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/crawl_audit.py

View on GitHub
#!/usr/bin/env python3
"""Robots-aware shallow site crawler with SEO metadata checks."""

from __future__ import annotations

import argparse
import json
from collections import Counter, defaultdict, deque

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


def sitemap_seeds(site: str, timeout: int, limit: int) -> list[str]:
    seeds = []
    for sm in discover_sitemap_urls(site, timeout=timeout)[:10]:
        fetched = fetch_url(sm, timeout=timeout, max_bytes=8_000_000)
        if fetched.get("status") != 200:
            continue
        parsed = parse_sitemap_xml(fetched.get("text") or "", sm)
        if parsed["type"] == "urlset":
            seeds.extend(row["loc"] for row in parsed["urls"])
        elif parsed["type"] == "sitemapindex":
            for child in parsed["sitemaps"][:5]:
                child_fetch = fetch_url(child["loc"], timeout=timeout, max_bytes=8_000_000)
                child_parsed = parse_sitemap_xml(child_fetch.get("text") or "", child["loc"])
                seeds.extend(row["loc"] for row in child_parsed["urls"])
        if len(seeds) >= limit:
            break
    return list(dict.fromkeys(seeds))[:limit]


def crawl(site: str, max_pages: int = 50, depth: int = 2, timeout: int = 15, use_sitemap: bool = True) -> dict:
    start = normalize_url(site)
    robots = fetch_robots(start, timeout=timeout)
    parsed_robots = robots.get("parsed")
    queue = deque([(start, 0, "seed")])
    if use_sitemap:
        for seed in sitemap_seeds(start, timeout, max_pages):
            if same_host(start, seed):
                queue.append((seed, 0, "sitemap"))

    seen = set()
    pages = {}
    inbound = defaultdict(set)
    issues = []
    title_counter = Counter()
    desc_counter = Counter()
    h1_counter = Counter()

    while queue and len(seen) < max_pages:
        url, current_depth, source = queue.popleft()
        url = clean_url(url)
        if url in seen or not same_host(start, url):
            continue
        seen.add(url)
        allowed, robots_rule = robots_allowed(parsed_robots, url, "Googlebot")
        if not allowed:
            pages[url] = {"url": url, "source": source, "depth": current_depth, "robots_allowed": False, "robots_rule": robots_rule}
            issues.append(issue("warning", "URL blocked by robots.txt", url, robots_rule))
            continue
        fetched = fetch_url(url, timeout=timeout, max_bytes=2_000_000)
        page = {
            "url": url,
            "final_url": fetched.get("url"),
            "source": source,
            "depth": current_depth,
            "status": fetched.get("status"),
            "redirects": fetched.get("redirect_chain", []),
            "robots_allowed": True,
            "robots_rule": robots_rule,
            "title": None,
            "meta_description": None,
            "h1": [],
            "canonical": None,
            "meta_robots": None,
            "word_count": 0,
            "outlinks": [],
            "error": fetched.get("error"),
        }
        ctype = fetched.get("headers", {}).get("content-type", "")
        if fetched.get("status") and fetched["status"] >= 400:
            issues.append(issue("error", f"HTTP {fetched['status']}", url))
        if fetched.get("redirect_chain"):
            issues.append(issue("info", "URL redirects", url))
        if fetched.get("text") and "html" in ctype:
            html = parse_html(fetched["text"], fetched.get("url") or url)
            page.update({
                "title": html["title"],
                "meta_description": html["meta_description"],
                "h1": html["headings"]["h1"],
                "canonical": html["canonical"],
                "meta_robots": html["meta_robots"],
                "word_count": html["word_count"],
                "outlinks": [link["href"] for link in html["links"] if same_host(start, link["href"])],
            })
            if page["title"]:
                title_counter[page["title"]] += 1
            else:
                issues.append(issue("warning", "Missing title", url))
            if page["meta_description"]:
                desc_counter[page["meta_description"]] += 1
            else:
                issues.append(issue("info", "Missing meta description", url))
            if page["h1"]:
                h1_counter[page["h1"][0]] += 1
            else:
                issues.append(issue("warning", "Missing H1", url))
            if page["meta_robots"] and "noindex" in page["meta_robots"].lower():
                issues.append(issue("warning", "Page has meta noindex", url, page["meta_robots"]))
            if page["canonical"] and not same_host(start, page["canonical"]):
                issues.append(issue("warning", "Cross-host canonical", url, page["canonical"]))

            if current_depth < depth:
                for link in page["outlinks"]:
                    clean = clean_url(link)
                    inbound[clean].add(url)
                    if clean not in seen:
                        queue.append((clean, current_depth + 1, "link"))
        pages[url] = page

    for label, counter in (("duplicate title", title_counter), ("duplicate meta description", desc_counter), ("duplicate H1", h1_counter)):
        for value, count in counter.items():
            if count > 1:
                issues.append(issue("warning", f"{label}: {count} pages", evidence=value[:160]))

    orphan_candidates = [url for url, page in pages.items() if page.get("source") == "sitemap" and not inbound.get(url) and url != start]
    for url in orphan_candidates[:50]:
        issues.append(issue("info", "Sitemap URL was not discovered through internal links in this crawl", url))

    result = {
        "site": start,
        "robots_url": robots["url"],
        "pages_crawled": len(pages),
        "max_depth": depth,
        "pages": pages,
        "status_counts": dict(Counter(str(p.get("status")) for p in pages.values())),
        "duplicates": {
            "titles": {k: v for k, v in title_counter.items() if v > 1},
            "meta_descriptions": {k: v for k, v in desc_counter.items() if v > 1},
            "h1": {k: v for k, v in h1_counter.items() if v > 1},
        },
        "orphan_candidates": orphan_candidates,
        "issues": issues,
    }
    return result


def main() -> None:
    parser = argparse.ArgumentParser(description="Run a pragmatic crawl audit")
    parser.add_argument("site")
    parser.add_argument("--max-pages", type=int, default=50)
    parser.add_argument("--depth", type=int, default=2)
    parser.add_argument("--timeout", type=int, default=15)
    parser.add_argument("--no-sitemap", action="store_true")
    parser.add_argument("--json", "-j", action="store_true")
    args = parser.parse_args()
    result = crawl(args.site, args.max_pages, args.depth, args.timeout, not args.no_sitemap)
    lines = [
        f"Crawl audit for {result['site']}",
        f"Pages crawled: {result['pages_crawled']}  Issues: {len(result['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