Option and When to Use sections sit after the final step, slightly muddying the sequence.

4 / 5

Progressive Disclosure

The body has a reasonable ##/### section structure, but everything lives in one ~150-line file with no reference files at all (no references/, scripts/, or assets/ exist in the bundle). The only external pointer, "Search the `./canvas-fonts` directory", cannot be verified and is not clearly signaled as a bundle resource, while content that could be split out (the five philosophy examples, font/licensing guidance) is fully inlined.

3 / 5

Total

12

/

20

Passed

Description

50%Weight 40%Scale 1-5

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 communicates a moderately concrete 'what' (creating visually-expressed design philosophies with .md/.pdf/.png outputs) in a distinctive creative niche, but it omits any 'when to use' trigger guidance and misses the natural vocabulary (poster, artwork, graphic, manifesto) users would actually say. All four dimensions land at the midpoint, making it functional yet under-specified for skill triggering.

Suggestions

Append an explicit trigger clause, e.g.: "Use when the user asks for posters, artwork, visual compositions, design manifestos, or a standalone aesthetic piece as a PDF or PNG."

Add natural synonyms users would say — "poster", "artwork", "graphic", "visual composition" — alongside the existing design/aesthetic vocabulary.

Name the concrete actions in the description itself (write a design philosophy manifesto, render a single-page visual canvas, verify exports) rather than only naming the domain and formats.

DimensionReasoningScore

Specificity

The description names the domain ("creating design philosophies - aesthetic movements") and one-two actions ("EXPRESSED VISUALLY", "Output only .md files, .pdf files, and .png files"), but does not list several specific actions like writing a manifesto or producing a single-page visual composition. It sits between the generic "Processes PDF files" level and the several-actions level.

3 / 5

Completeness

The 'what' is reasonably clear ("creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY", with explicit output formats), but the 'when' is entirely absent — there is no "Use when..." or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is more than vague.

3 / 5

Trigger Term Quality

Relevant keywords exist ("design", "aesthetic", "visual", and the file extensions ".md", ".pdf", ".png"), but the natural phrases a user would say for this skill — "poster", "artwork", "graphic", "design manifesto", "visual composition" — are absent. Good enough to rise above generic, but common variations are missing.

3 / 5

Distinctiveness Conflict Risk

"Design philosophies / aesthetic movements expressed visually" is a fairly niche framing, but with no 'when' guidance and only generic visual-design trigger words, it could overlap with other design, presentation, or image-generation skills. It is more specific than "Helps with document files" but lacks the distinct triggers needed for a 4-5.

3 / 5

Total

12

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

sickn33/agentic-awesome-skills

Path

skills/canvas-design/SKILL.md

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.