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/citation_readiness.py

View on GitHub
#!/usr/bin/env python3
"""Assess citation and entity readiness for AI answers."""

from __future__ import annotations

import argparse
import json
import os
import re
from urllib.parse import urlparse

from seo_common import load_html, parse_html


CLAIM_RE = re.compile(
    r"(\d+(?:\.\d+)?%|\$[\d,.]+|\b(?:20\d{2}|19\d{2})\b|"
    r"\b(?:study|research|survey|report|data|according to|found that|shows that|largest|first|only|most)\b)",
    re.I,
)
HIGH_TRUST_HOST_RE = re.compile(
    r"((^|\.)gov(\.|$)|(^|\.)edu$|who\.int$|nih\.gov$|cdc\.gov$|worldbank\.org$|oecd\.org$|wikipedia\.org$)",
    re.I,
)


def _load_source(source: str, timeout: int) -> tuple[str, str, dict]:
    if os.path.exists(source):
        with open(source, "r", encoding="utf-8") as fh:
            return fh.read(), "", {"url": source, "status": None, "headers": {}, "error": None}
    return load_html(source, timeout=timeout)


def _walk_json(value):
    if isinstance(value, dict):
        yield value
        for child in value.values():
            yield from _walk_json(child)
    elif isinstance(value, list):
        for child in value:
            yield from _walk_json(child)


def _schema_entity_signals(schema_items: list) -> dict:
    names = set()
    same_as = set()
    types = set()
    for item in schema_items:
        for node in _walk_json(item):
            if node.get("@type"):
                types.add(str(node["@type"]))
            if node.get("name"):
                names.add(str(node["name"]))
            value = node.get("sameAs")
            if isinstance(value, str):
                same_as.add(value)
            elif isinstance(value, list):
                same_as.update(str(v) for v in value)
    return {"types": sorted(types), "names": sorted(names), "sameAs": sorted(same_as)}


def check_citation_readiness(source: str, timeout: int = 15) -> dict:
    html, url, fetched = _load_source(source, timeout)
    parsed = parse_html(html, url)
    soup = parsed["soup"]
    page_host = urlparse(url).netloc if url else ""

    sentences = [sentence.strip() for sentence in re.split(r"(?<=[.!?])\s+", parsed.get("body_text", "")) if sentence.strip()]
    factual_claims = [sentence for sentence in sentences if CLAIM_RE.search(sentence)]
    external_links = []
    trusted_links = []
    for link in parsed.get("links", []):
        host = urlparse(link.get("href", "")).netloc
        if not host or host == page_host:
            continue
        external_links.append(link)
        if HIGH_TRUST_HOST_RE.search(host):
            trusted_links.append(link)

    cite_tags = [tag.get_text(" ", strip=True) for tag in soup.find_all(["cite", "blockquote"])]
    footnote_links = [
        link for link in parsed.get("links", [])
        if re.search(r"(footnote|reference|citation|source)", " ".join(map(str, link.get("rel", []))) + " " + link.get("href", ""), re.I)
    ]
    entity_signals = _schema_entity_signals(parsed.get("schema", []))
    author_signals = bool(entity_signals["names"]) or bool(soup.find(attrs={"class": re.compile(r"(author|byline)", re.I)}))

    citation_capacity = len(external_links) + len(cite_tags) + len(footnote_links)
    claim_coverage = min(1.0, citation_capacity / max(1, len(factual_claims)))
    score = 0
    score += int(claim_coverage * 35)
    score += min(20, len(trusted_links) * 5)
    score += 15 if author_signals else 0
    score += min(20, len(entity_signals["sameAs"]) * 5)
    score += 10 if parsed.get("canonical") else 0

    issues = []
    if factual_claims and citation_capacity < len(factual_claims):
        issues.append({"severity": "warning", "message": "Factual claims outnumber visible citation/source signals."})
    if not trusted_links:
        issues.append({"severity": "info", "message": "No high-trust external source domains detected."})
    if not author_signals:
        issues.append({"severity": "warning", "message": "No clear author or entity name signal detected."})
    if not entity_signals["sameAs"]:
        issues.append({"severity": "info", "message": "No sameAs entity links found in JSON-LD."})

    return {
        "url": url or source,
        "score": min(100, score),
        "factual_claims": len(factual_claims),
        "claim_samples": factual_claims[:10],
        "citation_signals": {
            "external_links": len(external_links),
            "trusted_external_links": len(trusted_links),
            "cite_or_blockquote_tags": len(cite_tags),
            "footnote_links": len(footnote_links),
        },
        "entity_signals": entity_signals,
        "issues": issues,
        "fetch_error": fetched.get("error"),
    }


def main() -> None:
    parser = argparse.ArgumentParser(description="Assess source, claim, author, and entity citation readiness.")
    parser.add_argument("source", help="URL or local HTML file")
    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_citation_readiness(args.source, args.timeout)
    print(json.dumps(result, indent=2) if args.json else f"Score: {result['score']} Claims: {result['factual_claims']}")


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: 472kUpdated 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: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated 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