claude-force: Skill for Claude Code

.claude/skills/seo-audit-checklist/SKILL.md

seo-audit-checklist is a skill for Claude Code from khanh-vu/claude-force. It costs 0 tokens per session (4,173 once invoked), scanned A, original, MIT.

A checklist and Python script for reviewing a website's technical search-engine setup. It checks items such as page titles, descriptions, headings, images, canonical links, structured data, and social-sharing metadata.

In plain words
What is it for?
Use it to audit a website URL, identify technical SEO problems by severity, and produce recommendations for fixing page metadata, headings, images, indexing signals, structured data, and sharing previews.
Why use it?
It helps find website issues that can make pages harder for search engines to understand or index. Automated checks provide a repeatable starting point for an SEO review.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is khanh-vu/claude-force's own configuration. It tells Claude Code how to work on claude-force itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-force configures →

Reuse

Borrowing it

Nothing to install: this file belongs to khanh-vu/claude-force. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/khanh-vu/claude-force/main/.claude/skills/seo-audit-checklist/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/khanh-vu/claude-force

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for seo-audit-checklist

README.md
[![agentmods](https://agentmods.dev/badge/skills/khanh-vu/claude-force/seo-audit-checklist/github.svg)](https://agentmods.dev/skills/khanh-vu/claude-force/seo-audit-checklist)
Your own site
<a href="https://agentmods.dev/skills/khanh-vu/claude-force/seo-audit-checklist"><img src="https://agentmods.dev/badge/skills/khanh-vu/claude-force/seo-audit-checklist/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for seo-audit-checklist

Your own site · 80×15
<a href="https://agentmods.dev/skills/khanh-vu/claude-force/seo-audit-checklist"><img src="https://agentmods.dev/badge/skills/khanh-vu/claude-force/seo-audit-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,173 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.04173
Opus 5 $0.00000 $0.02086
Sonnet 5 $0.00000 $0.00835
Haiku 4.5 $0.00000 $0.00417

Measured 11d ago against content hash a933cc642e3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

seo-audit-checklist scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

from urllib.parse import urlparse, urljoin
.claude/skills/seo-audit-checklist/SKILL.md · 556 lines

How it starts

The opening of the file, as written. The whole thing — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SEO Audit Checklist

Comprehensive patterns and automation for conducting technical SEO audits and identifying optimization opportunities.

Automated SEO Audit Script

import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse, urljoin
import json
from typing import Dict, List, Set

class SEOAuditor:
    """Automated SEO audit checker"""

    def __init__(self, url: str):
        self.url = url
        self.domain = urlparse(url).netloc
        self.issues = {
            "critical": [],
            "high": [],
            "medium": [],
            "low": []
        }
        self.recommendations = []

    def audit(self) -> Dict:
        """Run complete SEO audit"""
        try:
            response = requests.get(self.url, timeout=10)
            self.soup = BeautifulSoup(response.text, 'html.parser')

            # Run all checks
            self.check_title_tag()
            self.check_meta_description()
            self.check_heading_hierarchy()
            self.check_images()
            self.check_canonical()
            self.check_robots_meta()
            self.check_structured_data()
            self.check_open_graph()
            self.check_mobile_viewport()
            self.check_https()

            return {
                "url": self.url,
                "issues": self.issues,
                "recommendations": self.recommendations,
                "score": self._calculate_score()
            }
        except Exception as e:
            return {"error": str(e)}

    def check_title_tag(self):
        """Validate title tag"""
        title = self.soup.find('title')

        if not title:
            self.issues["critical"].append({
                "type": "missing_title",
                "message": "Missing <title> tag",
                "fix": "Add <title> tag with 50-60 characters"
            })
        elif title:
            title_text = title.string.strip() if title.string else ""
            length = len(title_text)

            if length < 30:
                self.issues["high"].append({
                    "type": "title_too_short",
                    "message": f"Title too short ({length} chars)",
                    "current": title_text,
                    "fix": "Expand title to 50-60 characters"
                })
            elif length > 60:
                self.issues["medium"].append({
                    "type": "title_too_long",
                    "message": f"Title too long ({length} chars)",
                    "current": title_text,
                    "fix": "Reduce title to 50-60 characters"
                })

    def check_meta_description(self):
        """Validate meta description"""
        meta_desc = self.soup.find('meta', attrs={'name': 'description'})

        if not meta_desc or not meta_desc.get('content'):
            self.issues["high"].append({
                "type": "missing_meta_description",
                "message": "Missing meta description",
                "fix": "Add meta description (150-160 characters)"
            })
        else:
            content = meta_desc.get('content', '').strip()
            length = len(content)

            if length < 120:
                self.issues["medium"].append({
                    "type": "meta_desc_too_short",
                    "message": f"Meta description too short ({length} chars)",
                    "fix": "Expand to 150-160 characters"
                })
            elif length > 160:
                self.issues["medium"].append({
                    "type": "meta_desc_too_long",
                    "message": f"Meta description too long ({length} chars)",
                    "fix": "Reduce to 150-160 characters"
                })

    def check_heading_hierarchy(self):
        """Check H1-H6 hierarchy"""
        h1_tags = self.soup.find_all('h1')

        if len(h1_tags) == 0:
            self.issues["high"].append({
                "type": "missing_h1",
                "message": "No H1 tag found",
                "fix": "Add exactly one H1 tag per page"
            })
        elif len(h1_tags) > 1:
            self.issues["medium"].append({
                "type": "multiple_h1",
                "message": f"Multiple H1 tags found ({len(h1_tags)})",
                "fix": "Use only one H1 per page"
            })

        # Check for heading gaps
        heading_levels = []
        for i in range(1, 7):
            if self.soup.find(f'h{i}'):
                heading_levels.append(i)

        for i in range(len(heading_levels) - 1):
            if heading_levels[i+1] - heading_levels[i] > 1:
                self.issues["low"].append({
                    "type": "heading_hierarchy_gap",
                    "message": f"Heading hierarchy skips from H{heading_levels[i]} to H{heading_levels[i+1]}",
                    "fix": "Use sequential heading levels"
                })

    def check_images(self):
        """Check image optimization"""
        images = self.soup.find_all('img')

        for img in images:
            # Check alt text
            if not img.get('alt'):
                self.issues["high"].append({
                    "type": "missing_alt_text",
                    "message": f"Image missing alt text: {img.get('src', 'unknown')}",
                    "fix": "Add descriptive alt text to all images"
                })

            # Check for explicit dimensions
            if not img.get('width') or not img.get('height'):
                self.issues["medium"].append({
                    "type": "missing_image_dimensions",
                    "message": f"Image missing width/height: {img.get('src', 'unknown')}",
                    "fix": "Add explicit width and height to prevent CLS"
                })

            # Check for lazy loading
            if not img.get('loading'):
                self.issues["low"].append({
                    "type": "missing_lazy_loading",
                    "message": f"Image missing lazy loading: {img.get('src', 'unknown')}",
                    "fix": "Add loading='lazy' for below-fold images"
                })

    def check_canonical(self):
        """Check canonical URL"""
        canonical = self.soup.find('link', rel='canonical')

        if not canonical:
            self.issues["medium"].append({
                "type": "missing_canonical",
                "message": "Missing canonical link tag",
                "fix": "Add <link rel='canonical' href='...'>"
            })
        elif canonical:
            href = canonical.get('href', '')
            if not href.startswith('http'):
                self.issues["high"].append({
                    "type": "invalid_canonical",
                    "message": "Canonical URL is not absolute",
                    "current": href,
                    "fix": "Use absolute URL for canonical tag"
                })

    def check_robots_meta(self):
        """Check robots meta tag"""
        robots = self.soup.find('meta', attrs={'name': 'robots'})

        if robots:
            content = robots.get('content', '').lower()
            if 'noindex' in content:
                self.issues["critical"].append({
                    "type": "noindex_found",
                    "message": "Page has noindex directive",
                    "fix": "Remove noindex if page should be indexed"
                })
            if 'nofollow' in content:
                self.issues["high"].append({
                    "type": "nofollow_found",
                    "message": "Page has nofollow directive",
                    "fix": "Remove nofollow if links should be followed"
                })

    def check_structured_data(self):
        """Check for structured data"""
        json_ld = self.soup.find_all('script', type='application/ld+json')

        if not json_ld:
            self.issues["medium"].append({
                "type": "missing_structured_data",
                "message": "No structured data found",
                "fix": "Add Schema.org JSON-LD structured data"
            })
        else:
            for script in json_ld:
                try:
                    data = json.loads(script.string)
                    if '@context' not in data:
                        self.issues["high"].append({
                            "type": "invalid_structured_data",
                            "message": "Structured data missing @context",
                            "fix": "Add @context: 'https://schema.org'"
                        })
                except json.JSONDecodeError:
                    self.issues["high"].append({
                        "type": "invalid_json_ld",
                        "message": "Invalid JSON-LD syntax",
                        "fix": "Fix JSON-LD syntax errors"
                    })

    def check_open_graph(self):
        """Check Open Graph tags"""
        required_og = ['og:title', 'og:description', 'og:image', 'og:url']
        missing = []

        for prop in required_og:
            if not self.soup.find('meta', property=prop):
                missing.append(prop)

        if missing:
            self.issues["medium"].append({
                "type": "missing_open_graph",
                "message": f"Missing Open Graph tags: {', '.join(missing)}",
                "fix": "Add all required Open Graph meta tags"
            })

    def check_mobile_viewport(self):
        """Check mobile viewport meta tag"""
        viewport = self.soup.find('meta', attrs={'name': 'viewport'})

        if not viewport:
            self.issues["critical"].append({
                "type": "missing_viewport",
                "message": "Missing viewport meta tag",
                "fix": "Add <meta name='viewport' content='width=device-width, initial-scale=1'>"
            })

    def check_https(self):
        """Check if site uses HTTPS"""
        if not self.url.startswith('https://'):
            self.issues["critical"].append({
                "type": "not_https",
                "message": "Site not using HTTPS",
                "fix": "Implement SSL certificate and redirect HTTP to HTTPS"
            })

    def _calculate_score(self) -> int:
        """Calculate SEO score (0-100)"""
        weights = {"critical": -20, "high": -10, "medium": -5, "low": -2}
        deductions = sum(
            weights[severity] * len(issues)
            for severity, issues in self.issues.items()
        )
        return max(0, 100 + deductions)


# Usage example
def run_seo_audit(url: str) -> Dict:
    """Run comprehensive SEO audit on URL"""
    auditor = SEOAuditor(url)
    results = auditor.audit()

    # Print summary
    print(f"SEO Score: {results['score']}/100")
    print(f"\nCritical Issues: {len(results['issues']['critical'])}")
    print(f"High Priority: {len(results['issues']['high'])}")
    print(f"Medium Priority: {len(results['issues']['medium'])}")
    print(f"Low Priority: {len(results['issues']['low'])}")

    return results

Read the full file on GitHub · 556 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 556 lines · 0 tokens per session scan A a933cc642e3b

Subscribe to this mod's changes

seo-audit-checklist is a skill published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,173 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens