Improve AI search visibility (GEO & AEO), with your agent
Audits and fixes your site’s visibility in ChatGPT, Claude, Perplexity and Google AI Overviews: AI crawler access, non-JS HTML readability, answer-first passages, entity sameAs schema and live citation tracking.
Add it, from the top of the site’s repositorynpx skills add subinternal/clickd --skill clickd-ai-visibility
Then ask your agentAudit our AI search visibility (GEO/AEO) on example.com with clickd, check AI crawlers and non-JS readability, and fix the top blockers in code.
For founders, marketers and developers who want their site read and cited by AI assistantsCheck AI crawlers & agent view
Four steps from citation check to GEO & AEO fixes
Your agent checks real assistant answers and non-JavaScript HTML extraction first, then fixes crawler access, passage structure and entity schema in code.
1Check live AI citations, crawler access and non-JS readabilityclickd_citations
2Unblock AI search crawlers and serve complete HTML
3Structure pages for passage retrieval and entity clarityclickd_tells
4Rescan and track citation changes with clickdclickd_rescan
What AI search engines read on your site
Fixing the technical and structural blockers that keep ChatGPT, Claude, Perplexity and AI Overviews from retrieving and quoting a page.
example.com GEO & AEO read
Checked with clickd_citations, clickd_check (kind: "agent") and /ai-crawler-checker.
Sample
AI search crawlersrobots.txt blocked GPTBot, OAI-SearchBot and PerplexityBot under wildcard ruleExplicit Allow rules for OAI-SearchBot, GPTBot, ClaudeBot and PerplexityBot
Non-JS agent viewPricing tiers and comparison table rendered only by client JSServer-rendered HTML outputs all pricing, specs and FAQs to non-JS crawlers
Answer-first passagesVague marketing headings with no direct definitions or numbersQuestion H2s followed by 40 to 60 word self-contained answers and primary citations
Entity & /llms.txtNo sameAs profile links; missing /llms.txt outlineOrganization sameAs wired to official profiles; live /llms.txt linked from footer
How clickd measures AI visibility
Combines live assistant citation tracking with raw HTML extraction and crawler checks.
clickd_citations & clickd_citeTracks which buyer questions in your market cite your site versus rivals across AI assistants.
clickd_check (kind: "agent") & clickd_site (view: "agent")Shows the exact text and Markdown an AI retrieval bot extracts from your pages without JavaScript.
clickd_tells & clickd_schema_createKeeps passages clean of stock AI filler and wires unambiguous entity JSON-LD with sameAs links.
When to reach for it
Reach for it when
Buyers ask ChatGPT, Claude, Perplexity or Google AI Overviews for tools or services in your market and your site is not cited.1
You want to verify that OAI-SearchBot, GPTBot, ClaudeBot and PerplexityBot can crawl and read your HTML without JavaScript.3,2
You want to combine /llms.txt, entity sameAs schema and answer-first headings in one GEO workflow.
Leave it when
You want a guarantee that ChatGPT will recommend your brand first on every prompt.
You only want to add /llms.txt and nothing else: the llms.txt skill does that one job.
More things to ask your agent
Everyday prompts that load the AI visibility skill in Claude Code, Codex or Cursor.
Full GEO / AEO auditCheck example.com with clickd_citations and clickd_check (kind: "agent"), unblock AI search crawlers in robots.txt, and fix non-JS HTML gaps.
Make key pages quotableRewrite headings and opening passages on our top 5 pages so AI assistants can extract 40 to 60 word direct answers with clear entity facts.
Track buyer-question citationsRun clickd_citations on example.com to see which buyer prompts cite our rivals instead of us and why.
AI visibility skill vs the alternatives
Why pairing an open repository skill with a live crawler beats manual audits and prompt-only checklists.
How it reads your siteBy hand: Manual spot-checks in a browser · Prompt-only skill: Reads local source files only; misses live headers, redirects and JS shellsReads the live URL, HTTP headers, raw HTML and Search Console via clickd MCP
How changes are madeBy hand: Copy-pasting between docs, spreadsheets and editors · Prompt-only skill: Suggests generic copy in chat with no repo contextEdits your actual templates, routes and schema in the repository
How fixes are provedBy hand: Checking pages one by one after deploy · Prompt-only skill: Agent grades its own homework with no live checkRuns clickd_rescan and clickd_changes on the deployed site to prove rules passed
Skills to use alongside it
Included when you run npx skills add subinternal/clickd.
llms.txtAdds a /llms.txt to a site, a plain text outline for AI assistants built from the site’s own pages and facts, with tests that catch a missing page, and checks it with clickd.See skill
Schema markupGenerates, wires and validates JSON-LD structured data (Organization, LocalBusiness, Product, Service, Article, FAQPage and BreadcrumbList) from the visible facts on your pages, checked live with clickd.See skill
On-page SEORewrites title tags, meta descriptions, single H1s, question headings, answer-first openings, image alt text and AI writing tells in your site’s templates and content files, checked live with clickd.See skill
Questions about the AI visibility skill
What is the difference between GEO, AEO and traditional SEO?
GEO (Generative Engine Optimization) and AEO (Answer Engine Optimization) make your site easy for AI systems (ChatGPT, Claude, Perplexity, Google AI Overviews) to crawl without JavaScript, verify as a named entity, and quote in 40 to 60 word answer passages.
Can we allow AI search answers while blocking model training in robots.txt?
Yes. The skill shows how to allow retrieval bots (OAI-SearchBot, Claude-SearchBot, PerplexityBot) on public pages while configuring training tokens separately if your policy requires it.
Install it by hand
The line at the top adds it for any agent. Or fetch its 1 files where your agent looks. Your agent also needs clickd connected over MCP: connecting an agent shows how.
Loads skills from .claude/skills/ in the repository, for everyone who works in it, or ~/.claude/skills/ for every project on your machine. Claude uses it when a request matches its description, or type /clickd-ai-visibility.
Puts the files in .claude/skills/clickd-ai-visibility/.
Loads skills from .agents/skills/ in the repository and its parent folders, or ~/.agents/skills/ for every project. Codex uses it when a task matches its description, or mention it as $clickd-ai-visibility; /skills lists them.
Puts the files in .agents/skills/clickd-ai-visibility/.
Loads skills from .cursor/skills/ or .agents/skills/ in the repository, or ~/.cursor/skills/ for every project. It also reads .claude/skills/, so one copy there serves both. The agent uses it when it is relevant, or type / in Agent chat and pick it.
Puts the files in .cursor/skills/clickd-ai-visibility/.
An agent that does not load skills can still follow the file. Save the folder in the repository and point its standing instructions at it, with a line in AGENTS.md, which many agents read. The agent reads AGENTS.md when it starts, and follows the file when the task matches.
Terminal, for Any other agent
mkdir -p docs/clickd-ai-visibility
curl -fsSL https://clickd.com/skills/ai-visibility/SKILL.md -o docs/clickd-ai-visibility/SKILL.md
echo "For GEO, AEO and AI assistant visibility, follow docs/clickd-ai-visibility/SKILL.md." >> AGENTS.md
SKILL.md stays short and sends your agent to a reference when a step needs it.
SKILL.mdThe four steps from checking live assistant citations, AI crawler rules and non-JS readability to unblocking retrieval bots, structuring answer-first passages with entity schema, and tracking citations on clickd.86 lines
Each is in a ## Sources list in the file that cites it, by the page’s own title.
Google Search Central
1AI Features and Your Website, Google Search Central.How Google's AI Overviews and AI Mode use web search indexing, structured data and crawlable HTML.