CtrlK
BlogDocsLog inGet started
Tessl Logo

web-prototype-taste-soft

Apple-tier soft web prototype. Silver/cream canvas, double-bezel cards, button-in-button CTAs, generous squircle radii, spring motion, ambient mesh. Distilled from Leonxlnx/taste-skill `soft-skill` + sections 4–8 of `taste-skill`.

57

Quality

65%

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 ./design-templates/web-prototype-taste-soft/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%Weight 40%Scale 1-3

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

The body is an excellent, token-efficient design spec with highly actionable concrete values and a verification checklist. Its main weakness is a broken reference to a non-existent example.html and the absence of an explicit ordered build workflow.

Suggestions

Either ship the referenced example.html template or remove the 'See example.html' reference so progressive disclosure is not broken.

Add a short ordered build sequence (scaffold -> components -> motion -> pre-flight) with a validate/fix/retry loop for the pre-flight checks.

Move the natural trigger terms out of the intro paragraph and into a labeled 'Use when' section for discoverability.

DimensionReasoningScore

Conciseness

The body is dense and lean — exact values, Tailwind classes, and concise lists with no explanation of concepts Claude already knows; every token earns its place.

3 / 3

Actionability

Provides concrete, copy-paste-ready guidance: exact radii ('border-radius: 28px-40px'), shadow values ('0 20px 40px -15px rgba(0,0,0,0.05)'), cubic-bezier curves, and a runnable pre-flight checklist.

3 / 3

Workflow Clarity

A pre-flight checklist supplies a verification step, but the body is organized as topical rules rather than an ordered build sequence, and there is no validate->fix->retry feedback loop.

2 / 3

Progressive Disclosure

Sections are well-organized and the single external reference ('See example.html in this directory') is clearly signaled one level deep, but that file does not exist in the bundle, so the disclosure promise is unfulfilled.

2 / 3

Total

10

/

12

Passed

Description

50%Weight 40%Scale 1-3

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 conveys a vivid, specific aesthetic but reads as a feature list for an artifact rather than a statement of the skill's actions and trigger conditions. It lacks an explicit 'Use when' trigger clause, capping its completeness.

Suggestions

Lead with a third-person action verb ('Builds Apple-tier soft web prototypes with...') instead of a noun phrase.

Add an explicit trigger clause, e.g. 'Use when briefs ask for Apple-like, Linear-tier, premium consumer, or calm SaaS finish.'

Surface the natural trigger terms currently buried in the body into the description itself.

DimensionReasoningScore

Specificity

Names the domain ('Apple-tier soft web prototype') and many concrete aesthetic specifics ('Silver/cream canvas, double-bezel cards, button-in-button CTAs, generous squircle radii, spring motion, ambient mesh'), but these describe the artifact's properties rather than the concrete actions the skill performs.

2 / 3

Completeness

Clearly states what the skill produces, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 2 per the judging guidelines.

2 / 3

Trigger Term Quality

'Apple-tier' and 'soft web prototype' are natural-ish terms, but most of the phrasing is design jargon; the natural trigger phrasing users would say ('Apple-like', 'premium consumer', 'calm SaaS') appears in the body rather than the description.

2 / 3

Distinctiveness Conflict Risk

The aesthetic niche is fairly distinctive (double-bezel, button-in-button CTAs), but trigger guidance is thin and it explicitly references a parent taste-skill, so it could overlap with sibling design skills.

2 / 3

Total

8

/

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
nexu-io/open-design
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.