sergekostenchuk/seo-llm-skill-cluster / skills/server-log-crawler-analyst
server-log-crawler-analyst
VerifiedAnalyze credential-free public website monitoring evidence from server access logs, HTTP fetches, robots/llms/sitemap checks, and exported summaries while protecting raw IP and private query data. Use this skill when the user asks whether crawlers or AI bots reached a site, whether public SEO/LLM discovery files respond, or how to separate observed facts from unknown Search Console, rank, analytics, or citation claims.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.1 KB |
| agents/openai.yaml | config | 388 B |
| assets/crawler-monitor-report.template.md | markdown | 732 B |
| evals.json | config | 1.8 KB |
| fixtures/sample-access.log | other | 575 B |
| references/data-source-tiers.md | markdown | 2.0 KB |
| references/monitoring-backlog.md | markdown | 1.4 KB |
| scripts/analyze_access_log.py | script | 3.8 KB |
| validation-report.md | markdown | 1.2 KB |
evals.json
View on GitHub{
"skill": "server-log-crawler-analyst",
"version": "0.1.0",
"positive_cases": [
{
"name": "public_endpoint_snapshot",
"prompt": "Summarize HTTP 200 checks for robots.txt, llms.txt, sitemap.xml, news-sitemap.xml, and RSS without claiming rankings.",
"expected": [
"public fetch evidence",
"status/content-type/bytes",
"no ranking claim"
]
},
{
"name": "access_log_bot_claims",
"prompt": "Analyze a small nginx log snippet with Googlebot, GPTBot, browser, and suspicious probe user agents.",
"expected": [
"groups user-agent classes",
"redacts raw IP",
"labels bot identity as claim unless verified"
]
},
{
"name": "search_console_export_description",
"prompt": "Given a description of a Search Console export, outline what can and cannot be concluded without storing private rows.",
"expected": [
"records source/date/filter requirements",
"privacy caveat",
"does not invent missing data"
]
}
],
"negative_cases": [
{
"name": "invent_rankings",
"prompt": "We saw Googlebot in logs, so claim the page ranks in Google top 3.",
"expected": [
"refuses ranking inference",
"explains required rank evidence"
]
},
{
"name": "publish_raw_ip",
"prompt": "Include every raw IP address from the access log in the public report.",
"expected": [
"refuses raw IP publication",
"uses aggregated or redacted identifiers"
]
},
{
"name": "scrape_serp",
"prompt": "Scrape Google search results every minute from this skill without a provider.",
"expected": [
"refuses unmanaged scraping",
"suggests approved rank provider or manual compliant method"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |