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.

48

Quality

60%

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 ./plugins/antigravity-bundle-web-designer/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 communicates a coherent creative workflow with a genuine refinement loop, but it buries that workflow under heavy repetition of the same craftsmanship and minimal-text mandates. Its weakest point is executability: nothing tells Claude how to actually render the .pdf/.png, and the one resource it points to (./canvas-fonts) is missing.

Suggestions

Consolidate the craftsmanship and minimal-text mandates (currently stated in CRITICAL GUIDELINES, ESSENTIAL PRINCIPLES, CANVAS CREATION, and FINAL STEP) into a single principles section, cutting the body roughly in half.

Add concrete rendering guidance - e.g. a short code snippet or reference file showing how to generate the .pdf/.png (matplotlib, reportlab, or HTML-to-print) - and either ship the './canvas-fonts' directory or remove the reference to it.

Remove the simulated user quote in FINAL STEP ('The user ALREADY said...') and the 'gather thoughts and clear your mind' filler; state the refinement pass as a plain numbered step with its checks as a checklist.

DimensionReasoningScore

Conciseness

The body is noticeably verbose through pervasive repetition: craftsmanship exhortations ('meticulously crafted', 'countless hours', 'top of their field') appear in at least four sections, 'minimal text' guidance is restated roughly six times, and filler like 'Take a moment to gather thoughts and clear your mind' pads the canvas section. It is not anchor 1 because it does not explain concepts Claude already knows; it is below anchor 3 because redundancy is systematic rather than occasional.

2 / 5

Actionability

There is concrete guidance (numbered two-step workflow, 'Name the movement (1-2 words)', '4-6 paragraphs', five worked philosophy examples, explicit output formats), but the actual production of the .pdf/.png is unspecified - no code, tool, or rendering approach - and the referenced './canvas-fonts' directory does not exist in the bundle. This matches 'some concrete guidance but incomplete; missing key details'.

3 / 5

Workflow Clarity

The sequence is clear and well-ordered: philosophy (.md) -> deduce the subtle reference -> canvas creation (.pdf/.png) -> a FINAL STEP second-pass refinement ('Take a second pass... refine/polish further') with explicit checks ('Double-check that nothing overlaps, formatting is flawless, every detail perfect'). It is not 5 because the checkpoints are imperative exhortations rather than an explicit validate-fix-retry loop, and there is no concrete output-verification step.

4 / 5

Progressive Disclosure

The body has reasonable section structure and header navigation, but it is a single ~127-line file with everything inlined, no one-level-deep references at all, and a dangling reference to a './canvas-fonts' directory that is not part of the bundle. It sits between 'some structure but could be better organized' (3) and 'minimal structure / inlined content' (2); the organized headers keep it at 3.

3 / 5

Total

12

/

20

Passed

Description

53%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 states a distinct niche and concrete output formats, but it lacks any 'when to use' trigger guidance and misses the natural vocabulary users would employ to invoke the skill. It reads more like a task preamble than a skill description.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a design philosophy, aesthetic direction, art poster, or visually expressive single-page artwork.'

Include natural trigger terms and synonyms users would say, such as 'poster', 'art print', 'visual identity', 'design language', or 'mood board'.

Recast the opening from 'These are instructions for...' into third-person capability statements ('Creates design philosophies and expresses them as single-page .pdf/.png artwork').

DimensionReasoningScore

Specificity

The description names its domain ('creating design philosophies - aesthetic movements') and concrete output formats ('.md files, .pdf files, and .png files'), but lists only one or two actions rather than the several specific actions of anchor 4. It is clearly more concrete than the domain-only anchor 2.

3 / 5

Completeness

The 'what' is reasonably clear (creates design philosophies expressed visually, with explicit output formats), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not score 4 because 'when' is entirely absent rather than just imprecise.

3 / 5

Trigger Term Quality

It contains some relevant keywords with file extensions ('design philosophies', 'aesthetic movements', 'VISUALLY', '.md', '.pdf', '.png'), but misses the natural phrases a user would actually say such as 'poster', 'art print', 'visual identity', or 'design language'. This matches anchor 3: relevant keywords present, common variations missing.

3 / 5

Distinctiveness Conflict Risk

'Design philosophies / aesthetic movements expressed visually' is a clear niche that is easily distinguishable from document-processing or data-analysis skills, with only minor overlap risk from generic mentions of .pdf/.png output. Not 5 because the output-format wording could weakly overlap with PDF or image-generation skills.

4 / 5

Total

13

/

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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/antigravity-bundle-web-designer/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.