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 pproenca/dot-skills --skill tailwind-ui-refactorgit clone --depth 1 https://github.com/pproenca/dot-skillsWrote 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/pproenca/dot-skills/tailwind-ui-refactor)<a href="https://agentmods.dev/skills/pproenca/dot-skills/tailwind-ui-refactor"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/tailwind-ui-refactor/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/pproenca/dot-skills/tailwind-ui-refactor"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/tailwind-ui-refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00075 | $0.02269 |
| Opus 5 | $0.00037 | $0.01135 |
| Sonnet 5 | $0.00015 | $0.00454 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade A, and why
tailwind-ui-refactor 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring UI Tailwind CSS Best Practices
Comprehensive UI refactoring guide based on Refactoring UI by Adam Wathan & Steve Schoger, implemented with Tailwind CSS utility classes. Contains 52 rules across 9 categories, prioritized by design impact to guide automated refactoring and code generation. Uses Tailwind CSS v4 syntax (v3 notes provided where syntax differs).
Important: Think first, style second. Before applying any visual rule, understand the UI's purpose, identify what matters to the user, and remove unnecessary elements. The Design Intent category (priority 1) must be considered before any styling changes. A simpler component with fewer elements always beats a decorated component with unnecessary markup.
When to Apply
Reference these guidelines when:
- Refactoring existing Tailwind CSS components
- Writing new UI with Tailwind utility classes
- Reviewing code for visual hierarchy and spacing issues
- Improving design quality without a designer
- Fixing accessibility contrast problems
Rule Categories by Priority
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Design Intent | CRITICAL | intent- |
| 2 | Visual Hierarchy | CRITICAL | hier- |
| 3 | Layout & Spacing | CRITICAL | space- |
| 4 | Typography | HIGH | type- |
| 5 | Color Systems | HIGH | color- |
| 6 | Depth & Shadows | MEDIUM | depth- |
| 7 | Borders & Separation | MEDIUM | sep- |
| 8 | Images & Content | LOW-MEDIUM | img- |
| 9 | Polish & Details | LOW | polish- |
Quick Reference
1. Design Intent (CRITICAL)
intent-audit-before-styling- Audit what each element communicates before changing any CSSintent-remove-before-decorating- Remove unnecessary elements before styling what remainsintent-reduce-cognitive-load- Reduce choices per screen — fewer options beat prettier optionsintent-progressive-disclosure- Hide secondary information behind interactionsintent-content-drives-layout- Let real content determine layout — not the other way aroundintent-simplify-over-decorate- Prefer removing a wrapper over adding 5 utility classes to itintent-match-context-fidelity- Match design polish to context — admin vs consumer vs productintent-match-existing-patterns- Audit sibling component patterns before restyling
What ships with it
55 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.
- assets/templates/_template.md 666 B
- metadata.json 716 B
- references/_sections.md 2.3 KB
- references/color-accessible-contrast.md 1.4 KB
- references/color-dark-gray-not-black.md 990 B
- references/color-define-palette-upfront.md 1.0 KB
- references/color-grayscale-first.md 1.8 KB
- references/color-light-backgrounds-dark-text.md 1.3 KB
- references/color-saturated-grays.md 1.3 KB
- references/depth-interactive-elevation.md 1.0 KB
- references/depth-light-closer-dark-recedes.md 1.3 KB
- references/depth-overlap-layers.md 1.4 KB
- references/depth-shadow-scale.md 1.3 KB
- references/depth-shadow-vertical-offset.md 994 B
- references/hier-button-hierarchy.md 1.2 KB
- references/hier-color-hierarchy-on-dark.md 1.4 KB
- references/hier-deemphasize-secondary.md 1.5 KB
- references/hier-icon-sizing.md 951 B
- references/hier-label-value-pairs.md 1.9 KB
- references/hier-semantic-vs-visual.md 1.2 KB
- references/hier-size-weight-color.md 1.1 KB
- references/img-control-user-content.md 1012 B
- references/img-dont-scale-up-icons.md 1.3 KB
- references/img-empty-states.md 1.2 KB
- references/img-text-overlay.md 1.1 KB
- references/intent-audit-before-styling.md 2.1 KB
- references/intent-content-drives-layout.md 2.1 KB
- references/intent-match-context-fidelity.md 2.7 KB
- references/intent-match-existing-patterns.md 2.4 KB
- references/intent-progressive-disclosure.md 2.1 KB
- references/intent-reduce-cognitive-load.md 1.8 KB
- references/intent-remove-before-decorating.md 1.8 KB
- references/intent-simplify-over-decorate.md 2.2 KB
- references/polish-accent-borders.md 1007 B
- references/polish-border-radius-personality.md 1.2 KB
- references/polish-custom-bullets.md 1.2 KB
- references/polish-gradient-close-hues.md 1.2 KB
- references/polish-inner-shadow-images.md 1.1 KB
- references/sep-background-color-separation.md 1.2 KB
- references/sep-card-radio-buttons.md 2.2 KB
- references/sep-fewer-borders.md 1.3 KB
- references/sep-table-spacing-not-lines.md 2.1 KB
- references/space-dont-fill-screen.md 1.3 KB
- references/space-grids-not-required.md 1.3 KB
- references/space-mobile-first.md 1.8 KB
- references/space-relationship-proximity.md 1.6 KB
- references/space-relative-sizing-fails.md 1.4 KB
- references/space-start-generous.md 1.3 KB
- references/space-systematic-scale.md 1.1 KB
- references/type-align-numbers-right.md 1.9 KB
- references/type-font-weight-variety.md 1.2 KB
- references/type-letter-spacing.md 1.0 KB
- references/type-line-height-inverse.md 1.3 KB
- references/type-line-length.md 1.2 KB
- references/type-no-center-long-text.md 1.3 KB
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 · 141 lines · 75 tokens per session scan A da0b3c8d5e52
tailwind-ui-refactor is a skill published in the GitHub repository pproenca/dot-skills (205 stars, last pushed 24d ago), licensed MIT. It adds 75 tokens to every session and 2,269 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.