CtrlK
BlogDocsLog inGet started
Tessl Logo

tailwind-theme-builder

Set up Tailwind v4 + shadcn/ui themed UI with dark mode. Install deps, configure CSS variables via @theme inline, wire dark mode toggle, verify. Use whenever the user mentions Tailwind v4, setting up Tailwind theming, shadcn/ui colours, dark mode, or troubleshooting colours not working, tw-animate-css errors, @theme inline conflicts, @apply breaking after upgrade, or v3 → v4 migration issues.

72

Quality

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.

Highly actionable with a clear sequenced workflow and strong error-recovery guidance, but it is verbose for its token budget and inlines content (18 gotchas, duplicated asset code) that would be better progressively disclosed into reference files.

Suggestions

Move the 18-gotcha detail section (and/or its code examples) into a references/gotchas.md file, keeping only the diagnosis table in SKILL.md as a one-level-deep pointer.

Drop the re-inlined vite.config.ts and index.css blocks from the body since they already exist in assets/ — reference the asset files instead to remove redundancy and trim tokens.

Consolidate the three overlapping checklists (Critical Rules, Prevention Checklist, Dark Mode Testing Checklist) into a single verification checklist to reduce repetition.

DimensionReasoningScore

Conciseness

The body is mostly actionable but carries redundancy: three overlapping summaries (Critical Rules, Prevention Checklist, Dark Mode Testing Checklist), re-inlined vite.config.ts and index.css that already live in assets/, and general WCAG contrast ratios ("4.5:1 normal text") Claude already knows. Not score 1 because it avoids explaining basic concepts; not score 3 because of the padding and duplicated checklists.

2 / 3

Actionability

Provides fully executable bash install commands, a complete vite.config.ts, full index.css, a copy-paste ModeToggle component, components.json, and WRONG/CORRECT code pairs for each gotcha — copy-paste ready throughout.

3 / 3

Workflow Clarity

A clear five-step sequence is paired with a symptom→cause→fix diagnosis table (an explicit error-recovery feedback loop) and verification checklists, matching the score-3 anchor; the destructive `rm -f tailwind.config.ts` does not cap the score because verification steps (checklists) are present rather than missing.

3 / 3

Progressive Disclosure

References are one-level-deep and clearly signaled (assets/ list, references/migration-guide.md) and all referenced files exist, but the body inlines substantial content that should be split out — all 18 gotchas with code and duplicated asset file contents — fitting the score-2 anchor "content that should be separate is inline." Not score 3 because the split is not clean; not score 1 because references are real and shallow.

2 / 3

Total

10

/

12

Passed

Description

100%

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, third-person description with concrete actions, explicit trigger guidance, and a distinct version-pinned niche. It scores maximally on all four dimensions with no vagueness or over-claiming.

DimensionReasoningScore

Specificity

"Install deps, configure CSS variables via @theme inline, wire dark mode toggle, verify" lists multiple specific concrete actions, matching the score-3 anchor rather than the single-action score-2 anchor.

3 / 3

Completeness

It answers both what ("Set up Tailwind v4 + shadcn/ui themed UI with dark mode") and when via an explicit "Use whenever the user mentions..." trigger clause, satisfying the score-3 anchor; not score 2 because the when is explicit, not implied.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered: "Tailwind v4", "shadcn/ui colours", "dark mode", "tw-animate-css errors", "@apply breaking after upgrade", "v3 → v4 migration" — terms a user would actually say, not just internal jargon.

3 / 3

Distinctiveness Conflict Risk

The niche is narrow and version-pinned (Tailwind v4 + shadcn/ui theming with named v4-specific failure modes), making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jezweb/claude-skills
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.