More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    AI Readability Standard

    1

    A standard for whether an AI answer engine can read and quote a site, plus the acceptance test that refuses to call the work done until a re-measurement passes. Runs locally, no account.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    An agent can rewrite markup but cannot say whether it worked. This gives it the standard: fifteen checks against GPTBot, ClaudeBot, PerplexityBot and OAI-SearchBot, plus the files a model reads, then the page itself; each failing check returns with a meaning and a fix, and the fix order is part of it. The sixteenth measurement runs on the buyer's own model key. Everything runs locally. No account, no key, no subscription; the only hosts contacted are the site being measured and the model provider you configure.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Marketing & SEO.

    Fifteen checks are machine-decidable; a content judgement is not one of them. A firewall that serves one source a stub page and another the real page can make two runs disagree, so re-run twice before treating a difference as a regression. It measures and reports; it does not repair the site.

    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 buying a skill.

    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 today

    Accounts
    OpenAIGroqGoogle AIDeepseekOpenrouter
    Software
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    Allowed Hosts

    api.openai.com
    api.deepseek.com
    api.groq.com
    generativelanguage.googleapis.com
    openrouter.ai

    File Scopes

    ~/.citeai/providers.json

    Reads one of OPENAI_API_KEY, DEEPSEEK_API_KEY, GROQ_API_KEY, GOOGLE_API_KEY or OPENROUTER_API_KEY from the environment, only when the buyer runs the optional sixteenth measurement; a key may also be passed with --key, in which case no variable is read. A key is sent only to the provider the buyer names and never to any publisher endpoint. The fifteen machine checks contact only the domain being measured. No telemetry, no account, no call home.

    Listed2 days ago
    Updatedtoday

    What's inside

    Frequently Asked Questions

    A standard for whether an AI answer engine can read and quote a site, plus the acceptance test that refuses to call the work done until a re-measurement passes. Runs locally, no account.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use AI Readability Standard on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Marketing & SEO