CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

baseline-ui

Validates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency.

70

Quality

88%

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

The canonical home for this skill is baseline-ui in ibelick/ui-skills

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 exemplarily lean constraint-style skill: every line is an actionable MUST/SHOULD/NEVER rule with concrete Tailwind utilities, libraries, and thresholds, and the review workflow is unambiguously defined. Only minor gaps (unspecified z-index scale values, no safe-area code pattern) and its fully-inline 80-line structure keep it just below top marks on two dimensions.

DimensionReasoningScore

Conciseness

The body is a lean constraint checklist with zero padding: every line states a rule ('NEVER use h-screen, use h-dvh', 'MUST use tabular-nums for data') and assumes Claude's competence without explaining what Tailwind or accessibility is. The single purpose sentence ('Enforces an opinionated UI baseline to prevent AI-generated interface slop') earns its place.

5 / 5

Actionability

Most guidance is directly executable: exact utilities (`h-dvh`, `text-balance`, `text-pretty`, `tabular-nums`, `size-*`), named libraries (`motion/react`, `tw-animate-css`, `cn` from `clsx` + `tailwind-merge`), concrete thresholds ('NEVER exceed 200ms'), and a defined review output format. A few rules state the what without the how — 'MUST use a fixed z-index scale' without specifying the scale, 'MUST respect safe-area-inset' without the pattern — which is a minor gap.

4 / 5

Workflow Clarity

This is a simple, single-purpose skill and the review action is unambiguous: the 'How to use' section defines both invocation modes and specifies the exact per-violation output (quoted snippet, why it matters, concrete fix). The skill is read-only review, so no destructive/batch validation cap applies.

5 / 5

Progressive Disclosure

Sections (Stack, Components, Interaction, Animation, Typography, Layout, Performance, Design) are well organized with no inlined content that belongs in separate files and no nested references, and the one external link (Base UI components) is clearly signaled. The body runs ~80 lines with no reference files, so the under-50-lines exception for a top score does not apply; structure is good but the skill relies solely on inline sections.

4 / 5

Total

18

/

20

Passed

Description

83%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 description in third-person voice with concrete actions and an explicit 'Use when...' trigger clause. It is specific and complete; only minor trigger-synonym gaps and slight overlap risk with general frontend/design skills keep it from top marks.

DimensionReasoningScore

Specificity

The description lists four concrete actions — 'Validates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns' — anchored in a named domain (Tailwind CSS projects). Coverage has minor gaps: the body also covers performance and design constraints (gradients, shadows, empty states) that the description omits, so it sits at 'several specific actions; minor gaps' rather than the comprehensive 5.

4 / 5

Completeness

It explicitly answers both parts: the 'what' is the four named validation/enforcement actions, and the 'when' is the explicit 'Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency' clause with four concrete trigger phrases. This matches the anchor for clearly and explicitly answering both what AND when.

5 / 5

Trigger Term Quality

Trigger phrases like 'building UI components', 'reviewing CSS utilities', and 'styling React views' are natural things a user would say, with 'Tailwind CSS' and 'React' naming the stack. A few common variations are missing (e.g., 'design review', 'accessibility/a11y', 'design system', 'animation'), placing it just below the comprehensive-coverage anchor.

4 / 5

Distinctiveness Conflict Risk

The Tailwind/React/CSS-utility framing carves a clear niche that is unlikely to trigger unrelated skills. However, broad phrases like 'building UI components' and 'enforcing design consistency' could overlap with general frontend or design-review skills, matching 'mostly distinct; minor overlap risk' rather than minimal conflict.

4 / 5

Total

17

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/baseline-ui/SKILL.md

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.