Audits websites for AI search visibility (GEO/SEO) and generates deployable artifacts (llms.txt, schema JSON-LD, robots.txt). 7-dimension scorecard tailored by site type and size, grounded in Princeton KDD 2024, Toronto 2025, and ICLR 2026 research. This skill should be used when optimizing for ChatGPT, Perplexity, Google AI Overviews, or other AI search engines. Also triggered by queries about AI search optimization, generative engine optimization, llms.txt, AI crawler configuration, schema markup for AI, citation optimization, or Google AI Mode.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
The command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
File Explorer
21 files
Showing SKILL.md
SKILL.md
Source instructions ยท Read-only preview
name
geo-seo
description
Audits websites for AI search visibility (GEO/SEO) and generates deployable artifacts (llms.txt, schema JSON-LD, robots.txt). 7-dimension scorecard tailored by site type and size, grounded in Princeton KDD 2024, Toronto 2025, and ICLR 2026 research. This skill should be used when optimizing for ChatGPT, Perplexity, Google AI Overviews, or other AI search engines. Also triggered by queries about AI search optimization, generative engine optimization, llms.txt, AI crawler configuration, schema markup for AI, citation optimization, or Google AI Mode.
GEO/SEO: AI Search Visibility Audit & Artifact Generator
Audit a website for AI search visibility across 7 research-grounded dimensions, generate deployable artifacts (llms.txt, schema JSON-LD, robots.txt), and produce a prioritized action plan โ all tailored to the site's type and scale.
Complementary to agentic-seo: This skill measures whether content gets cited when humans search via ChatGPT/Perplexity/Google AI Overviews. agentic-seo (run separately via ) measures whether AI agents can interact with the site (including manifests, skill discovery, permission systems). Run both for complete coverage.
npx agentic-seo ./out
agent.json
Arguments
Parse `` for:
path: Project root to audit (default: current working directory)
--type: Override auto-detected site type
--size: Override auto-detected size tier
--mode: audit (scorecard only), generate (artifacts only), full (both, default), monitor (compare to previous snapshot)
Workflow
Execute these phases in order: Detect โ Audit โ Classify โ Generate โ Report โ Cross-reference.
Mode-to-Phase Mapping
Mode
Detect
Audit
Classify
Generate
Report
Cross-ref
full
Yes
Yes
Yes
Yes
Yes
Yes
audit
Yes
Yes
Yes
Skip
Yes
Yes
generate
Yes
Skip
Skip
Yes
Yes
Yes
monitor
Yes
Yes
Yes
Skip
Yes (diff)
Yes
Phase 1: Detect Site Profile
Auto-detect site type, size, and framework from codebase signals. Report findings before proceeding.
Site Type Detection
Examine the project for these signals (override with --type):
Site Profile: [type] | [size] tier ([N] pages) | [framework]
Phase 2: Audit โ 7-Dimension Scoring
Score each dimension 0โ4. The inline tables below are quick-reference summaries. Load references/scoring-rubric.md for the authoritative rubric with research citations and detailed check procedures โ the reference version takes precedence when they differ.
Dimension 1: AI Crawler Access (0โ4)
Check robots.txt for the 9 critical AI crawlers. Distinguish training bots (safe to block) from search/retrieval bots (blocking = invisible to AI search).
Crawlers to check (three tiers): See references/ai-crawlers.md for the full registry.
P0 check โ JavaScript-only rendering: AI crawlers do not execute JavaScript. If the site is client-side rendered (CSR/SPA) without SSR/SSG, flag as P0.
# Check for SSR/SSG configuration
grep -r "getServerSideProps\|getStaticProps\|generateStaticParams\|output.*export\|prerender\|ssr" --include="*.{ts,tsx,js,jsx,mjs}" . 2>/dev/null | head -5
Score
Criteria
0
Search-critical bots blocked, OR CDN bot blocking, OR JS-only rendering (P0)
1
Some search bots allowed but OAI-SearchBot or PerplexityBot blocked
2
All search-critical bots allowed but user-triggered fetch bots blocked
3
All search-critical + user-triggered fetch bots allowed, no CDN blocking
4
All bots allowed + IndexNow configured + <500ms bot response
Dimension 2: AI Discovery Infrastructure (0โ4)
Check for llms.txt, sitemap, RSS/Atom feeds. Load references/llms-txt-spec.md for validation rules.
# Check for discovery filesls public/llms.txt public/llms-full.txt llms.txt llms-full.txt 2>/dev/null
ls public/sitemap.xml sitemap.xml out/sitemap.xml 2>/dev/null
grep -r "application/rss\|application/atom\|feed\.xml\|rss\.xml" --include="*.{tsx,jsx,html,xml}" . 2>/dev/null | head -3
llms.txt validation (if present):
Single H1 title (required)
Blockquote summary after H1
H2 sections with Markdown link lists in [name](url): description format
## Optional section for lower-priority content
Score
Criteria
0
No llms.txt, no AI-specific discovery files
1
llms.txt present but minimal (just H1)
2
llms.txt with H1 + blockquote + sections; OR sitemap with lastmod
3
Well-structured llms.txt + ## Optional; sitemap with lastmod; RSS/Atom
Rankeo finding: Minimal/generic schema (41.6% citation rate) performs WORSE than no schema (59.8%). Only award points for complete, attribute-rich schema.
Required @types by site type:
Type
Required
Bonus
ecommerce
Product, Organization, BreadcrumbList
AggregateRating, Review, Offer
saas
Organization, SoftwareApplication, FAQPage
HowTo, Article
content
Article, Organization, Person
NewsArticle, BlogPosting, LiveBlogPosting
local
LocalBusiness, Organization
Review, GeoCoordinates, OpeningHoursSpecification
docs
TechArticle, Organization
HowTo, SoftwareSourceCode
personal
Person, Organization
CreativeWork, Article
Score
Criteria
0
No JSON-LD structured data
1
Generic schema, <5 attributes โ WORSE than absent
2
Correct @types for site type, 5+ attributes, but no sameAs or nesting
3
Complete schema with nested types, sameAs, 8+ attributes
Lily Ray's constraint: if SEO foundation is broken (score 0โ1), flag P0 "Fix SEO before pursuing GEO." RAG requires crawl + index.
# Check meta tags, canonical, sitemap
grep -r "noindex" --include="*.{tsx,jsx,html}" . 2>/dev/null | grep -v node_modules | head -5
grep -r "canonical\|metadataBase" --include="*.{tsx,jsx,ts}" . 2>/dev/null | head -5
grep -r "<title\|metadata.*title\|Head.*title" --include="*.{tsx,jsx,ts}" . 2>/dev/null | head -5
grep -r "description\|meta.*description" --include="*.{tsx,jsx,ts}" . 2>/dev/null | head -5
# Check for Open Graph
grep -r "og:title\|openGraph\|twitter:card" --include="*.{tsx,jsx,ts,html}" . 2>/dev/null | head -5
Score
Criteria
0
Critical crawl issues: unintended noindex, broken canonicals, no sitemap
1
Indexable but slow, no meta descriptions, broken links
2
Core pages have titles, meta descriptions, canonical URLs, sitemap
3
All above + semantic HTML, mobile-friendly, heading hierarchy
4
All above + fast LCP, 5+ internal links/page, image alt coverage, Open Graph complete
Dimension 6: Entity & Brand Signals (0โ4)
Ahrefs 75K-brand study: unlinked mentions correlate 0.664 with AI visibility; backlinks only 0.218. YouTube mentions strongest single factor (0.737).
# Check Organization/Person schema with sameAs
grep -r "sameAs\|Organization\|Person" --include="*.{tsx,jsx,ts,json}" . 2>/dev/null | head -10
# Check for consistent brand naming
grep -r "publisher\|author\|brand\|organizationName" --include="*.{tsx,jsx,ts,json}" . 2>/dev/null | head -5
Score
Criteria
0
No entity signals, no Organization schema
1
Organization schema but no sameAs, no external references
2
Organization + sameAs to 2+ platforms; consistent brand name
3
All above + Wikipedia/Wikidata; author Person schema; consistent NAP
4
All above + earned media presence; YouTube; 5+ platform consistency
Dimension 7: Multi-Engine Readiness (0โ4)
Only 11% domain overlap between Perplexity and ChatGPT (U of Toronto). Engine-specific optimization is structurally required. Load references/engine-profiles.md for per-engine profiles.
# Check for engine-specific signals
grep -r "IndexNow\|indexnow" --include="*.{json,xml,ts,js}" . 2>/dev/null
grep -r "dateModified\|datePublished\|lastmod" --include="*.{tsx,jsx,ts,json,xml}" . 2>/dev/null | head -5
Score
Criteria
0
No engine-specific considerations
1
Optimized for Google only
2
Google AIO + one other (Perplexity or ChatGPT)
3
Google AIO + Perplexity + ChatGPT; freshness signals; earned media references
4
All engines + Perplexity freshness gates + ChatGPT earned media + Google AIO fan-out + Bing IndexNow
Site-Type Scoring Weights
Apply weight modifiers when interpreting scores. "Critical" dimensions with low scores warrant P0 findings.
Informational. IndexNow not configured, minor content improvements, missing RSS.
Phase 4: Generate Artifacts
Skip this phase in audit mode. In generate or full mode, produce the artifacts below.
4a. llms.txt
Generate llms.txt following Jeremy Howard's spec (AnswerDotAI, Sep 2024). Load references/llms-txt-spec.md for format details.
Detect site name from package.json, Organization schema, or site config
Write summary from homepage meta description or first content paragraph
Categorize pages by type (docs, blog, product, about, API)
Prioritize by internal link count and content depth
Mark lower-priority pages under ## Optional
Load assets/templates/llms-txt/ for site-type starter templates.
If llms.txt already exists, audit it against the spec instead of overwriting. Report improvements.
4b. Schema JSON-LD
Generate complete, attribute-rich JSON-LD for the detected site type. Load references/schema-patterns.md for patterns and assets/templates/schema/ for starters.
Detect existing schema and identify gaps
Generate schema with 8+ attributes per type (per Rankeo: completeness > presence)
Include sameAs links to known entity references
Use site-type-specific @types from the rubric
Validate: no duplicate singleton types per page
If schema already exists, report what's missing rather than overwriting.
4c. robots.txt AI Crawler Directives
Generate directives separating training bots from search bots. Load references/ai-crawlers.md for the full registry.
# AI Search Crawlers โ allow for AI search visibility
User-agent: OAI-SearchBot
Allow: /
User-agent: PerplexityBot
Allow: /
# User-triggered fetch โ recommended to allow
User-agent: ChatGPT-User
Allow: /
# AI Training Crawlers โ block to protect content
User-agent: GPTBot
Disallow: /
User-agent: CCBot
Disallow: /
The inline example above is a minimal subset. Load assets/templates/robots-ai-block.txt for the complete template covering all search, fetch, and training crawlers.
If robots.txt already exists, check for conflicts and report them. Do not overwrite without confirmation.
Phase 5: Report
Load references/research-basis.md when populating the Research Citations section with specific paper references supporting key findings.
Failure modes that produce wrong results without this section. Each represents a common mistake in AI search optimization.
"Add FAQs everywhere" โ FAQ bloat damages traditional SEO, which undermines GEO (Lily Ray, Mar 2026). FAQPage schema lifts citations 2.7x, but filling pages with 50 thin Q&As hurts the overall SEO foundation. Score FAQPage schema appropriately but do not recommend FAQ content universally.
Minimal schema worse than none โ 41.6% citation rate for generic schema vs 59.8% for no schema (Rankeo). An Organization with just name and url actively hurts. Enforce the 8+ attribute completeness threshold. When existing schema is too thin, recommend removing it or completing it โ not leaving it as-is.
All AI engines treated the same โ Only 11% domain overlap between Perplexity and ChatGPT (U of Toronto, 118K answers). Perplexity has a freshness hard gate; ChatGPT has earned media bias; Google AIO leans on traditional SEO signals. Provide engine-specific analysis, not generic "optimize for AI search."
Ignoring earned media โ On-page optimization alone cannot overcome the systematic earned media bias that ChatGPT and Google show. Entity & Brand dimension exists to surface this gap. Do not promise citation improvements from on-page work alone when the site has no external mentions.
CSR/SPA invisible to AI โ AI crawlers do not execute JavaScript. A React SPA with no SSR/SSG is completely invisible. Check rendering mode as the very first thing โ all other optimization is pointless if the content can't be crawled.
Silent CDN blocking โ Cloudflare Bot Fight Mode blocks AI crawlers without any robots.txt evidence. Check for CDN-level blocking, not just robots.txt directives.
GEO without SEO foundation โ RAG requires crawl + index. If traditional SEO is broken (no sitemap, noindex on main pages, broken canonicals), no GEO optimization will help. Technical SEO Foundation score 0โ1 is always P0.
robots.txt training/search confusion โ Most sites only reference GPTBot, which is training-only. Blocking GPTBot doesn't lose search. Blocking OAI-SearchBot does. Always surface the training vs search distinction โ most site owners don't know OpenAI has 3 separate crawlers.
dateModified as decoration โ Setting dateModified to today's date without changing content is a freshness signal lie. Perplexity will eventually detect and penalize this. Only recommend updating dateModified when content actually changes.
Overwriting existing artifacts โ When llms.txt or robots.txt already exists, audit and suggest improvements. Do not generate a replacement and overwrite without explicit confirmation. The site owner may have intentional customizations.
Perplexity-User ignores robots.txt โ Per Perplexity's own documentation, Perplexity-User "generally ignores robots.txt" directives. A Disallow rule for this bot gives false confidence โ the site owner thinks they've blocked user-triggered fetches but they haven't. When auditing, flag this distinction: only PerplexityBot reliably respects robots.txt. Server-side User-Agent filtering is the only reliable block for Perplexity-User.
Zero-click outcomes are structural โ AI search optimization may increase citation frequency while decreasing click-through traffic. This is not a failure of optimization โ it is the structural reality of AI-mediated search (Rand Fishkin, SparkToro). Set realistic expectations: GEO success means brand visibility and authority in AI answers, not necessarily more website visits. For sites that depend on direct traffic, note that citation โ click.
Reference Documents
Load these on-demand when deeper context is needed:
File
When to load
references/scoring-rubric.md
Full scoring criteria with research citations for each threshold
references/schema-patterns.md
JSON-LD patterns and examples by site type
references/ai-crawlers.md
Complete AI crawler registry with training vs search classification
references/research-basis.md
Academic paper summaries and key empirical findings
references/llms-txt-spec.md
llms.txt format specification and best practices
references/engine-profiles.md
Per-engine optimization profiles (Google AIO, Google AI Mode, Perplexity, ChatGPT, Bing)
