CtrlK
BlogDocsLog inGet started
Tessl Logo

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications. Generates creative, polished code that avoids generic AI aesthetics.

92

1.59x
Quality

90%

Does it follow best practices?

Impact

94%

1.59x

Average score across 6 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

80%Weight 40%Scale 1-3

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

The body is an exceptionally lean, actionable set of aesthetic DO/DON'T guidance with well-signaled reference pointers. Its main weaknesses are a soft rather than explicit validation workflow and reference links that point to files not present in the bundle.

Suggestions

Ship the referenced reference files (typography.md, color-and-contrast.md, spatial-design.md, motion-design.md, interaction-design.md, responsive-design.md, ux-writing.md) under reference/ so the progressive-disclosure links resolve.

Make the build-and-review workflow explicit with sequenced steps and a hard checkpoint, e.g. 1) commit to a Design Direction, 2) implement, 3) run the AI Slop Test, 4) revise any failing DON'Ts before finalizing.

Reconcile the reference path convention (reference/ vs references/) with the bundle's actual directory name to avoid broken links.

DimensionReasoningScore

Conciseness

The body is dense, actionable DO/DON'T guidance with no padding or explanation of concepts Claude already knows; every guideline earns its place (e.g. "DON'T: Use pure black (#000) or pure white (#fff)—always tint").

3 / 3

Actionability

Despite being instruction-only with no code, the guidance is highly concrete and specific — named fonts to avoid, named CSS functions to use (oklch, color-mix, clamp, @container), and named anti-patterns — which the rubric rewards for actionable instruction-only skills.

3 / 3

Workflow Clarity

A loose sequence exists (Design Direction → implement → AI Slop Test review) but it reads as a checklist rather than a tightly sequenced process, and the "AI Slop Test" checkpoint is soft rather than an explicit validate/fix/retry gate.

2 / 3

Progressive Disclosure

Reference pointers are well-signaled and one-level-deep with a consistent format ("→ Consult [typography reference](reference/typography.md)"), but the referenced reference/ files do not exist in the bundle, so the disclosure path is broken and navigation cannot complete.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 third-person, concise, and explicitly covers both capability and trigger conditions with concrete, natural-language terms. It is clearly distinguishable from generic coding skills. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Create distinctive, production-grade frontend interfaces", "Generates creative, polished code", and "build web components, pages, artifacts, posters, or applications" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what ("Create distinctive, production-grade frontend interfaces... Generates creative, polished code") and when ("Use this skill when the user asks to build..."), with an explicit trigger clause.

3 / 3

Trigger Term Quality

Natural user-facing terms "web components, pages, artifacts, posters, or applications" give good coverage of phrasings a user would actually say when requesting frontend work.

3 / 3

Distinctiveness Conflict Risk

The niche is clearly framed around distinctive aesthetics and "avoids generic AI aesthetics", with triggers scoped to building frontend artifacts, making conflict with other skills unlikely.

3 / 3

Total

12

/

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

relative_links

Relative link issues: 7 missing

Warning

Total

15

/

16

Passed

Repository
The-Vibe-Company/companion
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.