Skip to content
Back to search

dent

MarketplaceWorks with Claude CodeGitHub

Open-source AI design skill for Claude Code, Codex, Cursor & Copilot: asks the right questions, follows UX laws, accessibility and Google's Modern Web Guidance, verifies and scores its own UI. 41 styles, 31 commands.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/jeelnadaa--dent/badge.svg)](/listings/jeelnadaa--dent)

HTML

<a href="/listings/jeelnadaa--dent"><img src="/api/listings/jeelnadaa--dent/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**Claude Code (plugin, gets all 32 slash commands)**

/plugin marketplace add jeelnadaa/DENT
/plugin install dent@dent

**Any agent, one command** (detects Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode…)

npx skills add jeelnadaa/DENT

**Manual:** copy `skills/dent/` and `skills/modern-web-guidance/` side by side into your agent's skills folder:

| Agent | Personal (all projects) | Project only | |---|---|---| | Claude Code | `~/.claude/skills/dent/` | `.claude/skills/dent/` | | OpenAI Codex | `~/.codex/skills/dent/` | `.agents/skills/dent/` | | GitHub Copilot | `~/.copilot/skills/dent/` | `.github/skills/dent/` | | Cursor | `~/.cursor/skills/dent/` | `.cursor/skills/dent/` | | Gemini CLI | `~/.gemini/skills/dent/` | `.gemini/skills/dent/` | | Antigravity, OpenCode, Goose, Amp & other Agent Skills tools | — | `.agents/skills/dent/` |

Or run the installer (installs both): `./scripts/install.sh claude` (macOS/Linux) · `.\scripts\install.ps1 -Agent claude` (Windows).

**Claude.ai / Claude Desktop:** download `dent.zip` from [Releases](https://github.com/jeelnadaa/DENT/releases) and upload it under **Settings → Capabilities → Skills** (it includes Modern Web Guidance; upload `modern-web-guidance.zip` as well if you want it active outside DENT). Agents without skill support (Windsurf, Cline, Aider, Zed…): see [docs/INSTALL.md](docs/INSTALL.md#agents-without-native-skill-support).

**Updating:** run `/dent:update` in Claude Code, then click **Update** on DENT in Settings → Plugins (or `/plugin update dent@dent`). Turn on auto-update for the DENT marketplace to get new versions automatically. Details: [docs/INSTALL.md](docs/INSTALL.md#updating).

**Optional, for real verification:** `pip install playwright && python -m playwright install chromium` lets DENT run `verify_page.py` on what it builds. Node.js lets it use the always-current Modern Web Guidance CLI (`npx`); without it DENT reads the bundled guides.

> Skill folder paths change as tools evolve. If a path doesn't work, check your agent's docs for its "skills" directory. Full details: [docs/INSTALL.md](docs/INSTALL.md).

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 26 lines
  1. {
  2. "name": "dent",
  3. "owner": {
  4. "name": "Jeel Nada (solarquack)",
  5. "url": "https://github.com/jeelnadaa"
  6. },
  7. "metadata": {
  8. "description": "DENT: open-source product design skill for AI agents.",
  9. "version": "2.4.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "dent",
  14. "source": "./",
  15. "description": "Design-engineering skill: 32 commands, orchestration, planning + plan audit, 41 styles + directions library, component/motion/audio/video catalogues, verify_page.py, self-scoring and DESIGN.md. Includes Google's Modern Web Guidance skill as the web-platform authority.",
  16. "version": "2.4.0",
  17. "author": {
  18. "name": "Jeel Nada (solarquack)"
  19. },
  20. "homepage": "https://github.com/jeelnadaa/DENT",
  21. "license": "Apache-2.0",
  22. "category": "design",
  23. "keywords": ["design", "ui", "ux", "design-system", "accessibility"]
  24. }
  25. ]
  26. }
README.md · README · 446 lines
  1. <a href="#install">
  2. <picture>
  3. <source media="(prefers-color-scheme: dark)" srcset="assets/hero-dark.svg">
  4. <img src="assets/hero-light.svg" alt="DENT 2.0: a generic AI-template layout is knocked away by an orange dot and replaced by the DENT wordmark and the line 'Make a dent with your product's design.'" width="100%">
  5. </picture>
  6. </a>
  7. # DENT: the AI design skill for Claude Code, Codex, Cursor and Copilot
  8. **DENT is an open-source design-engineering skill for AI agents.** Install it once and your agent (Claude Code, Codex, Cursor, Copilot, Gemini CLI, Antigravity, or anything that reads `SKILL.md`) designs like a senior product designer, builds like a front-end engineer, animates like a motion designer, and scores like a strict reviewer. Interfaces, motion graphics, 3D, sound, narration and video.
  9. [![License: Apache 2.0](https://img.shields.io/badge/license-Apache%202.0-111?style=flat-square)](LICENSE)
  10. [![Agent Skills](https://img.shields.io/badge/format-SKILL.md-111?style=flat-square)](https://agentskills.io)
  11. [![Version](https://img.shields.io/badge/version-2.4.0-E8461E?style=flat-square)](CHANGELOG.md)
  12. [![Modern Web Guidance](https://img.shields.io/badge/web%20authority-Modern%20Web%20Guidance-111?style=flat-square)](#modern-web-guidance-the-authority-for-web-code)
  13. [![Styles](https://img.shields.io/badge/aesthetic%20styles-41-111?style=flat-square)](skills/dent/references/styles/_styles-index.md)
  14. [![Commands](https://img.shields.io/badge/commands-32-111?style=flat-square)](docs/COMMANDS.md)
  15. **[Website](https://dent.solarquack.in)** · **[Install](#install)** · **[One command](#one-command-the-right-pipeline)** · **[What it can make](#what-dent-can-make)** · **[Proof](#see-the-difference-run-the-benchmark)** · **[Commands](docs/COMMANDS.md)** · **[Architecture](docs/ARCHITECTURE.md)**
  16. ---
  17. ## The problem
  18. Ask any agent for a landing page and you get the average of every template: a violet gradient, a glowing orb, a centered headline, three equal cards, invented "loved by 10,000+ teams" stats, and a phone layout that scrolls sideways. It looks finished for a second and forgettable forever.
  19. **DENT changes how the agent works, not just what it outputs.**
  20. | Without DENT | With DENT 2.0 |
  21. |---|---|
  22. | Guesses the look from one sentence | Classifies the task, asks the few questions that matter, or decides for you and shows why |
  23. | The category cliché | Names the cliché, then diverges: concept, one of 41 styles, a directions library, a signature hero |
  24. | Invents social proof | **Never.** Honesty is a gate: real proof or clearly marked placeholders |
  25. | "Looks fine on my screen" | `verify_page.py` checks overflow at 6 widths, contrast, labels, reduced motion, autoplay audio |
  26. | Adds a second UI library to your repo | Detects your design system and extends it; picks libraries from sourced catalogues, licences included |
  27. | Writes yesterday's web code: JS modals with focus traps, positioning libraries, global animation kill switches | Follows Google's **Modern Web Guidance** first: native `<dialog>`, `popover`, anchor positioning, `<details>`, view transitions, with each guide's fallbacks |
  28. | Leaves OS-default tooltips, scrollbars, sliders and checkboxes on a designed page | Asks *match my design / brand tint / native*, then styles every built-in surface with your tokens and checks it (`/dent:surfaces`) |
  29. | Fades everything in | Motion with a purpose, storyboards for motion graphics, reduced-motion versions |
  30. | Click sounds everywhere, autoplaying music | Sound as a designed, opt-in system; narration with captions |
  31. | "Done!" | Scores itself against *your* request with evidence; `/dent:improve` raises the score |
  32. ---
  33. ## One command. The right pipeline.
  34. <picture>
  35. <source media="(prefers-color-scheme: dark)" srcset="assets/workflow-dark.svg">
  36. <img src="assets/workflow-light.svg" alt="Diagram: any request goes to /dent, which builds a pipeline (route, plan, audit, direct, build, verify, score, improve) powered by knowledge, catalogues, quality checks and memory." width="100%">
  37. </picture>
  38. You never have to learn the commands. Type `/dent` (or just describe what you want) and DENT's router works out the deliverable, the state of your project, the media involved and the risk, then chains the right sub-commands:
  39. ```text
  40. /dent go all out: a landing page for my app and a 45-second launch video with voice-over
  41. ```
  42. → *two pipelines, one shared design system:* `directions → create → type → motion-graphics → assets → verify → score → improve`, then `launch-video → voice → sound → verify → score`.
  43. ```text
  44. /dent this dashboard scrolls sideways on my phone
  45. ```
  46. → `responsive → verify`. No questionnaire for a bug.
  47. Power users can call any of the [32 commands](docs/COMMANDS.md) directly: `/dent:plan`, `/dent:audit`, `/dent:components`, `/dent:motion-graphics`, `/dent:sound`, `/dent:video`, `/dent:score`, `/dent:improve`…
  48. ---
  49. ## What DENT can make
  50. | Discipline | What DENT brings |
  51. |---|---|
  52. | **Product design** | Six modes (create, redesign, audit, extend, implement, adopt), 4 effort levels, 4 task depths, UX laws labelled Law / Rule / Convention, recipes for landing pages, apps and dashboards |
  53. | **Creative direction** | Concept sentence, category-cliché check, 41 aesthetic styles, a [library of 25 named directions](skills/dent/references/creative/directions-library.md) plus motion, sound and video directions, a [hero typography system](skills/dent/references/creative/hero-typography.md) with 18 composition techniques |
  54. | **Front-end engineering** | Tokens first, ~45 component specs, code guides for HTML/CSS, Tailwind, React, Vue, Svelte, Flutter, SwiftUI, Compose, React Native. On the web, [Modern Web Guidance](#modern-web-guidance-the-authority-for-web-code) decides how each piece is built |
  55. | **Component intelligence** | A [sourced catalogue](skills/dent/references/catalog/README.md) of primitives (Radix, Base UI, React Aria, Ark…), systems (MUI, Mantine, Ant, Carbon, Fluent…), collections (shadcn/ui, Magic UI, Aceternity…) and specialists (TanStack Table, AG Grid, Tiptap, cmdk, Sonner, dnd-kit, React Flow…), with licences and paid tiers called out |
  56. | **Motion graphics** | Interface motion vs motion graphics vs 3D, 1D → 2D → 2.5D → 3D → XR, storyboards, kinetic type, scroll stories, generative visuals, and a tech ladder from CSS to GSAP, Rive, PixiJS, Three.js and shaders |
  57. | **Sound and voice** | UI sound, sonic identity, ambience, interactive and procedural audio, music, narration and TTS, captions; never autoplay, always opt-in |
  58. | **Video** | Launch (teaser, reveal, feature tour, manifesto), trailers, explainers, demos, social, ads; scripts, storyboards, animatics; generative tools if you have them, otherwise HyperFrames, Remotion, Motion Canvas and FFmpeg |
  59. | **Quality** | 13 gates, runnable checks, an [All-out protocol](skills/dent/references/workflow/all-out.md) that misses nothing, request-specific self-scoring, and attribution of what came from DENT vs the agent vs you |
  60. ---
  61. ## Modern Web Guidance: the authority for web code
  62. DENT bundles Google Chrome's [Modern Web Guidance](https://developer.chrome.com/docs/modern-web-guidance) skill (stewarded with the Edge, Firefox and MDN teams, Apache-2.0) and makes it the **primary authority for every HTML, CSS and client-side JS task**. DENT decides *what* is designed; MWG decides *how* it is built on the web.
  63. - **Before writing web code** DENT searches and retrieves the relevant guides (`npx -y modern-web-guidance@latest search …`, or offline with `skills/dent/scripts/mwg.py`), applies them, checks the result against them (gate G13) and ends with a short `### Modern Web Guidance` note naming the guides it followed.
  64. - **MWG wins conflicts.** DENT 2.3 was audited against it: global reduced-motion resets, hand-made modal focus traps, split OTP inputs, library-first widgets and oversized fluid-type ranges were replaced with MWG's patterns ([full table](skills/dent/references/modern-web-guidance.md#6-conflicts-resolved-in-dent-230)).
  65. - **Native first:** `<dialog>`, `popover`, anchor positioning, `<details>`, `<input switch>`, customizable `<select>` before any library; libraries only where the platform has no primitive.
  66. - `verify_page.py` flags the mechanical violations (a global `*` reduced-motion reset, a lazy-loaded LCP image, ARIA re-added to `<dialog>`, split one-time-code inputs).
  67. The plugin ships MWG as its own skill too (`skills/modern-web-guidance/`, vendored verbatim and pinned in `UPSTREAM.json`), so it also kicks in on web tasks that never touch DENT.
  68. ---
  69. ## Built with DENT 2.0
  70. The next showcase pieces are being produced **with DENT 2.0 itself**, using the exact prompts in [`evals/scenarios.md`](evals/scenarios.md) (S19–S21). Every question the agent asks and every answer given will be published with the result.
  71. | Piece | Status |
  72. |---|---|
  73. | DENT's own landing page | Next |
  74. | A kinetic-typography motion piece about DENT | Next |
  75. | A 60–75 s explainer video with narration and captions | Next |
  76. The animated banner at the top of this page is hand-built SVG: the wordmark is drawn as paths, it plays once, and it respects reduced-motion settings. Its source is [`assets/build_assets.py`](assets/build_assets.py).
  77. ---
  78. ## See the difference: run the benchmark
  79. Don't take our word for it. Give your agent the **same prompt twice**, once without DENT and once with it, and compare the two websites. We publish every result: wins, ties and losses.
  80. **How to run either benchmark**
  81. 1. Use the same agent, model and settings for both runs, each in a **fresh session** and an **empty folder**.
  82. 2. **Run A, without DENT:** skill not installed. **Run B, with DENT:** skill installed ([install](#install)).
  83. 3. Paste the prompt unchanged. Apart from answering the agent's questions (benchmark 1 only), reply only `continue` if it stops early. Keep the first result of each run.
  84. 4. Open both `index.html` files side by side on your phone and desktop, and share your screenshots via a pull request or a [Benchmark result issue](https://github.com/jeelnadaa/DENT/issues/new?template=benchmark_result.md).
  85. Full rules, scoring sheet and a screenshot script: **[benchmark/](benchmark/README.md)** · Full test protocol: **[evals/protocol.md](evals/protocol.md)**
  86. ### Latest results: 8 builds with and without DENT (Claude Opus 5.5)
  87. Same agent (Claude Code), same model (Claude Opus 5.5, medium effort), same prompt, built twice: once without DENT and once with DENT 2.0. Full summary: **[RESULTS-SUMMARY.md](benchmark/RESULTS-SUMMARY.md)**.
  88. | Test | Without DENT | With DENT | Comparable? |
  89. |---|---|---|---|
  90. | [Brewlog marketing site](benchmark/results/brewlog-claude-code-opus-5.5-medium-2026-11-14/RESULT.md) | 38 | **44** | Yes |
  91. | [SaaS analytics dashboard](benchmark/results/saas-dashboard-claude-code-opus-5.5-medium-2026-11-14/RESULT.md) | 39 | **43** | Yes |
  92. | [Checkout with failure recovery](benchmark/results/checkout-flow-claude-code-opus-5.5-medium-2026-11-14/RESULT.md) | 39 | **44** | Partly |
  93. | [Kanban + command palette + drawer](benchmark/results/project-app-claude-code-opus-5.5-medium-2026-11-14/RESULT.md) | 37 | **43** | Partly |
  94. | [Scroll-story launch page](benchmark/results/scroll-story-launch-claude-code-opus-5.5-medium-2026-11-14/RESULT.md) | 37 | **45** | Partly |
  95. | [Meditation timer with sound](benchmark/results/meditation-sound-claude-code-opus-5.5-medium-2026-11-14/RESULT.md) | 39 | **44** | Partly |
  96. | [3D product viewer](benchmark/results/3d-product-viewer-claude-code-opus-5.5-medium-2026-11-14/RESULT.md) | 36 | **44** | Partly |
  97. | [45 s launch video](benchmark/results/launch-video-claude-code-opus-5.5-medium-2026-11-14/RESULT.md) | 38 | **43** | Partly |
  98. | **Average (/50)** | **37.9** | **43.8** | |
  99. | | Without DENT | With DENT |
  100. |---|---|---|
  101. | Scroll-story launch page | ![Tidal launch page without DENT](benchmark/results/scroll-story-launch-claude-code-opus-5.5-medium-2026-11-14/without-hero-1440.jpg) | ![Tidal launch page with DENT](benchmark/results/scroll-story-launch-claude-code-opus-5.5-medium-2026-11-14/with-hero-1440.jpg) |
  102. | 3D product viewer | ![Lamp product page without DENT](benchmark/results/3d-product-viewer-claude-code-opus-5.5-medium-2026-11-14/without-hero-1440.jpg) | ![Lamp product page with DENT](benchmark/results/3d-product-viewer-claude-code-opus-5.5-medium-2026-11-14/with-hero-1440.jpg) |
  103. **What the numbers say, honestly:**
  104. - **Automated checks:** all 7 web builds with DENT passed every automated gate. All 7 without DENT failed at least one: text contrast in all 7, animation that ignores reduced motion in 3, an unlabeled input in 1.
  105. - **Honesty:** one build without DENT invented "4.8 · 312 reviews". None of the DENT builds invented proof.
  106. - **Why the gap isn't bigger:** Opus 5.5 is a very strong model, and its pages are good on their own. DENT's lift shows most in correctness, distinctiveness (a concept instead of the template look) and process (plans, specs, self-checks). Expect a bigger gap with smaller models.
  107. - **Caveats:** the scores come from Claude Opus 5.5, the same model family and DENT's author, so they are not independent. Six of the eight DENT runs got a higher effort level, design feedback or extra features; every difference is listed in [DEVIATIONS](benchmark/results/DEVIATIONS-claude-code-opus-5.5-medium-2026-11-14.md). Human reviews are welcome.
  108. ### Benchmark 1: DENT's own landing page, built with DENT
  109. We are building DENT's landing page with DENT itself. Here is the exact prompt, so you can build it **with and without DENT** and compare.
  110. This prompt gives the agent the **content** (headlines, copy, links) and nothing about the look. It also **lets the agent ask questions**, the way real requests work: answer them briefly, and give the same answers in both runs where the questions overlap.
  111. ```text
  112. Build the landing page for DENT, an open-source product design skill for AI coding agents.
  113. Put it in a single self-contained index.html (HTML, CSS and JavaScript inline; Google Fonts
  114. allowed; no other external files, frameworks or images, so build any visuals with HTML, CSS
  115. or inline SVG). It must work well on phones, tablets and desktops.
  116. Every "Download" or "Get DENT" button links to https://github.com/jeelnadaa/DENT and opens
  117. in a new tab.
  118. Use this content. You may shorten or rephrase it lightly and choose the order of sections,
  119. but keep the facts accurate and don't invent statistics, testimonials, logos or user counts.
  120. PRODUCT
  121. - Name: DENT
  122. - Tagline: Make a dent with your product's design.
  123. - What it is: a free, open-source skill (a folder with a SKILL.md file) that gives AI coding
  124. agents the judgment of a senior product designer.
  125. - Works with: Claude Code, OpenAI Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode and any
  126. agent that supports Agent Skills (SKILL.md). Also Claude.ai and Claude Desktop.
  127. - License: Apache 2.0. Created by Jeel Nada (solarquack).
  128. HERO
  129. - Headline: AI agents can build anything. Now they can design it, too.
  130. - Subheadline: DENT is an open-source design skill that makes your AI agent ask the right
  131. questions, follow proven UX laws and accessibility rules, and ship interfaces that don't
  132. look like every other AI-made site.
  133. - Primary button: Download on GitHub (link above)
  134. - Secondary button: See how it works (scrolls to the "How it works" section)
  135. - Small note under the buttons: Free and open source · Apache 2.0 · Works with Claude Code,
  136. Codex, Cursor, Copilot and more
  137. THE PROBLEM
  138. - Heading: Every AI-made website looks the same.
  139. - Body: Ask an agent for a landing page and you get the usual: a purple gradient, a centered
  140. headline, three feature cards, one font at one weight, missing states and text you can
  141. barely read. It works for a second and looks like everything else forever.
  142. WITHOUT DENT vs WITH DENT (a comparison)
  143. - Guesses the look from one sentence → Asks a few focused questions, or decides for you if
  144. you say so
  145. - Default template look → A clear concept, a deliberate style and a signature element
  146. - One-off values everywhere → Design tokens and components reused on every screen
  147. - Happy path only → Empty, loading, error, success, hover, focus and disabled states
  148. - "Looks accessible" → WCAG 2.2 AA rules no style is allowed to break
  149. - Adds a second design system to your codebase → Detects your existing UI library and
  150. extends it
  151. - "I picked blue because it's nice" → A decision log with the reason behind every choice
  152. - Forgets everything next session → An approved DESIGN.md that becomes the source of truth
  153. HOW IT WORKS (5 steps)
  154. 1. Ask: DENT asks how far to go, then only the questions that matter, one at a time, each
  155. with a recommended answer.
  156. 2. Direct: it picks a concept and a style on purpose, not by default.
  157. 3. Build: tokens first, then components with every state, then screens.
  158. 4. Check: it reviews its own work against a quality checklist and, when the agent can,
  159. takes screenshots and fixes what's wrong.
  160. 5. Document: once you approve, everything goes into DESIGN.md so the next change stays
  161. consistent.
  162. FEATURES
  163. - Four effort levels: Essential, Standard, Polished and All-out. You choose the depth.
  164. - 41 aesthetic styles: from Minimal, Swiss and Editorial to Neo-Brutalism, Glassmorphism,
  165. Japandi, Dark Tech, Retro OS and Cyberpunk, each with rules for doing it well.
  166. - Proven principles: Gestalt, Fitts's Law, Hick's Law, Jakob's Law and Nielsen's heuristics,
  167. applied for you.
  168. - Accessibility built in: contrast, touch targets, keyboard and focus, reduced motion.
  169. - Works with your code: detects shadcn/ui, MUI, Chakra, Tailwind and your existing tokens,
  170. and extends them.
  171. - Design to code: HTML/CSS, Tailwind, React, Vue, Svelte, Flutter, SwiftUI, Jetpack Compose
  172. and React Native.
  173. - Six modes: create, redesign, audit, extend, implement, and adopt an existing design system.
  174. - Real product patterns: landing pages, pricing, dashboards, onboarding, checkout, settings,
  175. AI and chat interfaces, billing, roles, docs sites and more.
  176. STYLES SHOWCASE
  177. - Heading: 41 styles. Zero templates.
  178. - Show a sample of style names: Minimal, Swiss, Editorial, Luxury, Japandi, Neo-Brutalism,
  179. Glassmorphism, Dark Tech, Bento, Utilitarian, Retro OS, Y2K, Synthwave, Cyberpunk,
  180. Terminal, Pixel Art, plus "and 25 more".
  181. BENCHMARK
  182. - Heading: Don't take our word for it.
  183. - Body: We give an AI agent the same prompt twice, once without DENT and once with it, and
  184. publish both results: wins, ties and losses. This page itself was built with DENT. Run the
  185. benchmark yourself and share what you get.
  186. - Button: Run the benchmark (link: https://github.com/jeelnadaa/DENT/tree/main/benchmark)
  187. INSTALL
  188. - Heading: Install in one line.
  189. - Show these as copyable commands, each with a copy button:
  190. - Any agent: npx skills add jeelnadaa/DENT
  191. - Claude Code: /plugin marketplace add jeelnadaa/DENT then /plugin install dent@dent
  192. - Note: Or download the folder from GitHub and drop it into your agent's skills directory.
  193. Full guide: https://github.com/jeelnadaa/DENT/blob/main/docs/INSTALL.md
  194. FAQ
  195. - Is DENT free? Yes. It's open source under the Apache 2.0 license, including for
  196. commercial work.
  197. - Which agents does it work with? Any agent that supports Agent Skills (SKILL.md): Claude
  198. Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode and more. For other agents you
  199. can point a rules file at it.
  200. - Will it slow my agent down? DENT loads one main file and opens its detailed guides only
  201. when a task needs them.
  202. - Do I own what I design with it? Yes. DENT claims no rights over your designs.
  203. - Can it work on my existing app? Yes. It detects your existing design system and extends
  204. it, or audits your current UI and ranks what to fix.
  205. - Can I contribute? Yes. New styles, patterns and fixes are welcome on GitHub.
  206. FINAL CALL TO ACTION
  207. - Heading: Give your agent taste.
  208. - Body: Install DENT in a minute and ask for your next screen.
  209. - Button: Download on GitHub (link above)
  210. FOOTER
  211. - DENT · Make a dent with your product's design.
  212. - Links: GitHub (https://github.com/jeelnadaa/DENT) · Install guide · Benchmark · License
  213. (https://github.com/jeelnadaa/DENT/blob/main/LICENSE)
  214. - Created by Jeel Nada (solarquack). Apache 2.0.
  215. When you are done, give me a short summary of the design decisions you made.
  216. ```
  217. **Results: DENT landing page**
  218. | Agent + model | Without DENT | With DENT | Run by |
  219. |---|---|---|---|
  220. | *Official results coming soon* | | | [@jeelnadaa](https://github.com/jeelnadaa) |
  221. Prompt file and run notes: [benchmark/PROMPT-DENT-LANDING.md](benchmark/PROMPT-DENT-LANDING.md)
  222. ### Benchmark 2: "Brewlog", a one-shot website
  223. A fictional coffee app. This prompt never mentions DENT and tells the agent not to ask questions, so both runs are one-shot and directly comparable.
  224. ```text
  225. Build a complete, production-quality marketing website for "Brewlog", a fictional app
  226. for home coffee brewers. Brewlog lets people log brew recipes (beans, grind size, water
  227. temperature, ratio, time), rate each cup, and see which settings make their best coffee
  228. over time. It has a free plan and a paid "Pro" plan ($6/month or $60/year) that adds
  229. unlimited recipes, bean inventory tracking and brew analytics.
  230. Requirements:
  231. - One self-contained file named index.html (HTML, CSS and JavaScript inline). Web fonts
  232. from Google Fonts are allowed. No other external files, frameworks or images: build any
  233. visuals (product screenshots, illustrations, icons) with HTML, CSS or inline SVG.
  234. - Sections: a header with navigation, hero, how it works, key features, a preview of the
  235. app's interface, pricing (Free vs Pro, monthly/yearly), FAQ, a sign-up form, and a footer.
  236. - The sign-up form asks for name, email and password, validates in the browser and shows
  237. helpful errors and a success state. It does not need a backend.
  238. - It must look great and work well on phones, tablets and desktops.
  239. Make every decision yourself and don't ask me any questions. When you are done, reply with
  240. a short summary of the design decisions you made.
  241. ```
  242. **Results: Brewlog**
  243. **Run 1: Antigravity + Gemini 3.8 Flash (High effort)**, 2026-11-14, run by [@jeelnadaa](https://github.com/jeelnadaa)
  244. | | Without DENT | With DENT |
  245. |---|---|---|
  246. | Desktop | ![Brewlog without DENT, desktop first screen](benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/without-hero-1440.jpg) | ![Brewlog with DENT, desktop first screen](benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/with-hero-1440.jpg) |
  247. | Phone | ![Brewlog without DENT, phone first screen](benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/without-hero-390.jpg) | ![Brewlog with DENT, phone first screen](benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/with-hero-390.jpg) |
  248. | Full page | [Desktop](benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/without-1440.jpg) · [Phone](benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/without-390.jpg) | [Desktop](benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/with-1440.jpg) · [Phone](benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/with-390.jpg) |
  249. | Live site | [Open](https://jeelnadaa.github.io/DENT/benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/without/index.html) | [Open](https://jeelnadaa.github.io/DENT/benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/with/index.html) |
  250. | Score (/50) | **36** | **35** |
  251. **Honest verdict: about a tie.** On this model both runs produced a very similar dark espresso-and-orange site. DENT clearly improved the process: a written brief and concept, a full `DESIGN.md`, reduced-motion support, a light/dark theme and clearer pricing states. But it also shipped a sideways-scrolling header on phones and kept invented stats that its own rules forbid, so the run without DENT scored slightly higher (36 vs 35; the without-DENT page also overflows at 320 px and ignores reduced motion). We're fixing both in the skill. Full scores, checks and notes: **[RESULT.md](benchmark/results/brewlog-antigravity-gemini-3.8-flash-high-2026-11-14/RESULT.md)**
  252. *More runs on other agents and models are welcome. One run per side isn't enough to call a winner.*
  253. **What DENT 2.0 changed because of this run:** every failure above is now an enforced gate (overflow, honesty, labels, style mixing, category cliché, proofreading), the [landing-page recipe](skills/dent/references/recipes/landing-page.md) walks the agent through them step by step, and `verify_page.py` catches the mechanical ones automatically (its raw output for both pages is in the result folder). The next Brewlog run will use DENT 2.0.
  254. ---
  255. ## Install
  256. **Claude Code (plugin, gets all 32 slash commands)**
  257. ```bash
  258. /plugin marketplace add jeelnadaa/DENT
  259. ```
  260. ```bash
  261. /plugin install dent@dent
  262. ```
  263. **Any agent, one command** (detects Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode…)
  264. ```bash
  265. npx skills add jeelnadaa/DENT
  266. ```
  267. **Manual:** copy `skills/dent/` and `skills/modern-web-guidance/` side by side into your agent's skills folder:
  268. | Agent | Personal (all projects) | Project only |
  269. |---|---|---|
  270. | Claude Code | `~/.claude/skills/dent/` | `.claude/skills/dent/` |
  271. | OpenAI Codex | `~/.codex/skills/dent/` | `.agents/skills/dent/` |
  272. | GitHub Copilot | `~/.copilot/skills/dent/` | `.github/skills/dent/` |
  273. | Cursor | `~/.cursor/skills/dent/` | `.cursor/skills/dent/` |
  274. | Gemini CLI | `~/.gemini/skills/dent/` | `.gemini/skills/dent/` |
  275. | Antigravity, OpenCode, Goose, Amp & other Agent Skills tools | — | `.agents/skills/dent/` |
  276. Or run the installer (installs both): `./scripts/install.sh claude` (macOS/Linux) · `.\scripts\install.ps1 -Agent claude` (Windows).
  277. **Claude.ai / Claude Desktop:** download `dent.zip` from [Releases](https://github.com/jeelnadaa/DENT/releases) and upload it under **Settings → Capabilities → Skills** (it includes Modern Web Guidance; upload `modern-web-guidance.zip` as well if you want it active outside DENT). Agents without skill support (Windsurf, Cline, Aider, Zed…): see [docs/INSTALL.md](docs/INSTALL.md#agents-without-native-skill-support).
  278. **Updating:** run `/dent:update` in Claude Code, then click **Update** on DENT in Settings → Plugins (or `/plugin update dent@dent`). Turn on auto-update for the DENT marketplace to get new versions automatically. Details: [docs/INSTALL.md](docs/INSTALL.md#updating).
  279. **Optional, for real verification:** `pip install playwright && python -m playwright install chromium` lets DENT run `verify_page.py` on what it builds. Node.js lets it use the always-current Modern Web Guidance CLI (`npx`); without it DENT reads the bundled guides.
  280. > Skill folder paths change as tools evolve. If a path doesn't work, check your agent's docs for its "skills" directory. Full details: [docs/INSTALL.md](docs/INSTALL.md).
  281. ---
  282. ## Use it
  283. Just ask. These all work with plain `/dent` or no command at all:
  284. ```text
  285. Design a landing page for my meditation app.
  286. Redesign our settings screen. Keep the brand colors.
  287. Review this dashboard screenshot and tell me what's wrong.
  288. Build the pricing page from DESIGN.md in Next.js + Tailwind.
  289. Add sound to the app, but keep it subtle.
  290. Make a 60-second explainer video with a calm narrator.
  291. Go all out on an onboarding flow for a fintech app. Don't ask, just decide.
  292. Score it. Then improve it.
  293. ```
  294. **Effort levels:** Essential · Standard · Polished · **All-out**. All-out is a promise: the best achievable result for your use case with nothing missed, a mandatory completeness sweep, and self-review until the work scores 9/10 with evidence.
  295. ---
  296. ## Architecture
  297. ```
  298. skills/dent/
  299. ├── SKILL.md # the router: classify → route → gates → score (lean, always loaded)
  300. ├── commands/ # 32 command definitions (one source of truth per command)
  301. ├── references/ # loaded only when needed
  302. │ ├── workflow/ # orchestration, planning + plan audit, execution, verification, scoring, all-out
  303. │ ├── recipes/ # step-by-step procedures with gates (landing page, app & dashboard)
  304. │ ├── creative/ # directions library, hero typography, anti-slop detector
  305. │ ├── catalog/ # components, primitives, specialists, assets + selection method
  306. │ ├── motion/ # motion graphics, tech catalogue, 3D, motion system + verification
  307. │ ├── audio/ # sound design, voice & narration, audio tech, implementation + verification
  308. │ ├── video/ # video types & craft, tools & pipeline
  309. │ ├── styles/ # 41 aesthetic styles
  310. │ └── *.md # modern-web-guidance (web authority), color, typography, accessibility, patterns, platforms, tokens & code…
  311. ├── templates/ # PLAN, AUDIT, REVIEW, SCORECARD, MOTION, SOUND, VIDEO
  312. └── scripts/ # verify_page.py, contrast.py, mwg.py (offline Modern Web Guidance lookup)
  313. skills/modern-web-guidance/ # Google's Modern Web Guidance skill, vendored verbatim (scripts/sync_mwg.py)
  314. commands/ # Claude Code plugin wrappers → /dent:<name>
  315. evals/ # behaviour cases, 21 scenarios, command + routing tests, fixtures
  316. benchmark/ # public with/without comparisons
  317. ```
  318. Progressive disclosure keeps the agent's context small: `SKILL.md` is about 330 lines; the other 130+ files load only when a task needs them. More: [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md).
  319. ---
  320. ## Verification and evaluation
  321. - `python scripts/validate.py`: frontmatter, 500+ internal references, the styles index, the command trio (definition ↔ plugin wrapper ↔ router), 200+ catalogue entries with sources and status, versions, the vendored Modern Web Guidance copy, and every `mwg:<guide>` reference in DENT.
  322. - `python scripts/test_tools.py`: `verify_page.py` must fail a deliberately broken page on every gate (including each Modern Web Guidance rule it breaks) and pass a clean one.
  323. - [`evals/`](evals/): 15 behaviour cases, 21 scenarios (dashboards, data-heavy apps, checkout, existing design systems, unfamiliar frameworks, strict accessibility, motion graphics, 3D, animated data, audiovisual, launch and explainer videos, sonic identity) and a protocol that records the prompt, **every question asked and the answer chosen**, the output, machine checks, self-score and an independent score.
  324. - Catalogue licences are marked ✓ (checked against official sources on a date) or K (from knowledge, to verify), so DENT never presents a guess as a fact.
  325. CI runs the validator, the tool tests and the packager on every push.
  326. ---
  327. ## Roadmap
  328. - Publish the three showcase pieces built with DENT 2.0 (landing page, motion piece, explainer).
  329. - Re-run Brewlog with DENT 2.0, plus runs on more agents and models.
  330. - More recipes (mobile app, e-commerce, docs site, email) and more verified catalogue entries.
  331. - Motion verification tooling (frame-rate capture, timeline checks) alongside `verify_page.py`.
  332. Ideas and results are welcome: see [CONTRIBUTING.md](CONTRIBUTING.md).
  333. ---
  334. ## Creator
  335. DENT was created by **Jeel Nada**, known online as **solarquack** · GitHub [@jeelnadaa](https://github.com/jeelnadaa).
  336. If DENT helps you ship something, a ⭐ on the repo or a mention is the best thank-you.
  337. ## License
  338. DENT is licensed under the [Apache License 2.0](LICENSE). You may use, modify and distribute it, commercially too, as long as you keep the license and the [NOTICE](NOTICE) file (which credits the creator). The license does **not** grant rights to the DENT name or logo; see [TRADEMARKS.md](TRADEMARKS.md).
  339. Designs you create with DENT are yours. DENT claims no rights over its output.
  340. `skills/modern-web-guidance/` is [Modern Web Guidance](https://github.com/GoogleChrome/modern-web-guidance) by the Google Chrome team and contributors, redistributed unmodified under the Apache License 2.0 (its own `LICENSE` is included). It is not part of the DENT trademark.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.