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

74%

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.

The content is highly actionable with a clear, validated workflow, but it is monolithic and noticeably repetitive across Sections 4, 9, and 14, and it inlines reference material that would benefit from being split into bundled files.

Suggestions

Split the long reference material (Section 10 Reference Vocabulary, Appendix A install commands, Appendix B canonical sources, Appendix C liquid-glass skeleton) into separate reference files under references/ and link them one level deep from SKILL.md.

De-duplicate rules restated across Sections 4, 9, and 14 by stating each ban once in Section 4/9 and having the Section 14 Pre-Flight Check reference those anchors by number instead of restating them.

Populate the Block Library (skills/taste-skill/blocks/) referenced in Section 12 or remove the aspirational file-tree until the blocks exist, so signaled references point to real files.

Dimension	Reasoning	Score
Conciseness	Most content is genuinely novel domain knowledge (specific banned hexes, banned serifs, AI-tell signatures) that earns its tokens, but the same rules are restated three times across Section 4, Section 9, and the Section 14 Pre-Flight Check, which is more than minor padding that could be tightened.	3 / 5
Actionability	Fully executable guidance throughout: real install commands (Appendix A), canonical doc URLs (Appendix B), copy-paste-ready code skeletons (GSAP sticky-stack, horizontal-pan, Motion reveal, liquid-glass CSS), concrete dial tables, and specific Tailwind class recipes covering the common cases.	5 / 5
Workflow Clarity	Clear sequenced workflow (brief inference -> set dials -> pick design system -> build -> Pre-Flight Check) with an explicit validation matrix and feedback loop ('If a single checkbox cannot be honestly ticked, the page is not done. Fix it before delivering.'), plus audit-first checkpoints for redesigns.	5 / 5
Progressive Disclosure	The body is a monolithic ~1200-line SKILL.md with clear section headers but no bundle files (references/scripts/assets absent); content that belongs in separate files (Reference Vocabulary, Block Library schema, Appendices) is inlined, and the only cited file tree (skills/taste-skill/blocks/) is aspirational rather than real.	3 / 5
	Total	16 / 20 Passed

Description

71%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 is specific and distinctive with strong natural trigger terms, but it omits an explicit 'Use when...' clause, so the 'when' is only implied and completeness is capped at 3.

Suggestions

Append an explicit 'Use when...' clause to the description, e.g. 'Use when building or redesigning landing pages, portfolios, or marketing sites, or when the user asks for premium/anti-slop frontend work.'

Fold one or two of the strongest natural triggers from the `triggers` list (e.g. 'premium landing page', 'portfolio redesign') into the description prose so the keywords live where completeness is evaluated.

Add the explicit out-of-speccope contrast ('Not for dashboards, data tables, or product UI') from the body into the description to further sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('landing pages, portfolios, and redesigns') and lists multiple concrete actions ('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'), matching the comprehensive-coverage anchor.	5 / 5
Completeness	It gives a clear 'what' but no explicit 'Use when...' clause; the 'when' is only weakly implied by 'for landing pages, portfolios, and redesigns', which the rubric explicitly caps at 3.	3 / 5
Trigger Term Quality	The description text contains natural terms ('landing pages, portfolios, redesigns', 'anti-slop frontend') and the separate `triggers` list adds user-sayable phrases ('premium landing page', 'portfolio redesign', 'design taste'), giving good coverage, but a few common variations (e.g. file/surface terms, 'web design') are absent.	4 / 5
Distinctiveness Conflict Risk	'Anti-slop frontend' scoped to landing pages/portfolios/redesigns is a clear niche with distinctive triggers and minimal conflict risk; only minor overlap with general frontend skills keeps it below 5.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1234 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: nexu-io/open-design
Path: skills/taste-skill/SKILL.md
Commit: 1a7a23d

Reviewed: about 4 hours 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.