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.

47

Quality

50%

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

35%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 communicates a clear artistic vision and a legible two-phase workflow, but it spends most of its token budget on repeated motivational exhortations while leaving the executable core (how to produce the .pdf/.png) unspecified, and it references a bundle directory that is absent. Trimming the repetition and adding one concrete rendering path would substantially raise quality.

Suggestions

State the craftsmanship requirement once instead of six-plus times — collapse the repeated 'meticulously crafted / countless hours / top of the field' passages (lines 49, 84, 115, 123) into a single principle, cutting a large fraction of the body.

Add concrete rendering guidance for the canvas step (e.g., a named library or approach for generating .pdf/.png output, canvas dimensions, and margin/overlap check commands), since no executable detail currently exists for the hardest phase.

Fix or remove the dangling `./canvas-fonts` reference (the directory is not in the bundle), and consider moving the five philosophy examples into a references/ file to keep SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

The body is noticeably padded: it explicitly instructs repeating craftsmanship phrases ("Emphasize craftsmanship REPEATEDLY... repeat phrases like 'meticulously crafted'"), restates the craftsmanship exhortation in at least six places, and includes filler like "Take a moment to gather thoughts and clear the mind" plus roughly ten CRITICAL/IMPORTANT flags. It is not a 1 because genuine actionable guidance (output formats, philosophy length, examples) is mixed in.

2 / 5

Actionability

The skill names its deliverables (.md philosophy, .pdf/.png canvas) and provides five philosophy examples, but gives no concrete guidance for the hardest step — actually rendering the canvas (no tool, library, command, or code), and its only concrete pointer ("Search the `./canvas-fonts` directory") references a directory that does not exist in the bundle. It is not a 1 because the philosophy-creation step is reasonably concretely specified.

2 / 5

Workflow Clarity

The two-step sequence is stated upfront ("1. Design Philosophy Creation (.md file) 2. Express by creating it on a canvas") and sections follow that order, with a FINAL STEP second-pass refinement. However, validation is only implicit ("Check carefully that all text, graphics, and visual elements have breathing room") with no explicit checkpoint or fix-and-retry loop, matching anchor 3 rather than 4.

3 / 5

Progressive Disclosure

The single file has clear section headers and a coherent order, so it is not a monolithic wall, but nothing is split out — the five philosophy examples (roughly 20 lines) and the canvas-creation prose could live in reference files — and the only bundle path mentioned (`./canvas-fonts`) is broken since no such directory exists in the skill. This sits between anchors 2 and 3; the existing headers and single-level structure keep it at 3.

3 / 5

Total

10

/

20

Passed

Description

65%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 answers both 'what' and 'when' with a clear, explicit trigger clause and natural user vocabulary, but its capability statement is generic and it violates the third-person voice requirement, costing it specificity. Tightening the 'what' into concrete deliverables and dropping the second-person phrasing would move it toward the top anchors.

Suggestions

Rewrite in third person to remove 'You should use this skill when...' (e.g., 'Use when the user asks to create...'), which currently costs a specificity point under the rubric.

Replace vague capability language ('beautiful visual art', 'using design philosophy') with concrete deliverables, e.g., 'Creates a design-philosophy manifesto (.md) and expresses it as a one-page poster or art piece (.pdf/.png)'.

Add a few common trigger synonyms such as 'artwork', 'illustration', or 'flyer' to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain and roughly two concrete actions ("Create beautiful visual art in .png and .pdf documents", "Create original visual designs"), which matches anchor 3, but the explicit second-person voice ("You should use this skill when...") triggers the rubric's 1-point specificity penalty, landing it at anchor 2's territory. It is not a 1 because real actions and output formats are stated; it does not reach 3 because 'beautiful' and 'using design philosophy' are vague and the penalty applies.

2 / 5

Completeness

Both parts are present: what ("Create beautiful visual art in .png and .pdf documents") and an explicit when ("You should use this skill when the user asks to create a poster, piece of art, design, or other static piece"). It is not a 5 because the 'what' leans on the vague phrases 'beautiful' and 'using design philosophy' rather than concrete capability statements.

4 / 5

Trigger Term Quality

Natural user phrasing is present: 'create a poster, piece of art, design, or other static piece' plus file extensions '.png' and '.pdf'. It falls short of anchor 5 because common synonyms like 'artwork', 'illustration', 'flyer', or 'logo' are missing.

4 / 5

Distinctiveness Conflict Risk

The static visual-art niche (posters, art pieces, .png/.pdf outputs) is mostly distinct from document- and presentation-editing skills, with 'static piece' helping separate it from interactive work. Minor overlap risk remains with general document-creation or branding skills, so it does not reach anchor 5.

4 / 5

Total

14

/

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
netease-youdao/LobsterAI
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.