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

81%

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

Quality

Content

77%

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

The content is exceptionally actionable and workflow-clear, with real commands, doc links, copy-paste code skeletons, and a rigorous pre-flight checklist. Its weaknesses are conciseness (massive duplication between Sections 4, 9, and 14) and progressive disclosure (everything lives in one 1200-line file with no actual bundle files).

Suggestions

De-duplicate the body: the Section 14 pre-flight checklist restates nearly every rule from Sections 4 and 9. Either collapse it into cross-references ('verify Section 4.7 hero rules') or remove the inline rule text so each rule lives in one place.

Move the reference-heavy material into bundle files under references/ (e.g. Appendix A install commands, Appendix B canonical URLs, Appendix C liquid-glass CSS) and keep SKILL.md as an overview that links one level deep, which would also fix the missing Block Library files.

Tighten Section 9 ('AI Tells'), which substantially overlaps Section 4's design-engineering directives; merge the overlapping rules and keep only the net-new tells.

Dimension	Reasoning	Score
Conciseness	The body is specialized expertise rather than basic-concept padding, but at ~1200 lines it is extremely verbose with heavy duplication: Section 14's ~60-checkbox pre-flight list restates rules from Sections 4-9 and Section 9 overlaps Section 4, so it is not lean.	2 / 3
Actionability	Highly actionable with real npm install commands (Appendix A), canonical doc URLs (Appendix B), complete copy-paste-ready code skeletons (Sections 5.A-5.C, Appendix C), and concrete Tailwind classes plus exact banned hex values.	3 / 3
Workflow Clarity	A clear sequenced workflow (Section 0 brief inference through Section 14 pre-flight) with an explicit comprehensive validation checklist and a validate-fix-redeliver feedback loop ('If a single checkbox cannot be honestly ticked, the page is not done').	3 / 3
Progressive Disclosure	Well-organized into numbered sections and appendices, but it is a monolithic single file with no bundle files present (references/scripts/assets absent); content that should be split (appendices, Section 10 vocabulary, Section 12 Block Library) is inline, and the Block Library references files like blocks/hero/asymmetric-split.md that do not exist.	2 / 3
	Total	10 / 12 Passed

Description

85%

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, clearly stating both the capability set and the page-type scope it targets. Its weakest point is trigger-term coverage, which lists the core page kinds but omits common variations users would naturally say.

Suggestions

Add common natural-language trigger terms users would actually say, such as 'website', 'homepage', 'web design', or 'UI redesign', alongside the existing 'landing pages, portfolios, and redesigns'.

Consider adding an explicit 'Use when the user asks for a landing page, portfolio, or site redesign' clause to make the trigger guidance unmistakable rather than scope-implied.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('reads the brief, infers the right design direction, and ships interfaces', 'Real design systems when applicable, audit-first on redesigns, strict pre-flight check'), matching the anchor for several specific concrete actions.	3 / 3
Completeness	Answers what (multiple actions) and when explicitly via 'for landing pages, portfolios, and redesigns', which is equivalent explicit trigger guidance and therefore not capped at 2.	3 / 3
Trigger Term Quality	Natural terms appear ('landing pages, portfolios, and redesigns') but common variations a user would say ('website', 'homepage', 'web design', 'UI redesign') are missing, so coverage is not comprehensive.	2 / 3
Distinctiveness Conflict Risk	A clear niche ('Anti-slop frontend skill... do not look templated') with distinct, narrow triggers makes it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 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: a2ba3ee

Reviewed: about 14 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.