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/cache_compression_checker.py

View on GitHub
#!/usr/bin/env python3
"""Check compression and caching headers for a page and optional assets."""

from __future__ import annotations

import argparse
import json
import re
from pathlib import Path
from urllib.parse import urlparse

try:
    from lib.safe_http import safe_request
except ImportError:
    from scripts.lib.safe_http import safe_request

from seo_common import BeautifulSoup, load_html, normalize_url, require_bs4


STATIC_EXTENSIONS = (".css", ".js", ".mjs", ".png", ".jpg", ".jpeg", ".webp", ".avif", ".svg", ".woff2", ".woff")
TEXT_EXTENSIONS = (".html", ".css", ".js", ".mjs", ".json", ".xml", ".svg", ".txt")


def _load_source(source: str, timeout: int) -> tuple[str, str, dict]:
    path = Path(source)
    if path.is_file():
        return path.read_text(encoding="utf-8"), "", {"url": source, "status": None, "headers": {}, "error": None}
    return load_html(source, timeout=timeout)


def _is_url(value: str) -> bool:
    if Path(value).is_file():
        return False
    return urlparse(value).scheme in ("http", "https") or ("." in value and "/" not in value)


def _asset_urls(soup, page_url: str = "") -> list[str]:
    urls = []
    for tag in soup.find_all(["script", "link", "img"], src=True):
        value = tag.get("src")
        urls.append(normalize_url(value, page_url) if page_url and value else value)
    for tag in soup.find_all("link", href=True):
        rel = " ".join(tag.get("rel") or []).lower()
        if any(token in rel for token in ("stylesheet", "preload", "modulepreload", "icon")):
            value = tag.get("href")
            urls.append(normalize_url(value, page_url) if page_url and value else value)
    return [url for url in urls if url and url.startswith(("http://", "https://"))]


def _cache_max_age(cache_control: str | None) -> int | None:
    if not cache_control:
        return None
    match = re.search(r"(?:s-maxage|max-age)=(\d+)", cache_control)
    return int(match.group(1)) if match else None


def _check_url(url: str, timeout: int) -> dict:
    row = {
        "url": url,
        "status": None,
        "content_type": None,
        "content_encoding": None,
        "cache_control": None,
        "etag": None,
        "vary": None,
        "content_length": None,
        "issues": [],
        "error": None,
    }
    try:
        response = safe_request("HEAD", normalize_url(url), timeout=timeout, max_response_bytes=0)
    except Exception as exc:  # noqa: BLE001 - network and policy errors should be reported, not fatal
        row["error"] = str(exc)
        return row

    headers = {str(k).lower(): v for k, v in response.headers.items()}
    row.update({
        "status": response.status_code,
        "content_type": headers.get("content-type"),
        "content_encoding": headers.get("content-encoding"),
        "cache_control": headers.get("cache-control"),
        "etag": headers.get("etag"),
        "vary": headers.get("vary"),
    })
    length = headers.get("content-length")
    row["content_length"] = int(length) if length and length.isdigit() else None

    path = urlparse(url).path.lower()
    is_static = path.endswith(STATIC_EXTENSIONS)
    is_text = path.endswith(TEXT_EXTENSIONS) or (row["content_type"] and any(t in row["content_type"] for t in ("text/", "javascript", "json", "xml", "svg")))
    if is_text and row["content_encoding"] not in ("br", "gzip", "deflate"):
        row["issues"].append({"severity": "warning", "message": "Compressible response is not Brotli/gzip encoded"})
    max_age = _cache_max_age(row["cache_control"])
    if is_static and (max_age is None or max_age < 604800):
        row["issues"].append({"severity": "warning", "message": "Static asset cache lifetime is short or missing"})
    if is_static and row["cache_control"] and "immutable" not in row["cache_control"].lower() and max_age and max_age >= 2_592_000:
        row["issues"].append({"severity": "info", "message": "Long-lived static asset can use immutable"})
    if not row["etag"] and "last-modified" not in headers:
        row["issues"].append({"severity": "info", "message": "No validator header (ETag or Last-Modified)"})
    if row["content_encoding"] and row["vary"] and "accept-encoding" not in row["vary"].lower():
        row["issues"].append({"severity": "warning", "message": "Compressed response should vary on Accept-Encoding"})
    return row


def audit(source: str, include_assets: bool = False, timeout: int = 15, max_assets: int = 25) -> dict:
    if not _is_url(source):
        html, url, fetched = _load_source(source, timeout=timeout)
        require_bs4()
        soup = BeautifulSoup(html or "", "html.parser")
        return {
            "url": source,
            "resources_checked": 0,
            "issues": [{"severity": "info", "message": "Header checks require HTTP(S); local HTML was parsed for asset discovery only."}],
            "resources": [],
            "asset_count": len(_asset_urls(soup, url)),
            "fetch_error": fetched.get("error"),
        }

    html, url, fetched = _load_source(source, timeout=timeout)
    resources = [_check_url(url or source, timeout)]
    if include_assets and html:
        require_bs4()
        soup = BeautifulSoup(html or "", "html.parser")
        seen = {resources[0]["url"]}
        for asset in _asset_urls(soup, url):
            if asset in seen:
                continue
            seen.add(asset)
            resources.append(_check_url(asset, timeout))
            if len(resources) - 1 >= max_assets:
                break
    issues = []
    for row in resources:
        for item in row["issues"]:
            issues.append({**item, "url": row["url"]})
        if row["error"]:
            issues.append({"severity": "info", "message": "Could not fetch headers", "url": row["url"], "evidence": row["error"]})
    return {
        "url": url or source,
        "resources_checked": len(resources),
        "issues": issues,
        "resources": resources,
        "fetch_error": fetched.get("error"),
    }


def main() -> None:
    parser = argparse.ArgumentParser(description="Check cache and compression headers")
    parser.add_argument("source", help="URL or local HTML file")
    parser.add_argument("--include-assets", action="store_true", help="Also check linked CSS/JS/images/fonts")
    parser.add_argument("--max-assets", type=int, default=25)
    parser.add_argument("--timeout", type=int, default=15)
    parser.add_argument("--json", "-j", action="store_true")
    args = parser.parse_args()

    result = audit(args.source, args.include_assets, args.timeout, args.max_assets)
    if args.json:
        print(json.dumps(result, indent=2))
    else:
        print(f"Resources checked: {result['resources_checked']}; issues: {len(result['issues'])}")


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