Skip to content

Bhanunamikaze/Agentic-SEO-Skill

Deterministic LLM-first SEO audits for websites, blog posts, and GitHub repositories. Use this when the user asks to "perform SEO analysis", "run SEO audit", "analyze SEO", "check technical SEO", "review schema", "Core Web Vitals", "E-E-A-T", "hreflang", "GEO", "AEO", or GitHub repository SEO optimization. For full/page/repo audits, run bundled scripts for evidence and return prioritized, confidence-labeled fixes.

FileKindSize
SKILL.mdskill md19.4 KB
scripts/__init__.pyscript34 B
scripts/a11y_seo_checker.pyscript3.4 KB
scripts/ai_crawler_policy_matrix.pyscript2.2 KB
scripts/analyze_visual.pyexecutablescript6.5 KB
scripts/anchor_text_audit.pyscript7.7 KB
scripts/answer_block_scanner.pyscript3.9 KB
scripts/article_seo.pyscript27.1 KB
scripts/audit_runner.pyscript3.1 KB
scripts/broken_links.pyscript8.3 KB
scripts/cache_compression_checker.pyscript6.7 KB
scripts/canonical_checker.pyscript3.4 KB
scripts/capture_screenshot.pyexecutablescript4.4 KB
scripts/citation_readiness.pyscript5.1 KB
scripts/collection_page_checker.pyscript4.2 KB
scripts/competitor_gap.pyscript10.2 KB
scripts/content_decay_detector.pyscript6.2 KB
scripts/content_intent_matcher.pyscript5.4 KB
scripts/crawl_audit.pyscript7.2 KB
scripts/critical_request_chain.pyscript4.8 KB
scripts/duplicate_content.pyscript14.0 KB
scripts/eeat_signal_checker.pyscript5.5 KB
scripts/entity_checker.pyscript19.4 KB
scripts/env_loader.pyscript3.6 KB
scripts/external_link_quality.pyscript6.6 KB
scripts/faceted_nav_audit.pyscript3.3 KB
scripts/fetch_page.pyexecutablescript3.6 KB
scripts/finding_verifier.pyscript4.9 KB
scripts/font_audit.pyscript5.9 KB
scripts/freshness_checker.pyscript6.2 KB
scripts/generate_report.pyscript80.7 KB
scripts/github_api.pyscript12.8 KB
scripts/github_community_health.pyscript8.9 KB
scripts/github_competitor_research.pyscript17.2 KB
scripts/github_readme_lint.pyscript14.9 KB
scripts/github_repo_audit.pyscript21.0 KB
scripts/github_search_benchmark.pyscript7.7 KB
scripts/github_seo_report.pyscript32.0 KB
scripts/github_traffic_archiver.pyscript6.3 KB
scripts/github_weekly_scorecard.pyscript4.4 KB
scripts/gsc_checker.pyscript11.4 KB
scripts/hreflang_checker.pyscript24.2 KB
scripts/hreflang_sitemap_validator.pyscript6.4 KB
scripts/image_inventory.pyscript2.8 KB
scripts/image_weight_audit.pyscript4.8 KB
scripts/indexability_matrix.pyscript3.5 KB
scripts/indexnow_checker.pyscript9.4 KB
scripts/internal_links.pyscript10.5 KB
scripts/javascript_render_audit.pyscript2.9 KB
scripts/lcp_subparts.pyscript7.3 KB
scripts/lib/__init__.pyscript46 B
scripts/lib/safe_http.pyscript6.1 KB
scripts/lighthouse_runner.pyscript6.0 KB
scripts/link_profile.pyscript12.5 KB
scripts/llms_txt_checker.pyscript7.5 KB
scripts/llms_txt_generator.pyscript2.9 KB
scripts/local_seo_checker.pyscript3.7 KB
scripts/log_file_analyzer.pyscript6.0 KB
scripts/mobile_render_checker.pyscript6.9 KB
scripts/orphan_pages_from_sitemap.pyscript6.2 KB
scripts/pagespeed.pyscript12.9 KB
scripts/parse_html.pyexecutablescript12.2 KB
scripts/pre_commit_seo_check.shexecutablescript2.9 KB
scripts/product_schema_checker.pyscript4.9 KB
scripts/readability.pyscript14.5 KB
scripts/redirect_backlink_reclaim.pyscript5.7 KB
scripts/redirect_checker.pyscript6.2 KB
scripts/reference_freshness.pyexecutablescript2.9 KB
scripts/repo_docs_site_checker.pyscript5.7 KB
scripts/repo_file_inventory.pyscript3.6 KB
scripts/repo_release_seo.pyscript6.6 KB
scripts/repo_social_preview_checker.pyscript4.1 KB
scripts/repo_topic_suggester.pyscript6.3 KB
scripts/review_schema_checker.pyscript4.0 KB
scripts/rich_results_guard.pyscript3.4 KB
scripts/robots_checker.pyscript7.2 KB
scripts/robots_path_tester.pyscript1.8 KB
scripts/schema_diff.pyscript3.1 KB
scripts/schema_required_props.pyscript8.1 KB
scripts/schema_template_generator.pyscript5.4 KB
scripts/security_headers.pyscript6.8 KB
scripts/seo_common.pyscript14.1 KB
scripts/sitemap_checker.pyscript6.5 KB
scripts/sitemap_generator.pyscript3.4 KB
scripts/social_meta.pyscript8.7 KB
scripts/third_party_script_audit.pyscript4.7 KB
scripts/topical_cluster_mapper.pyscript6.4 KB
scripts/url_quality.pyscript2.5 KB
scripts/validate_schema.pyexecutablescript4.3 KB
scripts/validate_skill_inventory.pyexecutablescript4.8 KB
scripts/video_schema_checker.pyscript3.6 KB
scripts/visual_regression_snapshot.pyscript5.3 KB
scripts/x_robots_header_checker.pyscript2.0 KB

scripts/broken_links.py

View on GitHub
#!/usr/bin/env python3
"""
Check for broken links on a web page.

Crawls all links (internal + external) on a page, checks HTTP status.
Reports broken (4xx/5xx), redirected (3xx), and timeout links.

Usage:
    python broken_links.py https://example.com
    python broken_links.py https://example.com --json
    python broken_links.py https://example.com --internal-only
"""

import argparse
import json
import sys
from concurrent.futures import ThreadPoolExecutor, as_completed
from urllib.parse import urljoin, urlparse

try:
    import requests
except ImportError:
    print("Error: requests library required. Install with: pip install requests")
    sys.exit(1)

try:
    from bs4 import BeautifulSoup
except ImportError:
    print("Error: beautifulsoup4 library required. Install with: pip install beautifulsoup4")
    sys.exit(1)

try:
    from lib.safe_http import default_headers, safe_get, safe_head
except ImportError:
    from scripts.lib.safe_http import default_headers, safe_get, safe_head


HEADERS = default_headers()


def extract_links(html: str, base_url: str) -> list:
    """Extract all links from HTML content."""
    soup = BeautifulSoup(html, "html.parser")
    links = []
    seen = set()

    for tag in soup.find_all("a", href=True):
        href = tag["href"].strip()

        # Skip anchors, javascript, mailto, tel
        if href.startswith(("#", "javascript:", "mailto:", "tel:", "data:")):
            continue

        absolute = urljoin(base_url, href)
        if absolute in seen:
            continue
        seen.add(absolute)

        anchor_text = tag.get_text(strip=True)[:80] or "[no text]"
        links.append({
            "url": absolute,
            "anchor_text": anchor_text,
            "is_internal": urlparse(absolute).netloc == urlparse(base_url).netloc,
        })

    return links


def check_link(link: dict, timeout: int = 10) -> dict:
    """Check a single link's HTTP status."""
    url = link["url"]
    result = {**link, "status": None, "error": None, "redirect": None, "response_time_ms": None}

    try:
        resp = safe_head(url, timeout=timeout, headers=HEADERS, allow_redirects=True)

        # Some servers reject HEAD, fall back to GET
        if resp.status_code == 405:
            resp = safe_get(url, timeout=timeout, headers=HEADERS,
                            allow_redirects=True, stream=True)

        result["status"] = resp.status_code
        result["response_time_ms"] = round(resp.elapsed.total_seconds() * 1000)

        # Check if redirected
        if resp.history:
            result["redirect"] = {
                "from": url,
                "to": resp.url,
                "hops": len(resp.history),
                "codes": [r.status_code for r in resp.history],
            }

    except requests.exceptions.Timeout:
        result["error"] = "timeout"
    except requests.exceptions.ConnectionError:
        result["error"] = "connection_failed"
    except requests.exceptions.TooManyRedirects:
        result["error"] = "too_many_redirects"
    except requests.exceptions.RequestException as e:
        result["error"] = str(e)[:100]

    return result


def check_broken_links(url: str, internal_only: bool = False,
                       max_workers: int = 10, timeout: int = 10) -> dict:
    """
    Check all links on a page for broken links.

    Args:
        url: Page URL to check
        internal_only: Only check internal links
        max_workers: Concurrent request threads
        timeout: Per-request timeout in seconds

    Returns:
        Dictionary with all link check results
    """
    result = {
        "page_url": url,
        "total_links": 0,
        "checked": 0,
        "broken": [],
        "redirected": [],
        "timeout": [],
        "healthy": 0,
        "summary": {},
        "issues": [],
        "error": None,
    }

    # Fetch page
    try:
        resp = safe_get(url, timeout=15, headers=HEADERS)
        if resp.status_code != 200:
            result["error"] = f"Failed to fetch page: HTTP {resp.status_code}"
            return result
        html = resp.text
    except requests.exceptions.RequestException as e:
        result["error"] = f"Failed to fetch page: {e}"
        return result

    # Extract links
    links = extract_links(html, url)
    if internal_only:
        links = [l for l in links if l["is_internal"]]

    result["total_links"] = len(links)

    if not links:
        result["issues"].append("⚠️ No links found on page")
        return result

    # Check all links concurrently
    checked = []
    with ThreadPoolExecutor(max_workers=max_workers) as executor:
        futures = {executor.submit(check_link, link, timeout): link for link in links}
        for future in as_completed(futures):
            checked.append(future.result())

    result["checked"] = len(checked)

    for link in checked:
        status = link["status"]

        if link["error"]:
            if link["error"] == "timeout":
                result["timeout"].append(link)
            else:
                result["broken"].append(link)
        elif status and status >= 400:
            result["broken"].append(link)
        elif link["redirect"]:
            result["redirected"].append(link)
        else:
            result["healthy"] += 1

    # Generate summary
    result["summary"] = {
        "total": result["total_links"],
        "healthy": result["healthy"],
        "broken": len(result["broken"]),
        "redirected": len(result["redirected"]),
        "timeout": len(result["timeout"]),
    }

    # Generate issues
    if result["broken"]:
        result["issues"].append(
            f"🔴 {len(result['broken'])} broken link(s) found"
        )
    if result["timeout"]:
        result["issues"].append(
            f"⚠️ {len(result['timeout'])} link(s) timed out"
        )
    if result["redirected"]:
        chains = [l for l in result["redirected"]
                  if l.get("redirect", {}).get("hops", 0) > 1]
        if chains:
            result["issues"].append(
                f"⚠️ {len(chains)} redirect chain(s) detected (>1 hop)"
            )

    return result


def main():
    parser = argparse.ArgumentParser(description="Check for broken links on a page")
    parser.add_argument("url", help="Page URL to check")
    parser.add_argument("--json", "-j", action="store_true", help="Output as JSON")
    parser.add_argument("--internal-only", "-i", action="store_true",
                        help="Only check internal links")
    parser.add_argument("--workers", "-w", type=int, default=10,
                        help="Concurrent workers (default: 10)")
    parser.add_argument("--timeout", "-t", type=int, default=10,
                        help="Per-link timeout in seconds (default: 10)")

    args = parser.parse_args()
    result = check_broken_links(args.url, internal_only=args.internal_only,
                                max_workers=args.workers, timeout=args.timeout)

    if args.json:
        print(json.dumps(result, indent=2))
        return

    if result["error"]:
        print(f"Error: {result['error']}")
        sys.exit(1)

    print(f"Broken Link Check — {result['page_url']}")
    print("=" * 50)
    s = result["summary"]
    print(f"Total: {s['total']} | ✅ Healthy: {s['healthy']} | "
          f"🔴 Broken: {s['broken']} | ↪️ Redirected: {s['redirected']} | "
          f"⏱️ Timeout: {s['timeout']}")

    if result["broken"]:
        print(f"\n🔴 Broken Links:")
        for link in result["broken"]:
            status = link["status"] or link["error"]
            loc = "internal" if link["is_internal"] else "external"
            print(f"  [{status}] ({loc}) {link['url']}")
            print(f"         anchor: \"{link['anchor_text']}\"")

    if result["redirected"]:
        chains = [l for l in result["redirected"]
                  if l.get("redirect", {}).get("hops", 0) > 1]
        if chains:
            print(f"\n⚠️ Redirect Chains (>1 hop):")
            for link in chains:
                r = link["redirect"]
                print(f"  {link['url']}")
                print(f"    → {r['to']} ({r['hops']} hops: {r['codes']})")

    if result["timeout"]:
        print(f"\n⏱️ Timed Out:")
        for link in result["timeout"]:
            print(f"  {link['url']}")

    if result["issues"]:
        print(f"\nIssues:")
        for issue in result["issues"]:
            print(f"  {issue}")


if __name__ == "__main__":
    main()
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall