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/sitemap_checker.py

View on GitHub
#!/usr/bin/env python3
"""Discover and validate XML sitemaps."""

from __future__ import annotations

import argparse
import json
import re
from datetime import datetime, timezone

from seo_common import (
    discover_sitemap_urls,
    fetch_url,
    issue,
    normalize_url,
    parse_html,
    parse_sitemap_xml,
    print_json_or_text,
    same_host,
)


def check_sitemaps(site_url: str, sitemap_urls: list[str] | None = None, fetch_urls: bool = False, timeout: int = 15, max_urls: int = 100) -> dict:
    sitemap_urls = sitemap_urls or discover_sitemap_urls(site_url, timeout=timeout)
    result = {
        "site": normalize_url(site_url),
        "sitemaps_checked": [],
        "urls": [],
        "summary": {"sitemaps": 0, "urls": 0, "indexes": 0, "issues": 0},
        "issues": [],
    }
    queue = list(dict.fromkeys(sitemap_urls))
    seen_sitemaps = set()
    seen_urls = set()

    while queue and len(seen_sitemaps) < 25:
        sm_url = normalize_url(queue.pop(0), site_url)
        if sm_url in seen_sitemaps:
            continue
        seen_sitemaps.add(sm_url)
        fetched = fetch_url(sm_url, timeout=timeout, max_bytes=8_000_000)
        entry = {
            "url": sm_url,
            "status": fetched.get("status"),
            "final_url": fetched.get("url"),
            "redirects": fetched.get("redirect_chain", []),
            "type": None,
            "url_count": 0,
            "sitemap_count": 0,
            "error": fetched.get("error"),
        }
        if fetched.get("status") != 200:
            result["issues"].append(issue("error", f"Sitemap returned HTTP {fetched.get('status')}", sm_url, fetched.get("error")))
            result["sitemaps_checked"].append(entry)
            continue
        parsed = parse_sitemap_xml(fetched.get("text") or "", sm_url)
        entry["type"] = parsed["type"]
        entry["error"] = parsed["error"]
        entry["url_count"] = len(parsed["urls"])
        entry["sitemap_count"] = len(parsed["sitemaps"])
        if parsed["error"]:
            result["issues"].append(issue("error", f"Invalid sitemap XML: {parsed['error']}", sm_url))
        if parsed["type"] == "sitemapindex":
            result["summary"]["indexes"] += 1
            queue.extend(item["loc"] for item in parsed["sitemaps"])
        if parsed["type"] == "urlset" and len(parsed["urls"]) > 50000:
            result["issues"].append(issue("error", "Sitemap exceeds 50,000 URL limit", sm_url, str(len(parsed["urls"]))))

        for row in parsed["urls"]:
            loc = row["loc"]
            if loc in seen_urls:
                result["issues"].append(issue("warning", "Duplicate URL in sitemap set", loc))
                continue
            seen_urls.add(loc)
            url_entry = {"url": loc, **{k: v for k, v in row.items() if k != "loc"}, "checks": {}}
            if not loc.startswith("https://"):
                result["issues"].append(issue("warning", "Sitemap URL is not HTTPS", loc))
            if not same_host(site_url, loc):
                result["issues"].append(issue("warning", "Sitemap URL is cross-host", loc))
            if not row.get("lastmod"):
                result["issues"].append(issue("info", "Sitemap URL missing lastmod", loc))
            elif not re.match(r"^\d{4}-\d{2}-\d{2}", row["lastmod"]):
                result["issues"].append(issue("warning", "Sitemap lastmod is not ISO-like", loc, row["lastmod"]))
            elif row["lastmod"][:10] > datetime.now(timezone.utc).date().isoformat():
                result["issues"].append(issue("warning", "Sitemap lastmod is in the future", loc, row["lastmod"]))

            if fetch_urls and len(result["urls"]) < max_urls:
                page = fetch_url(loc, timeout=timeout, max_bytes=1_000_000)
                url_entry["checks"]["status"] = page.get("status")
                url_entry["checks"]["final_url"] = page.get("url")
                url_entry["checks"]["redirects"] = page.get("redirect_chain", [])
                if page.get("status") and page["status"] >= 400:
                    result["issues"].append(issue("error", f"Sitemap URL returns HTTP {page['status']}", loc))
                if page.get("redirect_chain"):
                    result["issues"].append(issue("warning", "Sitemap URL redirects", loc, " -> ".join(page["redirect_chain"] + [page.get("url", "")])))
                ctype = page.get("headers", {}).get("content-type", "")
                if page.get("text") and "html" in ctype:
                    html = parse_html(page["text"], page.get("url") or loc)
                    url_entry["checks"]["meta_robots"] = html.get("meta_robots")
                    url_entry["checks"]["canonical"] = html.get("canonical")
                    if html.get("meta_robots") and "noindex" in html["meta_robots"].lower():
                        result["issues"].append(issue("error", "Sitemap URL has meta noindex", loc, html["meta_robots"]))
                    if html.get("canonical") and normalize_url(html["canonical"]) != normalize_url(page.get("url") or loc):
                        result["issues"].append(issue("warning", "Canonical does not match sitemap URL", loc, html["canonical"]))
            result["urls"].append(url_entry)
        result["sitemaps_checked"].append(entry)

    result["summary"]["sitemaps"] = len(result["sitemaps_checked"])
    result["summary"]["urls"] = len(result["urls"])
    result["summary"]["issues"] = len(result["issues"])
    return result


def main() -> None:
    parser = argparse.ArgumentParser(description="Discover and validate XML sitemaps")
    parser.add_argument("site", help="Site URL")
    parser.add_argument("--sitemap", action="append", help="Explicit sitemap URL; can be repeated")
    parser.add_argument("--fetch-urls", action="store_true", help="Fetch sitemap URLs for status/noindex/canonical checks")
    parser.add_argument("--max-urls", type=int, default=100, help="Max sitemap URLs to fetch when --fetch-urls is used")
    parser.add_argument("--timeout", type=int, default=15)
    parser.add_argument("--json", "-j", action="store_true", help="Output JSON")
    args = parser.parse_args()
    result = check_sitemaps(args.site, args.sitemap, args.fetch_urls, args.timeout, args.max_urls)
    lines = [
        f"Sitemap check for {result['site']}",
        f"Sitemaps: {result['summary']['sitemaps']}  URLs: {result['summary']['urls']}  Issues: {result['summary']['issues']}",
    ] + [f"[{i['severity']}] {i['message']}: {i.get('url') or ''}" for i in result["issues"][:25]]
    print_json_or_text(result, args.json, lines)


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