Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill tailwind-v4-shadcngit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/tailwind-v4-shadcn)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/tailwind-v4-shadcn"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/tailwind-v4-shadcn/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/tailwind-v4-shadcn"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/tailwind-v4-shadcn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00111 | $0.04126 |
| Opus 5 | $0.00056 | $0.02063 |
| Sonnet 5 | $0.00022 | $0.00825 |
| Haiku 4.5 | $0.00011 | $0.00413 |
Grade A, and why
tailwind-v4-shadcn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
98% identical to tailwind-v4-shadcn — 37 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tailwind v4 + shadcn/ui Production Stack
Production-tested: WordPress Auditor (https://wordpress-auditor.webfonts.workers.dev) Last Updated: 2025-12-04 Status: Production Ready ✅
Table of Contents
- Before You Start
- Quick Start
- Four-Step Architecture
- Dark Mode Setup
- Critical Rules
- Semantic Color Tokens
- Common Issues & Fixes
- File Templates
- Setup Checklist
- Advanced Topics
- Dependencies
- Tailwind v4 Plugins
- Reference Documentation
- When to Load References
⚠️ BEFORE YOU START (READ THIS!)
CRITICAL FOR AI AGENTS: If you're Claude Code helping a user set up Tailwind v4:
- Explicitly state you're using this skill at the start of the conversation
- Reference patterns from the skill rather than general knowledge
- Prevent known issues listed in
reference/common-gotchas.md - Don't guess - if unsure, check the skill documentation
USER ACTION REQUIRED: Tell Claude to check this skill first!
Say: "I'm setting up Tailwind v4 + shadcn/ui - check the tailwind-v4-shadcn skill first"
Why This Matters (Real-World Results)
Without skill activation:
- ❌ Setup time: ~5 minutes
- ❌ Errors encountered: 2-3 (tw-animate-css, duplicate @layer base)
- ❌ Manual fixes needed: 2+ commits
- ❌ Token usage: ~65k
- ❌ User confidence: Required debugging
With skill activation:
- ✅ Setup time: ~1 minute
- ✅ Errors encountered: 0
- ✅ Manual fixes needed: 0
- ✅ Token usage: ~20k (70% reduction)
- ✅ User confidence: Instant success
Known Issues This Skill Prevents
- tw-animate-css import error (deprecated in v4)
- Duplicate @layer base blocks (shadcn init adds its own)
- Wrong template selection (vanilla TS vs React)
- Missing post-init cleanup (incompatible CSS rules)
- Wrong plugin syntax (using @import or require() instead of @plugin directive)
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/advanced-usage.md 3.6 KB
- references/common-gotchas.md 7.4 KB
- references/dark-mode.md 5.3 KB
- references/migration-guide.md 6.8 KB
- references/plugins-reference.md 3.1 KB
- templates/components.json 396 B
- templates/index.css 4.5 KB
- templates/theme-provider.tsx 2.2 KB
- templates/tsconfig.app.json 719 B
- templates/utils.ts 166 B runs code
- templates/vite.config.ts 337 B runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 565 lines · 111 tokens per session scan A 7197cbbf6535
tailwind-v4-shadcn is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 4,126 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to tailwind-v4-shadcn, differing in 37 lines, and is treated as a copy.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
column-resizing
Wire columnResizingFeature, header.getResizeHandler, resize mode and direction, pointer or touch events, and performant CSS-variable updates. Load when resize state changes but widths do not, or large tables resize slowly.
column-pinning
Pin columns into logical start, center, and end regions with columnPinningFeature and renderer-owned sticky CSS. Load for RTL offsets, z-index, backgrounds, overflow, widths, gaps, or overlaps.
ui-checkstyle
Run the exact ESLint + Prettier + organize-imports sequence that CI's UI Checkstyle workflow runs — on just the files the PR changed — and fail the task if any file ends up with a diff. Invoke after authoring or modifying any .ts, .tsx, .js, .jsx, or .json file under openmetadata-ui/src/main/resources/ui/src/…
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.