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

75%

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 ./.agents/skills/design-taste-frontend/SKILL.md

Quality

Content

71%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.

A highly actionable, well-sequenced body of dense design guidance that earns top marks for executability. Its weaknesses are repetition that hurts token efficiency and a monolithic structure with separable reference material inlined rather than split into bundle files.

Suggestions

Split the appendices (Appendix A install commands, Appendix B canonical URL lists, Appendix C Liquid Glass skeleton) into separate reference files under references/ and link to them one level deep, reducing the SKILL.md body to an overview.

De-duplicate the Section 14 pre-flight checklist against Sections 4 and 9 by referencing the rules rather than restating them verbatim, or consolidate the AI-tells rules so each rule appears in only one canonical place.

Add intermediate validation checkpoints between the major workflow steps (e.g., after dial-setting and after design-system selection) rather than only the terminal pre-flight check.

Dimension	Reasoning	Score
Conciseness	Content is dense and avoids explaining concepts Claude already knows, but at ~1100 lines it repeats material (Section 9 rehashes Section 4; the Section 14 pre-flight checklist restates earlier rules verbatim) that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready, executable guidance throughout: concrete Tailwind classes, GSAP/Motion code skeletons, specific CSS values, named packages, and real install commands covering the common cases.	5 / 5
Workflow Clarity	A clear sequenced process (brief inference → dials → design system → directives → redesign protocol → pre-flight check) with a terminal validation checkpoint, but it lacks intermediate checkpoints between steps.	4 / 5
Progressive Disclosure	Well-structured with numbered sections, but it is a monolithic single file with no bundle references; the appendices (install commands, canonical URL lists, Liquid Glass CSS skeleton) are reference material that clearly belongs in separate files.	3 / 5
	Total	15 / 20 Passed

Description

78%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 strong, specific description that names a clear niche and several concrete actions with explicit trigger domains. Its main gap is the absence of a literal 'Use when...' trigger clause, which keeps completeness and trigger-term quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists several 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'), with only minor gaps versus the comprehensive 5-anchor.	4 / 5
Completeness	A clear 'what' is paired with explicit trigger domains ('for landing pages, portfolios, and redesigns') serving as equivalent trigger guidance, though it lacks a literal 'Use when...' clause that would push it to 5.	4 / 5
Trigger Term Quality	Natural user-facing terms ('landing pages, portfolios, redesigns', 'frontend', 'design') are well covered; a few synonyms or surface variants are missing, so it sits just below the comprehensive 5-anchor.	4 / 5
Distinctiveness Conflict Risk	A clear niche (anti-slop frontend for landing pages/portfolios/redesigns) with distinct triggers and minimal overlap with other skill classes.	5 / 5
	Total	17 / 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 (1104 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: simstudioai/sim
Path: .agents/skills/design-taste-frontend/SKILL.md
Commit: 7945b29

Reviewed: 3 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.