vercel-labs avatar

Web Design Guidelines

This pulls Vercel's Web Interface Guidelines from their GitHub repo and audits your code against them. You trigger it by asking Claude to review UI, check accessibility, or audit design. It fetches the latest rules each time so you're always checking against current standards, then outputs findings in a terse file:line format that's easy to scan. The guidelines themselves live in a separate repo, so you're basically getting Vercel's opinionated take on web best practices baked into your code reviews. Saves you from having to remember accessibility rules or manually cross-checking design patterns when you're deep in implementation.

skills.sh installs
440
GitHub stars
279
last updated
Aug 21, 2026

Install

$ npx -y skills add vercel-labs/agent-eval --skill web-design-guidelines --agent claude-code

Installs into .claude/skills of the current project.

Files

Web Interface Guidelines

Review files for compliance with Web Interface Guidelines.

How It Works

  1. Fetch the latest guidelines from the source URL below
  2. Read the specified files (or prompt user for files/pattern)
  3. Check against all rules in the fetched guidelines
  4. Output findings in the terse file:line format

Guidelines Source

Fetch fresh guidelines before each review:

https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md

Use WebFetch to retrieve the latest rules. The fetched content contains all the rules and output format instructions.

Usage

When a user provides a file or pattern argument:

  1. Fetch guidelines from the source URL above
  2. Read the specified files
  3. Apply all rules from the fetched guidelines
  4. Output findings using the format specified in the guidelines

If no files specified, ask the user which files to review.

Sponsors

Details

Repository
github.com/vercel-labs/agent-eval
Categories
Git & Pull Requests, Code Review & Quality, AI & Agent Building, Cloud & Infrastructure, Design & UI/UX
First seen
Jun 3, 2026

More from vercel-labs/agent-eval

All 3
1yeachan-heo avataromc-referenceyeachan-heo/oh-my-claudecodeOMC agent catalog, available tools, team pipeline routing, commit protocol, and skills registry. Auto-loads when delegating to agents, using OMC tools, orchestr439skills.sh installs
2jwynia avatargitea-workflowjwynia/agent-skillsOrchestrate agile development workflows for Gitea repositories using the tea CLI. Use when working with Gitea-hosted repos and asking to 'run the workflow', 'co416skills.sh installs
3feiskyer avatarcodex-skillfeiskyer/claude-code-settingsLeverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review. Triggers: "codex", "use gpt", "gpt-5", "let openai", "full-au411skills.sh installs
4miles990 avatarproject-managementmiles990/claude-software-skillsAgile methodologies, issue tracking, and team collaboration tools397skills.sh installs
5everyinc avatarsetupeveryinc/compound-engineering-pluginConfigure project-level settings for compound-engineering workflows. Currently a placeholder — review agent selection is handled automatically by ce:review.392skills.sh installs
6davila7 avatarskill-installerdavila7/claude-code-templatesInstall Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill391skills.sh installs