Web Artifacts Builder
anthropics/skills
Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.
Design and accessibility rules for the open-doc viewer chrome — the browser shell, sidebars, thumbnail rail, outline, assets and design panels, inspector overlay, and menus.
$ npx skills add simonliu-ai-product/open-doc --skill viewer-ui-guidelines -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install simonliu-ai-product/open-doc viewer-ui-guidelines --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/simonliu-ai-product/open-doc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/viewer-ui-guidelines .claude/skills/viewer-ui-guidelines && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "viewer-ui-guidelines" agent skill from https://github.com/simonliu-ai-product/open-doc/tree/main/.agents/skills/viewer-ui-guidelines into .claude/skills/viewer-ui-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "viewer-ui-guidelines", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/simonliu-ai-product/open-doc/tree/main/.agents/skills/viewer-ui-guidelinesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add simonliu-ai-product/open-doc --skill viewer-ui-guidelines -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install simonliu-ai-product/open-doc viewer-ui-guidelines --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/simonliu-ai-product/open-doc.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/viewer-ui-guidelines .agents/skills/viewer-ui-guidelines && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "viewer-ui-guidelines" agent skill from https://github.com/simonliu-ai-product/open-doc/tree/main/.agents/skills/viewer-ui-guidelines into .agents/skills/viewer-ui-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "viewer-ui-guidelines", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add simonliu-ai-product/open-doc --skill viewer-ui-guidelines -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install simonliu-ai-product/open-doc viewer-ui-guidelines --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/simonliu-ai-product/open-doc.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/viewer-ui-guidelines .cursor/skills/viewer-ui-guidelines && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "viewer-ui-guidelines" agent skill from https://github.com/simonliu-ai-product/open-doc/tree/main/.agents/skills/viewer-ui-guidelines into .cursor/skills/viewer-ui-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "viewer-ui-guidelines", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/simonliu-ai-product/open-doc.git --path .agents/skills/viewer-ui-guidelines--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add simonliu-ai-product/open-doc --skill viewer-ui-guidelines -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install simonliu-ai-product/open-doc viewer-ui-guidelines --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/simonliu-ai-product/open-doc.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/viewer-ui-guidelines .gemini/skills/viewer-ui-guidelines && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "viewer-ui-guidelines" agent skill from https://github.com/simonliu-ai-product/open-doc/tree/main/.agents/skills/viewer-ui-guidelines into .gemini/skills/viewer-ui-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "viewer-ui-guidelines", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install simonliu-ai-product/open-doc viewer-ui-guidelinesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add simonliu-ai-product/open-doc --skill viewer-ui-guidelines -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/simonliu-ai-product/open-doc.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/viewer-ui-guidelines .github/skills/viewer-ui-guidelines && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "viewer-ui-guidelines" agent skill from https://github.com/simonliu-ai-product/open-doc/tree/main/.agents/skills/viewer-ui-guidelines into .github/skills/viewer-ui-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "viewer-ui-guidelines", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add simonliu-ai-product/open-doc --skill viewer-ui-guidelines -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install simonliu-ai-product/open-doc viewer-ui-guidelines --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/simonliu-ai-product/open-doc.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/viewer-ui-guidelines .opencode/skills/viewer-ui-guidelines && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "viewer-ui-guidelines" agent skill from https://github.com/simonliu-ai-product/open-doc/tree/main/.agents/skills/viewer-ui-guidelines into .opencode/skills/viewer-ui-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "viewer-ui-guidelines", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
viewer-ui-guidelinesDesign and accessibility rules for the open-doc viewer chrome — the browser shell, sidebars, thumbnail rail, outline, assets and design panels, inspector overlay, and menus.
Viewer UI Guidelines is an agent skill from simonliu-ai-product/open-doc. Design and accessibility rules for the open-doc viewer chrome — the browser shell, sidebars, thumbnail rail, outline, assets and design panels, inspector overlay, and menus. Use when building or reviewing UI under packages/core/src/app that surrounds a document. Does not apply to the printed page itself, which is governed by print-layout-review.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Frontend & Design. The repository describes itself as: The document framework built for agents — write reports as React, get real A4 pages, an outline, page numbers, and a PDF. The licence is MIT.
10 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit af6095d. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Viewer UI Guidelines loads about 1.6k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 870 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from simonliu-ai-product/open-doc at commit af6095d, republished under its MIT licence (© simonliu-ai-product). 870 words, ~1,561 tokens.
.claude/skills/viewer-ui-guidelines/SKILL.md (or your agent's skills folder).The chrome is everything that is not the sheet: the shell, the rails, the panels, the menus. It has one job — keep the paper the loudest thing on screen and get out of the way. Judge it against that, not against how interesting it looks in a screenshot.
The page is the subject. The sheet sits on --canvas; the chrome sits on --background. Chrome never competes with the document for contrast, saturation, or motion. A control that draws the eye away from the page during reading is a defect regardless of how well it's made.
Tokens, not literals. Colour comes from the theme tokens defined in app/styles.css — --background, --foreground, --canvas, --muted, --muted-foreground, --accent, --accent-foreground, --primary, --primary-foreground, --border. A raw hex, rgb(), or Tailwind palette colour (bg-zinc-800) in chrome code is a finding: it won't follow the dark theme.
Both themes, always. Dark mode is the .dark class variant wired through next-themes; every token has a dark value. Any new surface is checked in both. Never define a colour only inside one branch.
Document colours are not chrome colours. --od-* variables (--od-bg, --od-text, --od-accent, --od-margin, --od-size-*) belong to the document's design system and are scoped to the page. Chrome must never read them, and page content must never read chrome tokens — that leak is what makes a printed page follow the viewer's dark mode.
Keyboard first. Every action reachable by mouse is reachable by keyboard. Focus is visible (never outline: none without a replacement), focus order follows visual order, and focus is trapped and restored around any panel or menu that overlays content. New shortcuts are documented where the user can find them, and must not collide with browser or OS bindings.
Real semantics. Buttons are <button>, links are <a>, lists are lists. A <div onClick> is a finding. Interactive controls carry an accessible name — an icon-only control needs aria-label. Panels that appear over content announce themselves (role="dialog" + labelled) or are inert to assistive tech if purely decorative.
Motion is functional or absent. The viewer is a reading tool. Animate only to explain a spatial relationship (a panel sliding from its edge, a rail expanding). Duration stays under 200ms, easing is ease-out, and only transform/opacity animate. Animating width/height/top/left, or animating anything on a keyboard-triggered action, is a finding. Honour prefers-reduced-motion by dropping movement while keeping opacity.
Hit targets and pointer gating. Interactive targets are at least 32×32 CSS px in dense rails, 40×40 elsewhere. Hover-revealed affordances are gated behind @media (hover: hover) and (pointer: fine) and must have a non-hover path.
State is honest. Loading, empty, and error states are designed, not accidental. Prefer a hairline progress affordance over a spinner for short waits; prefer an empty state that says what to do next over a blank rail. Never show a stale page count while re-measuring — show the previous value or nothing, never a wrong one.
Density is deliberate. The rails are dense by design: small type, tight leading, generous hit targets. Chrome type stays in the small end of the scale (text-xs / text-sm) so it reads as instrumentation, not content. Do not import the document's type scale into the chrome.
routes/home-shell.tsx holds the left sidebar (nav counts, folders, theme toggle) and passes folder state to routes through the outlet context. A route that fetches the folders manifest itself is a finding.components/doc-sidebar.tsx is the left rail (thumbnails / outline), pages scroll in the middle, the design panel docks right. New surfaces pick one of those three homes rather than inventing a fourth region.app/components/ui/ is the primitive layer. Shared, unopinionated pieces only (currently menu.tsx). Feature-specific UI lives next to its feature, not here.lib/inspector/inline-edit.ts); the rendered node is only hidden. Anything shown before Save must be visibly unsaved — the dashed pending frame and the unsaved-edits bar — and Discard must restore exactly what was rendered. After Save, what you see is the re-render from source; the clone only bridges the reload.--od-*, or page content reading chrome tokens<div>/<span> with a click handler; icon button with no accessible nameoutline: none without a visible replacementease-in, or animating layout propertiesA findings table (Before / After / Why), then a verdict grouped by: accessibility blocks, theming correctness, hierarchy & density, motion, structure fit. Cite file:line. Block on any keyboard/screen-reader regression, any hardcoded colour, or any chrome/document token leak.
When building rather than reviewing: choose the boring, quiet option. The chrome's ceiling is "invisible"; there is no version of it that should be memorable.
© simonliu-ai-product, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/viewer-ui-guidelines of simonliu-ai-product/open-doc.
Open the folder on GitHubat commit af6095d
Viewer UI Guidelines next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Viewer UI Guidelines this skillsimonliu-ai-product/open-doc | 108 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Web Artifacts Builderanthropics/skills | 180k | 40 repos | ~769 | Automated safety check: Pass | Apache-2.0 | |
| React Doctormakeplane/plane | 61k | 12 repos | ~657 | Automated safety check: Pass | AGPL-3.0 | |
| Impeccablebestofjs/bestofjs | 3.1k | 26 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Figma Design System Builderwarpdotdev/warp | 65k | 2 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Web Interface Guidelines Reviewervercel-labs/openreview | 1.7k | 97 repos | ~308 | Automated safety check: Pass | None |
anthropics/skills
Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.
makeplane/plane
Scans React code for lint, accessibility, bundle size and architecture issues, reports a health score and checks that changes do not lower it.
bestofjs/bestofjs
A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…
warpdotdev/warp
Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.
vercel-labs/openreview
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…
anonaddy/anonaddy
Always invoke when the user's message includes 'tailwind' in any form.
simonliu-ai-product/open-doc
A skill your agent uses when the user asks to apply, process, or clear the comments they left in the open-doc inspector — phrases like "apply the comments", "apply my edits", "I left notes on the…
simonliu-ai-product/open-doc
Technical reference for writing or editing open-doc pages — file contract, the A4/B4/A3 page canvas, print type scale, the vertical budget that decides where a page breaks, tables, charts, table of…
simonliu-ai-product/open-doc
A skill your agent uses when the user wants to create, draft, author, or generate a new document, report, whitepaper, proposal, memo, or spec in this open-doc repo.
simonliu-ai-product/open-doc
Resolve which document, page, and (optionally) selected element the user is currently viewing in the open-doc dev server.
simonliu-ai-product/open-doc
Implementation patterns for the @open-doc/core runtime — the split between the viewer and the published bundle, virtual modules, the flow pipeline, the ops layer, dev-only plugins, and the…
simonliu-ai-product/open-doc
Reviews page layout, typography, and pagination code in open-doc against a print craft bar — the sheet is the deliverable, not the screen.
Categories
Design and accessibility rules for the open-doc viewer chrome — the browser shell, sidebars, thumbnail rail, outline, assets and design panels, inspector overlay, and menus. Viewer UI Guidelines is an agent skill from simonliu-ai-product/open-doc. Design and accessibility rules for the open-doc viewer chrome — the browser shell, sidebars, thumbnail rail, outline, assets and design panels, inspector overlay, and menus.
Viewer UI Guidelines fits situations like: reviewing UI under packages/core/src/app that surrounds a document.
Run `npx skills add simonliu-ai-product/open-doc --skill viewer-ui-guidelines -a claude-code`. Or copy the skill folder (.agents/skills/viewer-ui-guidelines in simonliu-ai-product/open-doc) into .claude/skills/viewer-ui-guidelines in your project. Claude Code loads it when a task matches its description.
Run `npx skills add simonliu-ai-product/open-doc --skill viewer-ui-guidelines -a codex`. Or copy the skill folder (.agents/skills/viewer-ui-guidelines in simonliu-ai-product/open-doc) into .agents/skills/viewer-ui-guidelines in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add simonliu-ai-product/open-doc --skill viewer-ui-guidelines -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/viewer-ui-guidelines, .gemini/skills/viewer-ui-guidelines, .github/skills/viewer-ui-guidelines and .opencode/skills/viewer-ui-guidelines in your project.
SKILL.md names no scripts, command-line tools or credentials: Viewer UI Guidelines is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Viewer UI Guidelines is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Viewer UI Guidelines: Web Artifacts Builder (anthropics/skills, 180k stars), React Doctor (makeplane/plane, 61k stars), Impeccable (bestofjs/bestofjs, 3.1k stars) and Figma Design System Builder (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
simonliu-ai-product (a GitHub organization) maintains it in simonliu-ai-product/open-doc, which has 108 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.
Source: simonliu-ai-product/open-doc on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.