Agent skill

Frontend Checklist Global

by thedaviddias in thedaviddias/Front-End-Checklist

A skill your agent uses when auditing or improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point.

MITAuto-check passedFrontend & Design

Install Frontend Checklist Global

skills CLI
$ npx skills add thedaviddias/Front-End-Checklist --skill frontend-checklist-global -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install thedaviddias/Front-End-Checklist frontend-checklist-global --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/thedaviddias/Front-End-Checklist.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/frontend-checklist-global .claude/skills/frontend-checklist-global && rm -rf skills-src

Use ~/.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/

Facts

Skill name
frontend-checklist-global
GitHub stars
74k
Token cost
~3.2k tokens
SKILL.md length
1,629 words
Files
2 (incl. references)
Skills in repo
390
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when auditing or improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point.

  • Works in 5 steps: Start with review_code for pasted code,… → Use audit_url for a public page when you… → Narrow or expand scope with… → …
  • Improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point
  • SKILL.md covers Workflow, Audit Stance, Coverage Checklist and Rule-Derived Highlights, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Frontend Checklist Global is an agent skill from thedaviddias/Front-End-Checklist. Use when auditing or improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point.

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/categories.md`).

It sits in Frontend & Design. The repository describes itself as: 🗂 The essential checklist for modern web development, for humans and AI agents. The licence is MIT.

When your agent uses it

  • Improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point

Example prompts

  • “/frontend-checklist-global”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Start with review_code for pasted code, file contents, or focused code review.
  2. Use audit_url for a public page when you need rendered HTML audited quickly.
  3. Narrow or expand scope with search_rules, list_categories, get_workflow, or get_quick_reference.
  4. For each issue, use get_rule, fix_rule, or explain_rule to give exact remediation.
  5. If a checklist is a better fit than ad hoc search, use get_checklist_rules.

What it can do on your machine

Read from SKILL.md and the folder at commit e8d14d0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    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.

  • Network

    Links to these hosts (documentation or services it may open):

    • frontendchecklist.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Frontend Checklist Global loads about 3.2k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 38 tokens; SKILL.md has 1,629 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.3k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from thedaviddias/Front-End-Checklist at commit e8d14d0, republished under its MIT licence (© thedaviddias). 1,629 words, ~3,176 tokens.

Download SKILL.mdSave it as .claude/skills/frontend-checklist-global/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
frontend-checklist-global
description
Use when auditing or improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point.
metadata.category
global
metadata.priority
high
metadata.difficulty
intermediate
metadata.estimatedTime
30
metadata.source
frontendchecklist.io
metadata.url
https://frontendchecklist.io/mcp

Front-End Checklist Global Audit

This skill connects one entry point to all 386 Front-End Checklist rules. Use MCP retrieval instead of trying to recall rules from memory.

Workflow

  1. Start with review_code for pasted code, file contents, or focused code review.
  2. Use audit_url for a public page when you need rendered HTML audited quickly.
  3. Narrow or expand scope with search_rules, list_categories, get_workflow, or get_quick_reference.
  4. For each issue, use get_rule, fix_rule, or explain_rule to give exact remediation.
  5. If a checklist is a better fit than ad hoc search, use get_checklist_rules.

Audit Stance

  • Be conservative. Prefer fewer, stronger findings over speculative breadth.
  • Only report an issue when the code or markup shown supports it directly.
  • In small component or route audits, prefer the strongest 1-2 supported findings over listing every possible enhancement.
  • Do not infer business intent from a snippet alone. Example: do not assume a field is required unless the code or surrounding copy makes that explicit.
  • Do not treat alt="" as an issue by default; empty alt can be correct for decorative images.
  • When an image is explicitly decorative, prefer zero findings unless the snippet shows a concrete problem rather than a hypothetical optimization.
  • If you see an isolated decorative image like <img ... alt="" aria-hidden="true">, treat it as a zero-issue pattern unless the snippet also shows real evidence of layout instability.
  • Do not raise low-confidence preference tweaks as findings when the snippet is otherwise sound. Prefer silence over weak nitpicks.
  • Do not treat autocomplete="off" as a defect by itself unless the snippet shows a stronger user-harm or security reason to flag it.
  • In link-preview cards, decorative preview images and favicons may be safe when nearby visible text already names the destination.
  • Do not treat React or JSX fragments as full HTML documents unless the snippet includes real document context like <html>, <head>, or <body>.
  • When reviewing Next.js or metadata-driven page files, consider metadata, viewport, and generateMetadata APIs before claiming head-tag omissions.

Coverage Checklist

  • Forms: check labels, accessible button names, explicit button types, autocomplete hints, password-field autocomplete, and validation semantics that are explicit in the code.
  • Images: check width/height, loading, srcset/sizes, and whether image semantics are clearly meaningful or decorative. Do not assume tiny SVG logos or clearly decorative assets must be lazy-loaded, and do not demand explicit dimensions for tiny ornamental dividers unless the snippet shows a real layout-shift risk. If an image is both decorative and hidden from assistive tech, bias strongly toward no finding.
  • Metadata: check title placement, canonical-url behavior, meta descriptions, Open Graph coverage, and structured data only when the file is responsible for metadata.
  • Motion: check expensive animated properties, prefer transform/opacity, and require prefers-reduced-motion handling for persistent motion.
  • Motion: when counters or visual widgets animate every frame, assess both reduced-motion support and whether the animation strategy adds unnecessary main-thread work.
  • Security: check target="_blank" links for noopener noreferrer, insecure form actions, password input best practices, and blocking third-party scripts.
  • Structure: check duplicate ids, list semantics, and table headers conservatively. For simple tables, column-header associations are stronger findings than speculative row-header or outer-layout landmark issues.
  • Structure: when a visible heading already introduces a simple table, treat missing captions as a lower-confidence improvement than missing header associations.

Rule-Derived Highlights

Set explicit width and height on images
  • Reserve findings for meaningful content images; decorative micro-SVGs or ornament-only assets are low-priority exceptions when CSS already reserves stable space
  • Example low-risk exception: <img src="/divider.svg" alt="" aria-hidden="true"> should not be flagged on its own without evidence of visible layout shift
  • Always set width and height attributes on <img> matching the image's intrinsic dimensions
  • Pair with height: auto in CSS to keep the image fluid while preserving the aspect ratio
  • Missing dimensions are the leading cause of Cumulative Layout Shift (CLS) from images
Hide decorative elements from assistive technology
  • Use alt='' (empty) for decorative images—not alt='image' or missing alt
  • Add aria-hidden='true' to decorative SVGs and icons
  • Use CSS background-image for purely decorative visuals
  • Role='presentation' removes semantic meaning from elements
  • Do not automatically raise performance findings on decorative micro-assets unless the snippet shows real layout instability
Use transform and opacity for animations
  • Only transform and opacity can be composited on the GPU without triggering layout
  • Use will-change: transform sparingly to promote an element to its own compositor layer
  • Prefer CSS transitions and animations over JavaScript animation libraries for simple effects
  • Respect prefers-reduced-motion to disable animations for users who need it
Respect reduced motion preferences
  • Use prefers-reduced-motion media query to disable non-essential animations
  • Never flash content more than 3 times per second (seizure risk)
  • Replace motion with opacity/color transitions when reduced motion is enabled
  • Provide user controls to pause or disable animations
Use semantic table markup for screen readers
  • Use <th> elements for headers with scope='col' or scope='row'
  • Add <caption> to describe the table's purpose
  • Never use tables for layout—use CSS Grid or Flexbox instead
  • Use id/headers for complex tables with merged cells
  • For simple tables with a clear adjacent section heading, missing scope is often a stronger finding than missing <caption>
Define proper table headers
  • Use <th> for all table headers, not <td>
  • Apply scope="col" or scope="row" to clarify header relationship
  • Ensure every data cell is associated with at least one header
  • In simple tables, prefer fixing header associations before escalating to caption-level recommendations
  • Missing scope="col" on a straightforward header row is often the clearest first fix
Minimize costly DOM read/write operations
  • Never interleave DOM reads (offsetHeight, getBoundingClientRect) with DOM writes (style changes)
  • Batch all reads first, then all writes
  • Use requestAnimationFrame for visual updates
  • Use DocumentFragment or innerHTML for bulk DOM insertion
  • Avoid per-frame React state updates across many visible components when a simpler CSS or reduced-frequency approach would work
Validate forms accessibly
  • Associate error messages with fields using aria-describedby
  • Use aria-invalid to indicate validation state
  • Mark required fields programmatically with required or aria-required
  • Provide inline error messages near the field
  • Don't rely solely on color to indicate errors
Show full SKILL.md (650 more words)Show less
Secure password input fields
  • Use type='password' with correct autocomplete attribute
  • Provide accessible show/hide toggle for password visibility
  • Show password strength indicator with requirements
  • Never store or transmit passwords in plain text
  • Support password managers with proper input names
Provide visible custom focus indicators
  • Never use outline: none or outline: 0 without a visible :focus-visible replacement
  • Use :focus-visible instead of :focus to show indicators only during keyboard navigation
  • Focus indicators must have 3:1 contrast ratio against adjacent colors (WCAG 2.2)
  • Provide at least 2px solid outline with an offset for a high-quality focus ring
  • If a focus ring is drawn with pseudo-elements, verify it is anchored to the correct positioned element and not clipped by overflow: hidden

Known Safe Patterns

Decorative Divider
  • Safe example: <img src="/divider.svg" alt="" aria-hidden="true">
  • Treat this as a safe decorative pattern by default. Do not flag alt text or missing dimensions unless the snippet also shows a real layout-shift risk.
Client-Handled React Form
  • Safe example: <form onSubmit={event => event.preventDefault()}><label htmlFor="q">Search</label><input id="q" type="search" /></form>
  • Do not require method or action when client-side submit handling is explicit and the form controls are otherwise accessible.
Next Metadata API
  • Safe example: export async function generateMetadata() { return { title: 'Docs', description: 'Reference' } }
  • Do not infer missing canonical-url, meta description, or Open Graph tags just because literal <head> markup is absent from the component file.
Preview Card Images
  • Safe example: <img src={resource.image} alt="" className="object-cover" /><img src={favicon} alt="" width={20} height={20} />
  • In link-preview or resource-card UIs, decorative preview/favicons can legitimately use empty alt when adjacent text already provides the destination name. Do not invent responsive-image or layout-shift defects for tiny favicon assets without stronger evidence.
Aspect-Ratio Media Wrapper
  • Safe example: <div className="aspect-2/1 overflow-hidden"><img className="object-cover w-full h-full" ... /></div>
  • When a wrapper already reserves media space with a stable aspect ratio, do not automatically raise a missing dimensions finding for the child preview image.
Pseudo-Element Focus Ring
  • Safe example: focus-visible:outline-none focus-visible:after:ring-2 after:absolute after:inset-0
  • If focus styling depends on a pseudo-element, verify the ring is anchored to the correct positioned element. A removed native outline is only safe when the replacement ring is clearly reliable.
Per-Frame React Counter Animation
  • Safe example: requestAnimationFrame(animate); setCount(Math.floor(eased * target))
  • Repeated requestAnimationFrame state updates across multiple components are a concrete performance concern when shown directly in the code.
Simple Data Table Headers
  • Safe example: <thead><tr><th>Priority</th><th>Rule</th><th>Title</th></tr></thead>
  • For simple data tables, prefer conservative column-header findings before speculating about row headers or outer-layout landmarks.
Adjacent Heading + Table
  • Safe example: <h2>Issues</h2><table><thead>...</thead><tbody>...</tbody></table>
  • A nearby visible section heading may already provide table context. Prefer scope/header association findings before requiring a caption unless the table purpose is ambiguous.

Conflict Resolution

  • If decorative-image guidance and dimensions guidance conflict, decorative guidance wins unless the snippet shows visible layout instability.
  • Example zero-issue pattern: <img src="/divider.svg" alt="" aria-hidden="true"> in an isolated component should not be flagged for alt text or dimensions unless the snippet also shows real layout-shift evidence.
  • If a form is clearly handled client-side with onSubmit, do not require traditional server-post method or action attributes.
  • If a file uses Next.js metadata APIs, do not infer missing head tags from the absence of literal <meta> or canonical-url markup.

Coverage

  • accessibility: 89 rules (9 critical, 25 high)
  • css: 31 rules (10 high)
  • html: 34 rules (3 critical, 12 high)
  • i18n: 5 rules
  • images: 25 rules (1 critical, 15 high)
  • javascript: 26 rules (1 critical, 12 high)
  • performance: 43 rules (1 critical, 22 high)
  • privacy: 5 rules (2 high)
  • security: 22 rules (4 critical, 10 high)
  • seo: 93 rules (19 high)
  • testing: 13 rules (7 high)

Evaluation Standard

  • Prefer findings tied to exact files, routes, selectors, or code snippets.
  • Prioritize critical and high issues first.
  • Explain uncertainty instead of overstating when the snippet does not show enough context.
  • Avoid generic advice when the MCP tools can retrieve a rule or fix prompt.
  • When no issue is found automatically, use search_rules to broaden review coverage before concluding clean.

See references/categories.md for category coverage and tool routing.

MCP docs: https://frontendchecklist.io/mcp

© thedaviddias, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/frontend-checklist-global of thedaviddias/Front-End-Checklist.

  • SKILL.md
  • references/categories.md

Open the folder on GitHubat commit e8d14d0

Compare with similar skills

Frontend Checklist Global 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.

Frontend Checklist Global compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Frontend Checklist Global this skillthedaviddias/Front-End-Checklist74k—~3.2kAutomated safety check: PassMIT
Web Artifacts Builderanthropics/skills180k40 repos~769Automated safety check: PassApache-2.0
React Doctormakeplane/plane61k12 repos~657Automated safety check: PassAGPL-3.0
Impeccablebestofjs/bestofjs3.1k26 repos~2.6kAutomated safety check: PassMIT
Figma Design System Builderwarpdotdev/warp65k2 repos~4.4kAutomated safety check: PassAGPL-3.0
Web Interface Guidelines Reviewervercel-labs/openreview1.7k97 repos~308Automated safety check: PassNone

Similar skills

  • Web Artifacts Builder

    anthropics/skills

    Official

    Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.

    180k GitHub starsUsed in 40 repos~769 tokens
    Frontend & DesignAuto-check passed
  • React Doctor

    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.

    61k GitHub starsUsed in 12 repos~657 tokens
    Frontend & DesignAuto-check passed
  • Impeccable

    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…

    3.1k GitHub starsUsed in 26 repos~2.6k tokens
    Frontend & DesignAuto-check passed
  • Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.

    65k GitHub starsUsed in 2 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Web Interface Guidelines Reviewer

    vercel-labs/openreview

    Official

    Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…

    1.7k GitHub starsUsed in 97 repos~308 tokens
    Frontend & DesignAuto-check passed
  • Tailwindcss Development

    anonaddy/anonaddy

    Always invoke when the user's message includes 'tailwind' in any form.

    4.9k GitHub starsUsed in 10 repos~865 tokens
    Frontend & DesignAuto-check passed

More from thedaviddias/Front-End-Checklist

All 390 skills in this repo
  • Content Dates Audit

    thedaviddias/Front-End-Checklist

    Audits article and blog pages for visible publish dates, Article JSON-LD with datePublished and dateModified, and Open Graph time tags, then fixes what is missing.

    74k GitHub stars~691 tokensUpdated 5 days ago
    Auto-check passed
  • FAQPage Schema Markup

    thedaviddias/Front-End-Checklist

    Adds, checks and fixes FAQPage JSON-LD on pages with visible question-and-answer sections so it matches what readers see and can qualify for rich results.

    74k GitHub stars~774 tokensUpdated 5 days ago
    Auto-check passed
  • Favicon Audit and Setup

    thedaviddias/Front-End-Checklist

    Checks that a site's favicon is linked, reachable and large enough for Google search results, and sets up ICO, SVG and Apple touch icon files when they are missing.

    74k GitHub stars~731 tokensUpdated 5 days ago
    Auto-check passed
  • Content Freshness Signals

    thedaviddias/Front-End-Checklist

    Audits article pages for freshness signals, covering the Last-Modified header, Article JSON-LD dateModified and a visible last-updated date, and fixes mismatches.

    74k GitHub stars~741 tokensUpdated 5 days ago
    Auto-check passed
  • Geo Meta Tags Audit

    thedaviddias/Front-End-Checklist

    Audits and fixes geo.region, geo.placename and geo.position meta tags on regional pages, noting where they help (Bing) and where they do not (Google).

    74k GitHub stars~763 tokensUpdated 5 days ago
    Auto-check passed
  • Improve a Front-End Checklist Rule

    thedaviddias/Front-End-Checklist

    Scores and rewrites a Front-End Checklist rule MDX file against a scored quality rubric, replacing generic stub prompts with specific, actionable ones.

    74k GitHub stars~1.3k tokensUpdated 5 days ago
    Auto-check passed

Questions about Frontend Checklist Global

What does Frontend Checklist Global do?

A skill your agent uses when auditing or improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point. Frontend Checklist Global is an agent skill from thedaviddias/Front-End-Checklist. Use when auditing or improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point.

When should I use Frontend Checklist Global?

Frontend Checklist Global fits situations like: improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point.

How do I install Frontend Checklist Global in Claude Code?

Run `npx skills add thedaviddias/Front-End-Checklist --skill frontend-checklist-global -a claude-code`. Or copy the skill folder (skills/frontend-checklist-global in thedaviddias/Front-End-Checklist) into .claude/skills/frontend-checklist-global in your project. Claude Code loads it when a task matches its description.

How do I install Frontend Checklist Global in Codex?

Run `npx skills add thedaviddias/Front-End-Checklist --skill frontend-checklist-global -a codex`. Or copy the skill folder (skills/frontend-checklist-global in thedaviddias/Front-End-Checklist) into .agents/skills/frontend-checklist-global in your project. Codex loads it when a task matches its description.

Can I use Frontend Checklist Global in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add thedaviddias/Front-End-Checklist --skill frontend-checklist-global -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/frontend-checklist-global, .gemini/skills/frontend-checklist-global, .github/skills/frontend-checklist-global and .opencode/skills/frontend-checklist-global in your project.

What does Frontend Checklist Global need to run?

SKILL.md names no scripts, command-line tools or credentials: Frontend Checklist Global is instructions for the agent only.

Does Frontend Checklist Global access the network?

SKILL.md names 1 domain. As links in the text: frontendchecklist.io. This is read from the text; nothing was executed.

Is Frontend Checklist Global safe to install?

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.

What licence does Frontend Checklist Global use?

Frontend Checklist Global is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Frontend Checklist Global use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Frontend Checklist Global?

Skills that share tags, products or a category with Frontend Checklist Global: 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.

Who maintains Frontend Checklist Global?

thedaviddias (a GitHub user) maintains it in thedaviddias/Front-End-Checklist, which has 74,421 GitHub stars. The repository holds 390 skills in this directory. The repository was last updated on October 6, 2026.

Source: thedaviddias/Front-End-Checklist on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.