This skill should be used when the user asks to "audit for AI visibility", "optimize for ChatGPT", "check GEO readiness", "analyze hedge density", "generate agentfacts", "check if my site works with AI search", "test LLM crawlability", "check discovery gap", or mentions Generative Engine Optimization, AI crawlers, Perplexity discoverability, or NANDA protocol.
From bopen-toolsnpx claudepluginhub b-open-io/claude-plugins --plugin bopen-toolsThis skill uses the workspace's default tool permissions.
README.mdevals/benchmark.jsonevals/evals.jsonexamples/agentfacts-example.jsonexamples/audit-report-example.mdreferences/agentfacts-schema.mdreferences/discovery-strategies.mdreferences/hedge-density.mdreferences/technical-visibility.mdscripts/audit-geo.pyscripts/check-hedge-density.pyscripts/generate-agentfacts.pySearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Generative Engine Optimization (GEO) for AI search visibility.
For background on what GEO is, how it differs from SEO, and the research behind it, see
README.md.
# Run full GEO audit
python3 ${CLAUDE_SKILL_DIR}/scripts/audit-geo.py https://example.com
# Check HTML size and JS dependency
curl -sI https://example.com | grep -i content-length
# Check hedge density of your content
python3 ${CLAUDE_SKILL_DIR}/scripts/check-hedge-density.py --url https://example.com/blog/post
# Or analyze text directly
python3 ${CLAUDE_SKILL_DIR}/scripts/check-hedge-density.py --text "Your content here"
# Generate AgentFacts schema for your domain
python3 ${CLAUDE_SKILL_DIR}/scripts/generate-agentfacts.py \
--domain example.com \
--agent-name "Example Service" \
--capabilities text,image \
--output /.well-known/agent-facts
Measures uncertainty language in content. Target: <0.2%
Hedge words to avoid:
See: references/hedge-density.md
Maximum: 1MB raw HTML. Above this threshold:
Check with: curl -sI URL | grep content-length
See: references/technical-visibility.md
AI crawlers vary in JavaScript rendering:
If your content requires JS to display, you're invisible to ~40% of AI crawlers.
See: references/discovery-strategies.md
The NANDA protocol provides machine-readable metadata for AI agent discovery. Place at /.well-known/agent-facts:
{
"@context": "https://nanda.dev/ns/agent-facts/v1",
"id": "nanda:example.com",
"agent_name": "urn:agent:example:com",
"endpoints": {
"static": ["https://api.example.com/v1/agent"]
},
"capabilities": {
"modalities": ["text"],
"authentication": {
"methods": ["oauth2", "jwt"]
}
},
"trust": {
"certification": "self-attested",
"human_oversight": "true"
}
}
See: references/agentfacts-schema.md
A complete GEO audit covers:
Technical Visibility
Content Authority
Discovery Strategy
Agent Infrastructure
| Script | Purpose |
|---|---|
audit-geo.py | Full GEO audit for a URL |
check-hedge-density.py | Analyze content confidence |
generate-agentfacts.py | Create NANDA-compliant schema |
| File | Contents |
|---|---|
hedge-density.md | Confidence scoring methodology |
agentfacts-schema.md | NANDA protocol specification |
technical-visibility.md | Crawler behavior & limits |
discovery-strategies.md | Startup vs incumbent approaches |
# Full audit with report
python3 ${CLAUDE_SKILL_DIR}/scripts/audit-geo.py https://mysite.com --output report.md
# Quick hedge check
python3 ${CLAUDE_SKILL_DIR}/scripts/check-hedge-density.py --url https://mysite.com/about
# Generate AgentFacts for SaaS
python3 ${CLAUDE_SKILL_DIR}/scripts/generate-agentfacts.py \
--domain myapp.com \
--agent-name "MyApp AI" \
--capabilities text \
--auth oauth2,apikey