Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Aie Web Audit

ASecurity

Runs a broad four-part health audit of any live website from just its URL — no repo or code access needed. Covers SEO/AEO signals, copy and messaging, UX and mobile usability, and a public-facing security surface scan. Produces an overall health score, category scores, top quick wins, and findings sorted by severity. Stack-agnostic — WordPress, Squarespace, Wix, Webflow, Shopify, plain HTML, or a custom React/Next/Vite build. Trigger on "audit my site," "check my website," "how's my site doin...

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsjavascriptpythongojavaphpreactnodegitdatabasebackend

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add mrhinkle/aienterprise-skills --skill aie-web-audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Aie Web Audit?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Aie Web Audit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mrhinkle-aie-web-audit/badge)](https://www.skillsdirectory.com/skills/mrhinkle-aie-web-audit)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: aie-web-audit
description: Runs a broad four-part health audit of any live website from just its URL — no repo or code access needed. Covers SEO/AEO signals, copy and messaging, UX and mobile usability, and a public-facing security surface scan. Produces an overall health score, category scores, top quick wins, and findings sorted by severity. Stack-agnostic — WordPress, Squarespace, Wix, Webflow, Shopify, plain HTML, or a custom React/Next/Vite build. Trigger on "audit my site," "check my website," "how's my site doing," "score my website," "what's wrong with my site," "review my site," "is my site any good," "site health check," or "review my WordPress/Squarespace/Wix site."
---

# Website Health Audit

A fast, broad first look at any live website. One URL in, one consolidated report out — health score, quick wins, and a fix roadmap across four dimensions. This is the wide-angle audit; when a dimension needs depth, hand off to the focused skills noted at the end.

## When to use this skill

The user has a live site and wants an honest overall read: what's working, what's broken, and what to fix first. No GitHub, no code handoff, no login required — the audit works from public pages only.

## Inputs

- A **live URL**. That's the minimum.
- Optional: specific pages or flows to prioritize; known concerns; the audience the site serves.

Fetch the URL and a few key public pages (home, about, primary product/service, contact). Analyze the rendered HTML and CSS. Client-side JavaScript state is only partially visible from a fetch — note that where it limits a finding.

## The four-part audit

Work through all four. For the full checkable item lists, read `reference/audit-areas.md`.

1. **SEO & AEO** — title/meta tags, heading hierarchy, Open Graph/social tags, JSON-LD schema, mobile signals, image alt text, URL structure, Core Web Vitals indicators, and answer-engine readiness. (For a deep SEO pass, use the `aie-web-seo` skill.)
2. **Copy & content** — headline hook, value proposition clarity ("can a stranger get it in 5 seconds?"), CTA strength and placement, readability, microcopy, and tone consistency.
3. **UX** — navigation depth (find anything in ~3 clicks), mobile responsiveness, visual hierarchy, tap-target size, line length and font size, and common anti-patterns (autoplay video, load-time pop-ups, ambiguous buttons).
4. **Security surface** — HTTPS enforcement, security headers (CSP, HSTS, X-Frame-Options, X-Content-Type-Options), mixed content, third-party script inventory, and presence of a privacy/cookie policy. This is a public-signal scan only — see limits below.

## Scoring

Score each of the four categories 0-100, then average for the overall health score. Interpret:

- **80-100** Strong — minor polish only.
- **65-79** Good — a few meaningful fixes.
- **50-64** Fair — clear gaps, solid quick wins available.
- **Below 50** Needs work — prioritize the critical findings.

## Output format

```
WEBSITE HEALTH AUDIT — {url}
Date: {date}

OVERALL HEALTH: {n}/100

CATEGORY SCORES
  SEO & AEO   {n}/100
  Copy        {n}/100
  UX          {n}/100
  Security    {n}/100

TOP QUICK WINS (high impact, low effort)
  1. {fix} — {effort estimate}
  ... (up to 5)

FINDINGS BY SEVERITY
  [Critical] security issues, broken functionality
  [Major]    significant SEO or UX problems
  [Minor]    good-to-fix issues
  [Cosmetic] polish

WHAT'S NEXT
  {which focused skill or action addresses each major finding}
```

Each finding names the exact page/element and a concrete fix. Keep the tone encouraging and specific: "62/100 is a solid base — these five changes could push it past 80." No shame; every site is a work in progress.

## What this audit cannot check

Be transparent. A public URL audit does **not** see:

- Server-side code quality (Node, Python, PHP, database queries).
- Database security or injection risk.
- Backend dependencies (packages, plugins, libraries).
- Full client-side JavaScript execution and dynamic state.
- Authenticated pages (admin panels, member dashboards).
- The complete sitemap — it samples public pages.
- Performance under real global load — it tests from one location.

For those, the focused skills go deeper: `aie-web-seo` (SEO/AEO), `aie-web-performance` (speed and Core Web Vitals), and `aie-web-qa` (does everything actually work).

Attribution

mrhinklemrhinkle
View sourceMore from mrhinkle →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →