More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI-Search SEO Kit: Get Cited by ChatGPT, Perplexity & Google

    1

    Audit any website for AI search, then generate and validate the files that get it cited: schema.org JSON-LD, llms.txt, a robots.txt AI-crawler policy and sitemap.xml, plus answer-first rewrite briefs.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    AI-Search SEO Kit: Get Cited by ChatGPT, Perplexity & Google

    AI-Search SEO Kit: Get Cited by ChatGPT, Perplexity & Google

    Example session with this skill installed

    Audit my bakery's website for AI search (the site files are in ./site, live at riseandcrumb.example). I want ChatGPT and Perplexity to find and cite us, but I don't want our content used to train AI models. Fix what you can and show me before and after.

    • Read your context and instructions
    • Compiled the ai-search seo kit
    • Generated the app files

    Done. Rise & Crumb Bakery went from

    32/100 (grade F) to 99/100 (grade A) on the AI-search audit. The biggest problem was not the content: a copy-pasted "block AI bots" list in robots.txt was hiding the site from ChatGPT search and Perplexity.

    Score, before → after

    PillarBeforeScripts onlyAfter rewrite
    AI answer-readiness374098
    Crawl & index4389100
    Structured data0100100
    Trust & E-E-A-T4144100
    Overall32 (F)65 (C)99 (A)

    AI crawler access (your policy: cite us, don't train on us)

    • Now allowed: all 9 AI search engines (Googlebot, Bingbot, OAI-SearchBot, PerplexityBot, Claude-SearchBot, Applebot, DuckAssistBot, Amzn-SearchBot, Meta-WebIndexer) and 5 user-triggered fetchers. OAI-SearchBot and PerplexityBot were blocked before.
    • Blocked on purpose: 7 training crawlers (GPTBot, ClaudeBot, Google-Extended, Applebot-Extended, Amazonbot, Meta-ExternalAgent, CCBot). Three of them were allowed by default before. Your /drafts/ rule is kept in every group.

    Files generated (aiseo/generated/)

    • JSON-LD for 5 pages: Bakery + WebSite (home), AboutPage + Person (about), Product + AggregateOffer $48-$165 (cakes), FAQPage with 8 questions (FAQ), BlogPosting + HowTo with 5 steps (starter guide), BreadcrumbList on every inner page
    • llms.txt (5 sections, 6 links), llms-full.txt (5 pages, 11.9 KB), robots.txt, sitemap.xml (5 URLs; lastmod only where a real date exists)

    Validation: SUMMARY: 9 of 9 files PASS, 0 FAIL line(s), 0 WARN line(s). Every FAQ question in the markup is visible on the page.

    Copy: all 5 pages rewritten answer-first from the briefs: 40-70 word intros that answer the main question with real numbers, 31 question-style headings, a byline and updated date on the guide, 2 source links, FAQ blocks. Fact density went from 0-1.2 to 9.6-14.4 numbers per 100 words. Only facts you confirmed were used.

    Injected JSON-LD, canonical and Open Graph tags into the 5 HTML files and copied the 4 root files. Originals are in site_aiseo_backup/<time>/; undo with aiseo.py restore <that folder>.

    Still open (optional): "Add depth and scannable structure" on about.html and faq.html (+0.5 points).

    Next steps

    1. Deploy the site folder.
    2. Submit sitemap.xml in Google Search Console and Bing Webmaster Tools.
    3. Re-run audit --compare after every content change and keep the dates honest.
      No tool can guarantee rankings or AI citations; this makes you the easiest source to quote.

    about.html

    ZIP · project files

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Make your site the easiest source for AI search to quote, and prove it with PASS/FAIL checks.

    Most SEO skills hand your agent a checklist. This one ships the tooling: tell your agent "Audit my site for AI search and fix what you can" and it scores every page for AI-citation readiness, generates the files ChatGPT search, Perplexity, Google AI Overviews, Copilot and Claude read, validates every one of them, writes answer-first rewrite briefs for the copy, and injects the markup into your HTML with a backup. On the bundled demo site the score goes 32 → 65 with the scripts alone, and 99 after the answer-first rewrite.

    What you get

    • Audit of a local site folder, a saved page or (only when you ask) a live URL: 30 page checks and 12 site checks in four pillars (AI answer-readiness, crawl & index, structured data, trust/E-E-A-T). Answer-first intros, question-style headings, fact density, citations, bylines, visible dates, FAQ blocks, canonical, meta, headings, alt text, broken links, sitemap coverage.
    • A report you can hand to a client: self-contained, printable HTML with score ring, pillar bars, before → after deltas, an AI-crawler access table, a page-by-page matrix and every fix ranked by its simulated point gain with the exact snippet to paste. Plus audit.json and fixes.md.
    • AI-crawler policy, done right: 21 crawlers mapped from the operators' own docs (OAI-SearchBot vs GPTBot, PerplexityBot, Claude-SearchBot vs ClaudeBot, Google-Extended, Applebot-Extended, CCBot...). Search bots in so you can be cited; training bots follow your choice. RFC 9309 matching, and your private paths survive.
    • Generators: schema.org JSON-LD per page (Organization/LocalBusiness with 100+ business subtypes, WebSite, Article/BlogPosting with author, FAQPage, HowTo, Product with Offer/AggregateOffer, BreadcrumbList, Person, AboutPage), llms.txt + llms-full.txt (llmstxt.org format), sitemap.xml and robots.txt, all from a small YAML profile and your real pages. Nothing is invented.
    • Validators that print PASS/WARN/FAIL: JSON-LD against Google's required/recommended properties, URL/date/price/currency formats, @id integrity, and a check that FAQ answers are really visible on the page; llms.txt linter; robots.txt checker; sitemap validator.
    • Answer-first rewrite briefs per page: the question to answer, suggested question headings, current fact density, and acceptance checks. Your agent writes the copy; the audit verifies it.
    • Safe inject: dry run, backup outside the site, idempotent marker blocks, never overwrites your own tags, one-command restore.
    • One-command demo on a 5-page sample business, so your first run shows the whole pipeline in about a second.

    Why it beats prompting

    Prompting a chat agentAI-Search SEO Kit
    A generic GEO checklist42 measured checks per site, scored and ranked by points gained
    Hand-written JSON-LD that may be invalidGenerated JSON-LD, validated against Google's property rules, matched to the visible page
    "Block AI bots" advice that also blocks ChatGPT searchSearch vs training crawlers separated, RFC 9309 matching, PASS/FAIL per bot
    An llms.txt nobody checksllms.txt + llms-full.txt built from your pages and linted line by line
    "Make your content better"A brief per page with the question, the headings and the checks that must pass
    Copy-paste into every pageInjected with backup, re-runnable, one-command undo

    Honest by design

    Every rule in references/ cites its source (Google Search Central, OpenAI/Anthropic/Perplexity/Apple/Amazon/Meta crawler docs, llmstxt.org, RFC 9309, sitemaps.org, the GEO research paper). Heuristics are labelled as heuristics. It tells you that Google retired FAQ and How-to rich results and that llms.txt is a proposal. No promises of rankings or citations, and no invented facts, reviews or dates.

    What's inside

    SKILL.md (10-step workflow, report template, quality checklist) · 9 Python scripts (audit engine, report, generators, validators, injector, demo) · 6 reference guides (AI crawler table, schema requirements, llms.txt spec notes, AI-citation checklist with evidence labels, scoring, profile format) · demo site, sample rewrites, demo profile and pre-built before/after reports.

    Requirements

    An agent that can run code with Python 3.8+. Standard library only: no installs, no API keys. Offline except the optional live-URL audit.

    • Automatic injection works on static HTML files. For WordPress, Shopify, Webflow or JavaScript frameworks the agent applies the generated JSON-LD and files through the platform instead.
    • The audit reads the HTML as delivered and does not run JavaScript, so content rendered only in the browser is not seen.
    • Answer-first, question-heading and fact-density checks are practitioner heuristics, not published ranking factors. No rankings, citations or rich results are guaranteed.
    • Content heuristics are tuned for English; other languages get the structural checks reliably.
    • Not covered: keyword research, backlinks, Core Web Vitals/page speed, Search Console data, competitor analysis.
    • The JSON-LD validator uses offline rule tables based on Google's documentation (October 2026); it is not Google's Rich Results Test, and Google's rules change.
    • The AI crawler list (21 bots) reflects the operators' docs as of October 2026; new bots appear regularly.
    • Live audits are capped at 200 pages on one host and skip URLs with query strings.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files

    File Scopes

    aiseo/**

    Terminal / code execution: runs the bundled Python scripts (scripts/aiseo.py, standard library only); it starts no other programs. Read files: your site folder (HTML, robots.txt, sitemap.xml, llms.txt), your site profile and the skill's own references/examples. Write files: only the output folder you choose (aiseo/ by default); your site folder is written only by inject, after a dry run and your OK, with every changed file backed up outside the site, and restore undoes it. Network access: ONLY for the optional live audit (audit --url) when you ask for it: GET requests to the one site you name, robots.txt honoured, 1 s between requests, max 200 pages, nothing uploaded. Every other command works offline. No environment variables, API keys, secrets, telemetry or installs.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Your agent can list GEO tips and write some JSON-LD. This skill gives it a tested audit engine (42 checks), generators, strict validators and a safe injector, so you get scored reports, valid files and verified changes instead of advice you have to check yourself.

    No tool can. It removes the blockers (crawler access, missing markup, vague copy, no dates or authors) and makes your pages the easiest to quote. The report says which checks are official requirements and which are practitioner heuristics.

    No. OpenAI uses OAI-SearchBot for ChatGPT search and GPTBot for model training. The kit separates search crawlers from training crawlers for 21 bots, so you can stay citable and still opt out of training.

    Yes for the audit (point it at the built HTML or, if you ask, the live URL) and for the generated files. Automatic injection is for static HTML; for a CMS or framework your agent places the generated JSON-LD and files through the platform (theme head, SEO plugin, layout component, robots.txt setting).

    Only the inject step, only after a dry run and your OK. It backs up every file outside the site folder, never overwrites your own tags, and restore undoes the run.

    No. Pure Python standard library. Network is used only for the optional live-URL audit. llms.txt is generated too, but treated as a light, optional extra because Google says AI Overviews need no special files.

    New in Marketing & SEO