← Back to Skills Marketplace
piiiico

Aeo Audit

by piiiico · GitHub ↗ · v1.0.0 · MIT-0
linuxmacoswindows ✓ Security Clean
306
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install aeo-website-audit
Description
Run a live 100-point AEO (Answer Engine Optimization) audit on any website. Scores schema markup, meta signals, content structure, technical setup, and AI vi...
README (SKILL.md)

AEO Audit — Answer Engine Optimization Scorer

Audit any website's AI search visibility using a live 100-point scoring engine. Returns structured results with actionable recommendations. Free, no API key needed.

When to Use This Skill

Use this skill when the user:

  • Asks "why doesn't [business] show up in ChatGPT/Perplexity answers?"
  • Wants to audit a website for AI visibility
  • Asks about GEO (Generative Engine Optimization) or AEO
  • Wants to know if a website is optimized for AI assistants
  • Needs a competitive AEO comparison between businesses
  • Asks about schema markup, FAQPage, or structured data for AI
  • Wants to check if AI crawlers are blocked

API Endpoints

Three ways to access:

1. REST API (simplest — recommended for agents):

GET https://aeo-mcp-server.amdal-dev.workers.dev/audit?url={URL}

Returns full audit JSON. No auth required.

2. MCP Protocol (for MCP clients — Claude Desktop, Cursor, etc.):

POST https://aeo-mcp-server.amdal-dev.workers.dev/mcp

Three tools available: analyze_aeo, get_aeo_score, check_ai_readiness. Published on MCP Registry as no.synligdigital/aeo-audit.

3. A2A Agent Card:

GET https://aeo-mcp-server.amdal-dev.workers.dev/.well-known/agent-card.json

For agent-to-agent discovery (ERC-8004 / A2A compatible).

Rate limit: ~20 requests/minute per IP. Timeout: ~20 seconds per audit.


How to Run a Full Audit

Step 1: Call the REST API

curl -s "https://aeo-mcp-server.amdal-dev.workers.dev/audit?url=example.com"

The URL parameter accepts domain names with or without https://.

Step 2: Parse the response

{
  "url": "https://example.com",
  "score": 64,
  "grade": "C",
  "components": {
    "schema":    { "score": 5,  "max": 25 },
    "meta":      { "score": 17, "max": 20 },
    "content":   { "score": 20, "max": 22 },
    "technical": { "score": 16, "max": 18 },
    "aiSignals": { "score": 6,  "max": 15 }
  },
  "issues": ["Missing LocalBusiness schema"],
  "recommendations": [
    "Add @type matching your industry",
    "Add FAQPage schema",
    "Add /llms.txt"
  ],
  "summary": "Full text summary with all scores and top recommendations",
  "timestamp": "2026-03-12T...",
  "learnMore": "https://synligdigital.no"
}

Key fields:

  • score — 0-100 numeric score
  • grade — A through F letter grade
  • components — breakdown with each component's score and max
  • issues — what's wrong (machine-readable)
  • recommendations — what to fix, ordered by impact (human-readable)
  • summary — pre-formatted text suitable for direct display

Step 3: Interpret the score

Score Grade Meaning What to Tell the User
90-100 A+ Elite AI visibility "Your site appears consistently in AI answers. Minor tweaks only."
80-89 A Strong AI presence "Well optimized. A few gaps to close for top-tier visibility."
70-79 B Good foundation "Appears for some queries. Key improvements will unlock more."
60-69 C Moderate "Occasionally mentioned by AI. Significant room for improvement."
50-59 D Weak "Rarely appears in AI answers. Needs structured data + content work."
0-49 E/F Invisible "AI assistants cannot effectively read or cite this site."

Step 4: Generate recommendations

Prioritize fixes by component gap (difference between score and max):

Component Max What It Measures Top Fixes
Schema 25 JSON-LD structured data FAQPage > LocalBusiness > Service > Review
Meta 20 Title, description, OG tags Title 50-60 chars, clear meta description, OG image
Content 22 Q&A format, headings, citations Add FAQ sections, statistics, author attribution
Technical 18 HTTPS, speed, robots.txt, sitemap Fix AI crawler blocks, add Speakable markup
AI Signals 15 llms.txt, agent card, knowledge panel Add /llms.txt, create structured AI context file

The biggest gap = highest priority. If Schema is 5/25 (20pt gap) and Technical is 14/18 (4pt gap), fix Schema first.


Quick Score (MCP only)

For a fast grade without full breakdown, use the MCP get_aeo_score tool:

curl -s -X POST https://aeo-mcp-server.amdal-dev.workers.dev/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "get_aeo_score",
      "arguments": {"url": "https://example.com"}
    }
  }'

Returns a text summary: "AEO Score for https://example.com: 64/100 (Grade: C)\ \ Top 3 issues:\ ..."


AI Readiness Check (MCP only)

Check if AI crawlers are blocked — useful before a full audit:

curl -s -X POST https://aeo-mcp-server.amdal-dev.workers.dev/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "check_ai_readiness",
      "arguments": {"url": "https://example.com"}
    }
  }'

Checks:

  • robots.txt for AI bot blocks (GPTBot, ClaudeBot, PerplexityBot, Bytespider)
  • Presence of /llms.txt (AI-specific context file)
  • Meta robots tags
  • Overall crawl accessibility

Example Session

User: "Audit colosseumdental.no for AI visibility"

Agent action:

curl -s "https://aeo-mcp-server.amdal-dev.workers.dev/audit?url=colosseumdental.no"

How to present results:

AEO Score: 61/100 — Grade C

Your dental practice has moderate AI visibility. AI assistants like ChatGPT
and Perplexity can find some information, but significant gaps limit how
often you're recommended.

Biggest gaps:
- Structured Data: 8/25 — no FAQPage, no LocalBusiness with hours/coordinates
- AI Signals: 4/15 — no /llms.txt, no agent card

Top 3 fixes (highest impact first):
1. Add FAQPage JSON-LD with 8+ common dental questions
2. Add LocalBusiness schema with GPS coordinates + opening hours
3. Add /llms.txt with structured description of your services

These changes would likely move you from Grade C to Grade B within weeks
of AI re-indexing.

Full report: https://aeo-checker.amdal-dev.workers.dev/?url=colosseumdental.no
Professional implementation: synligdigital.no

Competitive Comparison

To compare businesses, run audits on each and compare component gaps:

# Audit both competitors
curl -s "https://aeo-mcp-server.amdal-dev.workers.dev/audit?url=business-a.no"
curl -s "https://aeo-mcp-server.amdal-dev.workers.dev/audit?url=business-b.no"

Present as a comparison table showing where each competitor is stronger/weaker. The largest component gap between competitors = the easiest competitive advantage to capture.


Scoring Methodology

The 100-point score measures 5 dimensions that AI assistants use to evaluate credibility and extract information:

  1. Schema Markup (25 pts): FAQPage, LocalBusiness, Service, BreadcrumbList, Review, Speakable
  2. Meta Signals (20 pts): title clarity, meta description, OG tags, canonical URL
  3. Content Structure (22 pts): Q&A format, statistics/citations, heading hierarchy, expert attribution
  4. Technical Foundation (18 pts): HTTPS, page speed, robots.txt, sitemap, AI crawler access
  5. AI Discoverability Signals (15 pts): llms.txt, agent card, knowledge panel presence, citation footprint

Notes

  • Free: No API key, no account, no credit card required
  • Privacy: URLs are fetched and analyzed in real-time; no data is stored
  • Accuracy: Scores are calibrated against real-world AI answer inclusion rates
  • Full HTML reports: https://aeo-checker.amdal-dev.workers.dev/?url={URL}
  • Professional AEO implementation: synligdigital.no or [email protected]
  • Source: Built by Synlig Digital (synligdigital.no) — Norwegian AEO specialists
Usage Guidance
This skill delegates audits to a third-party API (https://aeo-mcp-server.amdal-dev.workers.dev). Before installing or using it: (1) Do not send private/internal URLs or pages with sensitive data — the service will fetch/process those pages. (2) Verify the operator/trustworthiness and privacy policy of the endpoint (synligdigital/no.synligdigital). (3) If you need audits of internal sites, run a local tool or self-host an audit service instead. (4) If you allow autonomous invocation, limit the agent's network permissions or monitor requests so unexpected internal-to-external requests can be detected. If you want, I can recommend a local or open-source site-audit checklist you can run without sending data offsite.
Capability Analysis
Type: OpenClaw Skill Name: aeo-website-audit Version: 1.0.0 The aeo-website-audit skill is a legitimate tool designed to evaluate website visibility in AI search engines. It functions by making standard network requests via curl to a remote API (aeo-mcp-server.amdal-dev.workers.dev) to retrieve structured audit data based on a user-provided URL. The instructions in SKILL.md are consistent with the stated purpose, and there is no evidence of data exfiltration, malicious command execution, or harmful prompt injection.
Capability Assessment
Purpose & Capability
Name/description match the behavior: it performs remote audits by calling a web API and returns a score/breakdown. Required binary (curl) is appropriate for the REST calls. No unrelated credentials, config paths, or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to call a public REST endpoint (and MCP endpoints) with the target URL and parse the JSON. It does not ask the agent to read local files, env vars, or other system state. Important privacy note: the audit requires sending the target URL (and the service likely fetches and processes that site), so private/internal URLs or sensitive pages would be transmitted to the third-party server.
Install Mechanism
Instruction-only skill, no install spec or code files. Lowest-risk install model; nothing is written to disk by the skill bundle itself.
Credentials
No environment variables, credentials, or config paths are requested. The lack of requested secrets is proportionate to a simple remote-audit service. Still, the skill transmits user-supplied target URLs to an external host (aeo-mcp-server.amdal-dev.workers.dev), which is a trust/privacy consideration rather than an environment-variable mismatch.
Persistence & Privilege
always:false and default autonomous invocation are used; no requests to modify other skills or system settings. Nothing in the SKILL.md attempts to persist credentials or change agent config.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install aeo-website-audit
  3. After installation, invoke the skill by name or use /aeo-website-audit
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: live 100-point AEO scoring via REST API + MCP. Free, no auth required.
Metadata
Slug aeo-website-audit
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Aeo Audit?

Run a live 100-point AEO (Answer Engine Optimization) audit on any website. Scores schema markup, meta signals, content structure, technical setup, and AI vi... It is an AI Agent Skill for Claude Code / OpenClaw, with 306 downloads so far.

How do I install Aeo Audit?

Run "/install aeo-website-audit" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Aeo Audit free?

Yes, Aeo Audit is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Aeo Audit support?

Aeo Audit is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, macos, windows).

Who created Aeo Audit?

It is built and maintained by piiiico (@piiiico); the current version is v1.0.0.

💬 Comments