CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

76%

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

The canonical home for this skill is design-taste-frontend in Leonxlnx/taste-skill

SKILL.md
Quality
Evals
Security

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 exceptionally actionable, well-sequenced design skill with real code skeletons and a rigorous validation checklist, but it is over-long for a SKILL.md with notable cross-section repetition and an unpopulated Block Library whose referenced files are absent. Splitting the appendices and block implementations into real reference files would lift the structure score.

Suggestions

Move Appendix A (install commands), Appendix B (canonical sources), and Appendix C (liquid-glass skeleton) into separate reference files under references/ and link to them, shrinking the inlined SKILL.md body.

Populate the blocks/ tree referenced in Section 12 (e.g. blocks/hero/asymmetric-split.md) or remove the forward reference until those files exist, so navigation is not a dead end.

De-duplicate rules restated between the body and the Section 14 Pre-Flight Check - keep the pre-flight as a short pointer list that cites sections rather than re-stating each rule in full.

DimensionReasoningScore

Conciseness

The ~1182-line body is dense with high-signal domain rules Claude does not already know (no basic-concept padding), but rules are repeated across sections - the em-dash ban recurs in 4.10, 9.F, 9.G and the pre-flight; eyebrow and palette rules are restated verbatim - and the pre-flight re-lists ~60 items already covered, so it could be tightened well beyond "minor".

3 / 5

Actionability

Fully executable guidance throughout: real install commands (Appendix A), copy-paste TSX skeletons with correct imports (StickyStack, HorizontalPan, RevealStagger), a complete labeled liquid-glass CSS approximation, and concrete Tailwind classes and library import paths covering the common cases.

5 / 5

Workflow Clarity

A clear sequenced workflow - brief inference (0.B one-liner) → dials → design-system map → directives → redesign protocol (11 has audit-then-ordered-levers) - terminating in an explicit validation checklist with a feedback loop ("If a single checkbox cannot be honestly ticked, the page is not done. Fix it before delivering.").

5 / 5

Progressive Disclosure

Clear numbered section structure, but everything is inlined in one monolithic file - appendices (install commands, canonical sources, liquid-glass skeleton) clearly belong in separate reference files - and the Block Library (Section 12) references a blocks/ tree that does not exist, an unfulfilled multi-level forward reference.

3 / 5

Total

16

/

20

Passed

Description

75%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, uses natural trigger terms, and names a clear niche with both what and when, though it lacks an explicit "Use when..." clause and a few natural synonyms. It is well above the vague baseline but stops short of the comprehensive, copy-paste-ready exemplars.

DimensionReasoningScore

Specificity

Lists several concrete actions - "reads the brief, infers the right design direction, and ships interfaces", "audit-first on redesigns, strict pre-flight check" - but they stay at a directive level rather than the fully concrete verb set of a 5.

4 / 5

Completeness

Both what ("ships interfaces that do not look templated", "Real design systems when applicable") and when ("for landing pages, portfolios, and redesigns") are present, but the when is embedded rather than an explicit "Use when..." clause, so it falls just below 5.

4 / 5

Trigger Term Quality

Strong natural trigger terms - "landing pages, portfolios, and redesigns", "frontend" - that users would actually say; missing synonyms like "website", "homepage", or "marketing site" that keep it off 5.

4 / 5

Distinctiveness Conflict Risk

The "anti-slop" / "do not look templated" framing carves a clear niche for landing/portfolio/redesign work; minor overlap risk remains with a generic frontend or web-design skill, preventing a 5.

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1208 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
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.