CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tailwind-design-system

Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.

84

1.13x
Quality

81%

Does it follow best practices?

Impact

100%

1.13x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is tailwind-design-system in wshobson/agents

SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

The content is highly actionable — complete, executable v4 patterns and an accurate migration guide — but the file is a monolithic ~860 lines with substantial boilerplate (Card family, LoginForm, ThemeProvider) that assumes too little of Claude's competence. Splitting patterns into reference files and trimming generic React boilerplate would materially improve both conciseness and progressive disclosure.

Suggestions

Trim boilerplate that Claude already knows: replace the six Card subcomponents and the full React Hook Form LoginForm with one exemplar pattern plus a note on the conventions they share, cutting roughly 150-200 lines.

Split the pattern library into one-level-deep reference files (e.g., references/patterns.md for components/forms/grid, references/animations.md, references/migration.md) and keep SKILL.md as a concise overview with the v4 changes table, Quick Start, and clearly signaled links.

Add a brief verification step for theme work (e.g., 'confirm both light and dark palettes define every semantic token used by components') so the dark-mode guidance has an explicit checkpoint.

DimensionReasoningScore

Conciseness

The v4-specific material (Key v4 Changes table, @theme, @custom-variant, @starting-style, @utility) is dense and valuable, but large sections are boilerplate Claude already knows: the six-member Card family (~100 lines of near-identical components), a full React Hook Form LoginForm, and a complete ThemeProvider implementation. This fits 'mostly efficient but includes some unnecessary content that could be tightened' rather than 2, since explanations themselves are lean and the padding is confined to a few code sections.

3 / 5

Actionability

Every pattern ships complete, executable code (CVA button with variants, full @theme token config, dark-mode override block, @starting-style popover animation, ThemeProvider), plus a concrete v3-to-v4 migration checklist. This is copy-paste-ready guidance covering the common cases, matching the 5 anchor.

5 / 5

Workflow Clarity

Not a sequential workflow skill, but 'When to Use' + 'Quick Start' + the ordered v3-to-v4 migration checklist give a clear sequence for the main task, fitting 'clear sequence with most checkpoints present'. Not 5 because there are no explicit validation/verification steps (only 'Test both themes' in the Don'ts) — though the operations are neither destructive nor batch, so no cap applies.

4 / 5

Progressive Disclosure

No bundle files exist and the entire ~860-line pattern library (6 patterns plus advanced sections) is inlined in a single monolithic SKILL.md with no external references. Section headers provide some structure, matching 'some structure but content that should be separate is inline'; the under-50-line exception does not apply at this size.

3 / 5

Total

15

/

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 with explicit third-person 'what' and 'when' clauses and concrete, natural trigger phrases. Its only weaknesses are slightly repetitive trigger terms between the two clauses and omission of a couple of the skill's actual capabilities (dark mode, migration).

DimensionReasoningScore

Specificity

Names the domain ("Tailwind CSS v4") and multiple concrete deliverables ("design tokens, component libraries, and responsive patterns"), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because the description omits key covered capabilities like theming/dark mode and v3-to-v4 migration.

4 / 5

Completeness

Explicitly answers both questions: a clear third-person 'what' ("Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns") and an explicit 'when' with concrete trigger phrases ("Use when creating component libraries, implementing design systems, or standardizing UI patterns"), matching the 5 anchor exactly. The 4 anchor's caveat ('when' could be more explicit) does not apply.

5 / 5

Trigger Term Quality

Includes natural user phrases like "component libraries", "design systems", and "UI patterns", which matches 'good keyword coverage; a few natural terms missing'. Not 5 because the 'when' clause merely repeats the 'what' clause's terms without adding synonyms like 'theming', 'dark mode', or 'UI kit'.

4 / 5

Distinctiveness Conflict Risk

The Tailwind v4 design-system niche is clearly distinct with specific triggers, fitting 'mostly distinct; minor overlap risk'. Not 5 because 'standardizing UI patterns' is broad enough to brush generic CSS/styling or component-library skills.

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

skill_md_line_count

SKILL.md is long (867 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

calesthio/OpenMontage

Path

.agents/skills/tailwind-design-system/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.