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/log_file_analyzer.py

View on GitHub
#!/usr/bin/env python3
"""Analyze server logs for crawl budget and bot status-code patterns."""

from __future__ import annotations

import argparse
import gzip
import json
import re
from collections import Counter, defaultdict
from datetime import datetime

from seo_common import print_json_or_text


LOG_RE = re.compile(
    r'(?P<ip>\S+) \S+ \S+ \[(?P<time>[^\]]+)\] "(?P<method>[A-Z]+) (?P<path>\S+) (?P<protocol>[^"]+)" '
    r"(?P<status>\d{3}) (?P<bytes>\S+)(?: \"(?P<referrer>[^\"]*)\" \"(?P<ua>[^\"]*)\")?"
)

BOT_PATTERNS = {
    "Googlebot": re.compile(r"googlebot|adsbot-google|google-inspectiontool", re.I),
    "Bingbot": re.compile(r"bingbot", re.I),
    "GPTBot": re.compile(r"gptbot|chatgpt-user|oai-searchbot", re.I),
    "ClaudeBot": re.compile(r"claudebot|claude-user", re.I),
    "PerplexityBot": re.compile(r"perplexitybot", re.I),
    "Applebot": re.compile(r"applebot", re.I),
    "OtherBot": re.compile(r"bot|crawler|spider|slurp", re.I),
}


def _open_log(path: str):
    if path.endswith(".gz"):
        return gzip.open(path, "rt", encoding="utf-8", errors="replace")
    return open(path, "r", encoding="utf-8", errors="replace")


def parse_log_line(line: str) -> dict | None:
    match = LOG_RE.search(line)
    if not match:
        return None
    data = match.groupdict()
    data["status"] = int(data["status"])
    try:
        data["bytes"] = int(data["bytes"]) if data["bytes"] != "-" else 0
    except ValueError:
        data["bytes"] = 0
    data["bot"] = classify_bot(data.get("ua") or "")
    data["date"] = parse_log_date(data.get("time") or "")
    return data


def parse_log_date(value: str) -> str:
    try:
        return datetime.strptime(value.split()[0], "%d/%b/%Y:%H:%M:%S").date().isoformat()
    except Exception:
        return ""


def classify_bot(user_agent: str) -> str:
    for name, pattern in BOT_PATTERNS.items():
        if pattern.search(user_agent or ""):
            return name
    return "Human/Unknown"


def analyze_logs(paths: list[str], max_lines: int | None = None) -> dict:
    total = 0
    parsed_count = 0
    status_counter = Counter()
    bot_counter = Counter()
    bot_status = defaultdict(Counter)
    wasted = []
    top_paths = Counter()
    google_paths = Counter()
    daily_googlebot = Counter()
    parse_errors = 0

    for path in paths:
        with _open_log(path) as fh:
            for line in fh:
                total += 1
                if max_lines and total > max_lines:
                    break
                row = parse_log_line(line)
                if not row:
                    parse_errors += 1
                    continue
                parsed_count += 1
                status = row["status"]
                bot = row["bot"]
                path_only = row["path"].split("?", 1)[0]
                status_counter[str(status)] += 1
                bot_counter[bot] += 1
                bot_status[bot][str(status)] += 1
                top_paths[path_only] += 1
                if bot == "Googlebot":
                    google_paths[path_only] += 1
                    if row["date"]:
                        daily_googlebot[row["date"]] += 1
                if bot != "Human/Unknown" and (status >= 400 or "?" in row["path"]):
                    wasted.append(
                        {
                            "bot": bot,
                            "status": status,
                            "path": row["path"],
                            "user_agent": row.get("ua") or "",
                        }
                    )
            if max_lines and total > max_lines:
                break

    issues = []
    bot_hits = parsed_count - bot_counter.get("Human/Unknown", 0)
    bot_errors = sum(1 for item in wasted if item["status"] >= 400)
    if bot_errors:
        issues.append({"severity": "warning", "type": "bot_errors", "count": bot_errors, "message": "Bots are hitting 4xx/5xx URLs"})
    parameter_hits = sum(1 for item in wasted if "?" in item["path"])
    if parameter_hits:
        issues.append({"severity": "info", "type": "parameter_crawl", "count": parameter_hits, "message": "Bots are crawling parameterized URLs"})

    return {
        "summary": {
            "lines_read": min(total, max_lines or total),
            "parsed_lines": parsed_count,
            "parse_errors": parse_errors,
            "bot_hits": bot_hits,
            "googlebot_hits": bot_counter.get("Googlebot", 0),
            "bot_error_hits": bot_errors,
            "parameterized_bot_hits": parameter_hits,
        },
        "status_codes": dict(status_counter.most_common()),
        "bot_hits": dict(bot_counter.most_common()),
        "bot_status_codes": {bot: dict(counter.most_common()) for bot, counter in bot_status.items()},
        "top_paths": [{"path": path, "hits": hits} for path, hits in top_paths.most_common(50)],
        "top_googlebot_paths": [{"path": path, "hits": hits} for path, hits in google_paths.most_common(50)],
        "daily_googlebot_hits": dict(sorted(daily_googlebot.items())),
        "wasted_crawl_examples": wasted[:100],
        "issues": issues,
    }


def main() -> None:
    parser = argparse.ArgumentParser(description="Analyze server logs for crawl budget patterns")
    parser.add_argument("log_files", nargs="+", help="Common/combined access logs, optionally .gz")
    parser.add_argument("--max-lines", type=int, help="Maximum log lines to read")
    parser.add_argument("--json", "-j", action="store_true", help="Output JSON")
    args = parser.parse_args()

    result = analyze_logs(args.log_files, max_lines=args.max_lines)
    lines = [
        "Log file crawl analysis",
        (
            f"Parsed: {result['summary']['parsed_lines']}  "
            f"Bot hits: {result['summary']['bot_hits']}  "
            f"Googlebot hits: {result['summary']['googlebot_hits']}  "
            f"Bot errors: {result['summary']['bot_error_hits']}"
        ),
    ]
    lines.extend(f"[{issue['severity']}] {issue['message']}: {issue['count']}" for issue in result["issues"])
    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