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.

67

Quality

81%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

An exceptionally actionable and well-sequenced design-engineering skill with executable code skeletons and a rigorous validation checklist. Its main weaknesses are conciseness (significant repetition across Sections 4/9/14) and progressive disclosure (a monolithic single file that inlines reference material and points to a Block Library bundle that is not present).

Suggestions

Move the Appendices (install commands, canonical-source links, the Liquid Glass CSS skeleton) into separate reference files (e.g. references/install-commands.md, references/canonical-sources.md) and keep SKILL.md as a concise overview that links one level deep, reducing the ~1200-line monolith.

De-duplicate the bans that appear in Section 4 directives, Section 9 AI Tells, and Section 14 Pre-Flight Check by stating each rule once and cross-referencing it from the checklist.

Create the referenced Block Library bundle (skills/taste-skill/blocks/...) so the Section 12 references point to real files, or mark Section 12 as a forward contract and avoid presenting the paths as if they exist.

DimensionReasoningScore

Conciseness

The body is highly actionable but very large (~1200 lines) and repeats guidance across Section 4 directives, Section 9 AI Tells, and Section 14 Pre-Flight Check; some material (e.g. the banned-hex lists, the long Section 9.F tells) restates the same bans three times, which is efficient in places but padded in others and could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste-ready code skeletons (StickyStack, HorizontalPan, RevealStagger components with exact GSAP/Motion configs, e.g. `start: "top top"`, `pin: true`), concrete install commands (Appendix A), real doc links, and specific Tailwind class recipes; matches the 'fully executable, copy-paste ready' anchor.

3 / 3

Workflow Clarity

The brief-inference (Section 0), redesign protocol (Section 11 with audit-first and decision tree), and the 60-item mandatory Pre-Flight Check (Section 14) give a clear sequenced workflow with explicit validation checkpoints and feedback loops (validate -> fix -> re-run), satisfying the level 3 anchor.

3 / 3

Progressive Disclosure

Although well-organized into numbered sections, the SKILL.md is a single monolithic ~1200-line file that inlines reference material (full install-command list, canonical-source link directory, and a complete CSS skeleton) that would more naturally live one level deep in separate reference files; the Block Library directory it points to (Section 12) does not exist in the bundle, so references are not backed by actual files.

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.

A strong, mostly specific description that answers both what and when with a clear niche, written in third person. Its weak point is trigger-term quality: it leans on skill jargon ("anti-slop", "pre-flight check") rather than the natural phrases a user would actually say.

Suggestions

Add a natural-language 'Use when...' clause naming common user phrasings, e.g. 'Use when building a landing page, portfolio, or marketing site that should not look AI-generated or templated.'

Reframe jargon like 'anti-slop' and 'pre-flight check' into trigger terms users say ('my landing page looks AI-generated', 'redesign my portfolio site', 'make this not look templated').

DimensionReasoningScore

Specificity

Lists several concrete actions the skill performs: "reads the brief", "infers the right design direction", "ships interfaces that do not look templated", plus audit-first and pre-flight check; closer to the 'lists multiple specific concrete actions' anchor than the domain-only level 2.

3 / 3

Completeness

Answers both 'what' (frontend skill that infers design direction and ships non-templated interfaces, real design systems, audit-first) and 'when' via explicit scope ("for landing pages, portfolios, and redesigns"); the use-when trigger is explicit, satisfying the level 3 anchor.

3 / 3

Trigger Term Quality

Includes some natural user terms ("landing pages, portfolios, redesigns") but a user would more likely say "landing page", "portfolio", "redesign", "frontend design", or "my site looks AI-generated / templated"; the skill-specific jargon ("anti-slop", "pre-flight check") is not phrased as natural trigger keywords and common variations are missing.

2 / 3

Distinctiveness Conflict Risk

The niche (anti-slop landing/portfolio/redesign frontends with brief-inference and pre-flight discipline) is specific and distinct, with scope cues unlikely to conflict with general frontend or dashboard skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1207 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
Leonxlnx/taste-skill
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.