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.

56

Quality

66%

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 ./skills/taste-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

66%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.

This is an exceptionally actionable, well-sequenced design rulebook with a strong final validation checklist, but it fails progressive disclosure entirely (one monolithic file, no reference bundle, appendices inlined) and pays for it in conciseness through heavy cross-section repetition. Splitting appendices, the vocabulary catalog, and the AI-tells list into reference files and de-duplicating rules restated in Sections 4, 9, and 14 would fix both weaknesses at once.

Suggestions

Move Appendix A (install commands), Appendix B (canonical links), Appendix C (liquid-glass CSS), and the Section 10 vocabulary catalog into references/ files (e.g. references/design-systems.md, references/ai-tells.md), keeping SKILL.md as a lean overview with one-level-deep pointers.

De-duplicate rules restated across Sections 4, 9, and 14: state each rule once in its home section and have the pre-flight checklist reference the section number only, instead of re-describing the rule.

Actually create the blocks/ directory defined in Section 12 (or remove the placeholder contract) so the promised progressive-disclosure structure exists rather than being declared but absent.

DimensionReasoningScore

Conciseness

The 1233-line body is noticeably verbose: the same rules are stated multiple times (em-dash ban in 4.10, 9.F, 9.G, and the pre-flight list; eyebrow rules in 4.7, 9.F, and 14; fake-screenshot bans in 4.8, 9.E, and 9.F), and ~220 lines of appendices (install commands, canonical links, a full CSS skeleton) are padded into the main file. It is not 1 because most of the text is dense prescriptive design judgment rather than explanation of concepts Claude already knows.

2 / 5

Actionability

Fully executable throughout: exact package names with install commands (Appendix A), complete copy-paste code skeletons (GSAP sticky-stack 5.A, horizontal-pan 5.B, reveal stagger 5.C, liquid-glass CSS in Appendix C), specific hex values, Tailwind class strings, and WCAG contrast ratios. Concrete examples cover the common cases.

5 / 5

Workflow Clarity

The pipeline is clearly sequenced (Section 0 brief inference and design read -> Section 1 dials -> Section 2 design-system choice -> build sections -> Section 11 redesign protocol -> Section 14 pre-flight) with a ~60-item explicit validation checklist and a fix-before-deliver feedback loop ("If a single checkbox cannot be honestly ticked, the page is not done"). Not destructive/batch work, so no cap applies.

5 / 5

Progressive Disclosure

No references/, scripts/, or assets/ directories exist; everything is inlined in one monolithic 1233-line file. Content that clearly belongs in separate files (the appendix install commands, canonical link lists, liquid-glass CSS, the Section 10 vocabulary catalog) is inlined, and the Section 12 Block Library directory is specified but not present ("Blocks will be added iteratively"). It is not 1 because the file has clear numbered section headers and internal cross-references, so it is navigable.

2 / 5

Total

14

/

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 specific, third-person description with good natural trigger terms for its landing-page/portfolio niche, but it lacks an explicit "Use when..." clause, which caps completeness and leaves invocation conditions implicit. Adding a trigger clause with common synonyms (website, marketing site, homepage) would raise both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when building or redesigning landing pages, portfolios, marketing sites, or hero pages, or when the user asks for non-templated, premium, or non-AI-looking frontend work."

Include common synonyms and file/page types users actually say ("website", "marketing page", "homepage") to broaden natural keyword coverage.

State the exclusions inline (not dashboards, not product UI) to sharpen distinctiveness against general frontend skills.

DimensionReasoningScore

Specificity

The description lists several concrete actions in third person ("reads the brief, infers the right design direction", "Real design systems when applicable, audit-first on redesigns, strict pre-flight check"), which matches the 'several specific actions; minor gaps' anchor. It is not 5 because the actions are telegraphic fragments rather than a comprehensive list, and not 3 because it goes beyond 1-2 actions.

4 / 5

Completeness

The "what" is clear (anti-slop frontend skill that infers design direction and ships non-templated interfaces), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The "when" is only weakly implied by the domain listing.

3 / 5

Trigger Term Quality

"landing pages", "portfolios", and "redesigns" are natural phrases users say, giving good keyword coverage. Not 5 because common synonyms and variations ("website", "marketing site", "homepage", "hero page") are missing.

4 / 5

Distinctiveness Conflict Risk

"Anti-slop frontend skill for landing pages, portfolios, and redesigns" carves a mostly distinct niche with distinct triggers. Minor overlap risk remains with general frontend/component-ui skills since "frontend" alone is broad; not 5.

4 / 5

Total

15

/

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.