julyssaalexandrauriarteanccota/inventori/web-design-guidelines

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Audit UI code against Vercel Web Interface Guidelines for design, accessibility, and UX compliance. Use when: reviewing frontend PRs, auditing pages/components, and generating terse file:line findings.

Install

npx vskill@latest install julyssaalexandrauriarteanccota/inventori/web-design-guidelines

SKILL.md

Web Design Guidelines Audit

Objective

Audit UI code against Vercel Web Interface Guidelines with concise, actionable findings that are easy to remediate.

When To Use

  • Reviewing frontend pull requests before merge.
  • Auditing pages, layouts, and components for visual and interaction quality.
  • Catching accessibility, UX, and consistency regressions in production-facing UI.

Inputs

  1. One or more file paths, folders, or glob patterns.
  2. Optional context: product area, target device, design system constraints.

If no files are provided, ask the user which files to review before continuing.

Procedure

  1. Refresh the source of truth before each audit.
  • Fetch the latest Vercel guidelines from the remote repository before reviewing code.
  • If the primary remote document is unavailable, use the best available official fallback from the same repository and state that fallback in output.
  1. Resolve scope and files.
  • If arguments include explicit files, audit only those files.
  • If arguments include globs, expand and audit matching UI files.
  • If arguments are empty, prompt for files or patterns.
  1. Run a category-based review.
  • Design: typography scale, spacing rhythm, color contrast, hierarchy, visual clarity.
  • Accessibility: semantics, labels, keyboard flows, focus visibility, ARIA misuse, readable states.
  • UX: affordance clarity, feedback states, loading/empty/error states, responsiveness.
  1. Produce terse findings for fast remediation.
  • Output each issue on one line in this format:

path/to/file.ext:line | severity | rule | short fix

  • Keep severity to: high, medium, low.
  • Do not append narrative summaries or extra prose.
  • If no issue is found, return: No findings.
  1. Add completion checks.
  • Confirm every finding includes an exact file and line.
  • Remove duplicate findings that describe the same root issue.
  • Prioritize high-impact issues first, then medium, then low.

Decision Points

  • If guidelines cannot be fetched: continue with fallback and explicitly flag reduced confidence.
  • If requested files are missing: report unresolved paths and request corrected targets.
  • If generated findings are verbose: compress each finding to one line while preserving actionability.

Quality Criteria

  • Uses latest available remote guidelines at review time.
  • Findings are terse, scannable, and directly mappable to edits.
  • Covers design, accessibility, and UX in every audit.
  • Avoids generic advice; each finding points to concrete code.

Output Example

apps/web/src/app/(public)/page.tsx:42 | high | Missing visible focus state on primary CTA | Add :focus-visible style with >= 3:1 contrast ring. apps/web/src/components/forms/contact-form.tsx:88 | medium | Input lacks associated label | Add <label htmlFor> and matching id.

Example Prompts

  • /web-design-guidelines apps/web/src/app/**
  • /web-design-guidelines apps/web/src/components/**/*.tsx
  • /web-design-guidelines Audit checkout and support pages for accessibility and UX regressions.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/julyssaalexandrauriarteanccota/inventori/web-design-guidelines/badge)](https://verified-skill.com/skills/julyssaalexandrauriarteanccota/inventori/web-design-guidelines)

Something wrong with this skill or its page? Tell us.