design-taste-frontend

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/taste-skill/SKILL.md

Quality

Content

77%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.

An extraordinarily actionable, well-sequenced skill with executable skeletons and a rigorous validation checklist. Its weakness is progressive disclosure: it is one giant file with no real bundle files, and the promised block library is unpopulated.

Suggestions

Move the Reference Vocabulary (Section 10) and the Appendices (install commands, canonical links, Liquid Glass skeleton) into separate reference files the SKILL.md points to one level deep, shrinking the main body.

Either populate the Block Library with real per-block .md files or mark Section 12 clearly as a stub so the reader does not expect implementations that are not there.

Trim repeated restatements of the same bans (e.g. the em-dash ban appears in 4.1/4.10/9.G/14 and the AI-purple ban in 4.2/9.A/14) to one canonical statement plus short cross-references.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and mostly earns its tokens, but at ~1200 lines it includes some restatement and emphatic elaboration (repeated BANNED/capitalised directives restating the same ban multiple ways) that could be tightened.	3 / 5
Actionability	It ships fully executable, copy-paste-ready code skeletons (GSAP sticky-stack, horizontal-pan, Motion reveal stagger, Liquid Glass CSS), concrete install commands, exact Tailwind classes, and a mechanical Pre-Flight checklist covering the common cases.	5 / 5
Workflow Clarity	Multi-step processes are explicitly sequenced with validation checkpoints: brief inference -> dials -> design-system map -> directives -> pre-flight, plus the redesign audit-before-touching flow and a binary, mandatory final checklist that enforces feedback loops before shipping.	5 / 5
Progressive Disclosure	Internal sectioning is thorough and cross-referenced, but the file is a monolithic 1200-line wall; the promised Block Library is described as not-yet-populated, and there are no actual reference/bundle files to offload the dense appendices and vocabulary, so structure that should be separate is inline.	3 / 5
	Total	16 / 20 Passed

Description

66%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.

A vivid, capability-rich description that signals a sharp niche and excludes adjacent domains. Its main gap is the missing explicit Use when trigger clause, which caps completeness at 3.

Suggestions

Add an explicit trigger clause (e.g. "Use when building or redesigning landing pages, portfolios, or marketing sites") so the when is stated, not implied.

List a couple of natural synonyms or file tokens users might say ("homepage", "one-pager", ".tsx marketing page") to lift trigger-term coverage toward 5.

Dimension	Reasoning	Score
Specificity	The description lists several concrete capabilities (reads the brief, infers design direction, ships non-templated interfaces, applies real design systems, audit-first redesigns, pre-flight check), naming the domain and multiple specific actions.	4 / 5
Completeness	The what is clearly stated (anti-slop frontend skill with concrete sub-actions), but the when/trigger guidance is only weakly implied; there is no explicit Use when clause naming the situations that should activate it.	3 / 5
Trigger Term Quality	Natural user-facing terms (landing pages, portfolios, redesigns) are present with good coverage, but it omits common synonyms and file/extension tokens, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (marketing/landing/portfolio redesigns) and explicitly excludes dashboards and data tables, leaving only minor overlap risk with general frontend skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1207 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Leonxlnx/taste-skill
Path: skills/taste-skill/SKILL.md
Commit: ccbc156

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

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.