aiseo-audit 1.2.7 → 1.3.0

package/README.md

@@ -5,7 +5,7 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-7EB6D7.svg)](https://opensource.org/licenses/MIT)
 [![Node.js](https://img.shields.io/badge/node-%3E%3D20-7EB6D7.svg)](https://nodejs.org)
 [![TypeScript](https://img.shields.io/badge/TypeScript-5.9-7EB6D7?logo=typescript&logoColor=white)](https://www.typescriptlang.org/)
-[![Tests](https://img.shields.io/badge/tests-194%20passed-8FBC8F)](https://github.com/agencyenterprise/aiseo-audit)
+[![Tests](https://img.shields.io/badge/tests-238%20passed-8FBC8F)](https://github.com/agencyenterprise/aiseo-audit)
 [![Coverage](https://img.shields.io/codecov/c/github/agencyenterprise/aiseo-audit?color=8FBC8F&label=coverage)](https://codecov.io/gh/agencyenterprise/aiseo-audit)
 
 <div align="center">
@@ -15,6 +15,9 @@
 
 Deterministic CLI that audits web pages for **AI search readiness**. Think Lighthouse, but for how well AI engines can fetch, extract, understand, and cite your content.
 
+> [!TIP]
+> Run `aiseo-audit https://www.aiseo-audit.com` to see a 100/100 [A+ Score](https://www.aiseo-audit.com/).
+
 **AI SEO measures how reusable your content is for generative engines, not traditional search rankings.**
 
 - [Quick Start](#quick-start)

package/dist/cli.js

@@ -27,7 +27,7 @@ var import_commander = require("commander");
 
 // src/modules/analyzer/constants.ts
 var DOMAIN_SIGNAL_TIMEOUT_CAP = 5e3;
-var VERSION = true ? "1.2.7" : "0.0.0";
+var VERSION = true ? "1.3.0" : "0.0.0";
 
 // src/modules/fetcher/constants.ts
 var MAX_RESPONSE_SIZE = 10 * 1024 * 1024;
@@ -366,7 +366,16 @@ function extractEntities(text) {
     0,
     15
   );
-  return { people, organizations, places, topics };
+  const imperativeVerbCount = doc.verbs().isImperative().length;
+  const numberCount = doc.numbers().length;
+  return {
+    people,
+    organizations,
+    places,
+    topics,
+    imperativeVerbCount,
+    numberCount
+  };
 }
 function computeFleschReadingEase(text) {
   const words = text.split(/\s+/).filter((w) => w.length > 0);
@@ -435,6 +444,7 @@ function auditAnswerability(page) {
   const text = page.cleanText;
   const $ = page.$;
   const factors = [];
+  const { imperativeVerbCount = 0 } = extractEntities(text);
   const defCount = countPatternMatches(text, DEFINITION_PATTERNS);
   const defScore = thresholdScore(defCount, [
     [6, 10],
@@ -479,7 +489,7 @@ function auditAnswerability(page) {
   );
   const stepCount = countPatternMatches(text, STEP_PATTERNS);
   const hasOl = $("ol").length > 0;
-  const stepTotal = stepCount + (hasOl ? 2 : 0);
+  const stepTotal = stepCount + imperativeVerbCount + (hasOl ? 2 : 0);
   const stepScore = thresholdScore(stepTotal, [
     [5, 10],
     [2, 7],
@@ -491,7 +501,7 @@ function auditAnswerability(page) {
       "Step-by-Step Content",
       stepScore,
       10,
-      `${stepCount} step indicators${hasOl ? ", ordered lists found" : ""}`
+      `${stepCount} step indicators, ${imperativeVerbCount} instruction verbs${hasOl ? ", ordered lists found" : ""}`
     )
   );
   const questionMatches = text.match(/[^.!?]*\?/g) || [];
@@ -790,51 +800,99 @@ function auditAuthorityContext(page) {
 }
 
 // src/modules/audits/support/robots.ts
+function parseRobotGroups(robotsTxt) {
+  const groups = [];
+  let current = null;
+  for (const raw of robotsTxt.split("\n")) {
+    const line = raw.split("#")[0].trim();
+    if (!line) {
+      current = null;
+      continue;
+    }
+    const colonAt = line.indexOf(":");
+    if (colonAt === -1) continue;
+    const field = line.slice(0, colonAt).trim().toLowerCase();
+    const value = line.slice(colonAt + 1).trim();
+    if (field === "user-agent") {
+      if (!current) {
+        current = { agents: [], rules: [] };
+        groups.push(current);
+      }
+      current.agents.push(value.toLowerCase());
+    } else if (field === "disallow" || field === "allow") {
+      if (current) {
+        current.rules.push({ type: field, path: value });
+      }
+    }
+  }
+  return groups;
+}
+function matchingRulesForCrawler(groups, crawlerLower) {
+  const specific = [];
+  const wildcard = [];
+  for (const group of groups) {
+    if (group.agents.includes(crawlerLower)) specific.push(...group.rules);
+    else if (group.agents.includes("*")) wildcard.push(...group.rules);
+  }
+  return { specific, wildcard };
+}
+function resolvesPathAsBlocked(rules, path) {
+  let bestMatchLength = -1;
+  let bestMatchIsDisallow = false;
+  for (const rule of rules) {
+    const rulePath = rule.path;
+    if (!rulePath || !path.startsWith(rulePath)) continue;
+    if (rulePath.length > bestMatchLength) {
+      bestMatchLength = rulePath.length;
+      bestMatchIsDisallow = rule.type === "disallow";
+    } else if (rulePath.length === bestMatchLength && rule.type === "allow") {
+      bestMatchIsDisallow = false;
+    }
+  }
+  return bestMatchLength >= 0 && bestMatchIsDisallow;
+}
+function findPartialBlocks(rules) {
+  return rules.filter((r) => r.type === "disallow" && r.path && r.path !== "/").map((r) => r.path);
+}
 function checkCrawlerAccess(robotsTxt) {
   if (!robotsTxt)
     return { allowed: [], blocked: [], unknown: [...AI_CRAWLERS] };
-  const lines = robotsTxt.split("\n").map((l) => l.trim());
+  const groups = parseRobotGroups(robotsTxt);
   const allowed = [];
   const blocked = [];
   const unknown = [];
+  const partiallyBlocked = [];
   for (const crawler of AI_CRAWLERS) {
     const crawlerLower = crawler.toLowerCase();
-    let currentAgent = "";
-    let isBlocked = false;
-    let found = false;
-    for (const line of lines) {
-      const lower = line.toLowerCase();
-      if (lower.startsWith("user-agent:")) {
-        currentAgent = lower.split(":")[1]?.trim() || "";
-      } else if (currentAgent === crawlerLower || currentAgent === "*") {
-        if (lower.startsWith("disallow:")) {
-          const path = lower.split(":")[1]?.trim();
-          if (path === "/") {
-            if (currentAgent === crawlerLower) {
-              isBlocked = true;
-              found = true;
-            } else if (currentAgent === "*" && !found) {
-              isBlocked = true;
-            }
-          }
-        } else if (lower.startsWith("allow:")) {
-          if (currentAgent === crawlerLower) {
-            found = true;
-            isBlocked = false;
-          }
-        }
-      }
+    const { specific, wildcard } = matchingRulesForCrawler(
+      groups,
+      crawlerLower
+    );
+    const applicableRules = specific.length > 0 ? specific : wildcard;
+    if (applicableRules.length === 0) {
+      unknown.push(crawler);
+      continue;
     }
-    if (found) {
-      if (isBlocked) blocked.push(crawler);
-      else allowed.push(crawler);
-    } else if (isBlocked) {
+    const isSiteBlocked = resolvesPathAsBlocked(applicableRules, "/");
+    if (isSiteBlocked) {
       blocked.push(crawler);
     } else {
-      unknown.push(crawler);
+      allowed.push(crawler);
+      const pathBlocks = findPartialBlocks(applicableRules);
+      for (const path of pathBlocks) {
+        const entry = `${crawler}: ${path}`;
+        if (!partiallyBlocked.includes(entry)) {
+          partiallyBlocked.push(entry);
+        }
+      }
     }
   }
-  return { allowed, blocked, unknown };
+  return {
+    allowed,
+    blocked,
+    unknown,
+    ...partiallyBlocked.length > 0 && { partiallyBlocked }
+  };
 }
 
 // src/modules/audits/categories/content-extractability.ts
@@ -851,7 +909,7 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
     )
   );
   const extractRatio = page.stats.rawByteLength > 0 ? page.stats.cleanTextLength / page.stats.rawByteLength : 0;
-  const extractScore = extractRatio >= 0.05 && extractRatio <= 0.15 ? 12 : extractRatio >= 0.01 ? 8 : extractRatio > 0.15 ? 10 : 2;
+  const extractScore = extractRatio >= 0.05 && extractRatio <= 0.15 ? 12 : extractRatio > 0.15 ? 10 : extractRatio >= 0.01 ? 8 : 2;
   factors.push(
     makeFactor(
       "Text Extraction Quality",
@@ -876,7 +934,7 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
     )
   );
   const wc = page.stats.wordCount;
-  const wcScore = wc >= 300 && wc <= 3e3 ? 12 : wc >= 100 ? 8 : wc > 3e3 ? 10 : 2;
+  const wcScore = wc >= 300 && wc <= 3e3 ? 12 : wc > 3e3 ? 10 : wc >= 100 ? 8 : 2;
   factors.push(makeFactor("Word Count Adequacy", wcScore, 12, `${wc} words`));
   if (domainSignals) {
     const access2 = checkCrawlerAccess(domainSignals.robotsTxt);
@@ -891,6 +949,10 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
       )
     );
     rawData.crawlerAccess = access2;
+    rawData.llmsTxt = {
+      llmsTxtExists: domainSignals.llmsTxtExists,
+      llmsFullTxtExists: domainSignals.llmsFullTxtExists
+    };
     const hasLlms = domainSignals.llmsTxtExists;
     const hasLlmsFull = domainSignals.llmsFullTxtExists;
     const llmsScore = hasLlms && hasLlmsFull ? 6 : hasLlms || hasLlmsFull ? 4 : 0;
@@ -1110,6 +1172,7 @@ function auditGroundingSignals(page) {
   const $ = page.$;
   const text = page.cleanText;
   const factors = [];
+  const { numberCount = 0 } = extractEntities(text);
   const externalLinks = page.externalLinks;
   const extScore = thresholdScore(externalLinks.length, [
     [6, 13],
@@ -1143,7 +1206,8 @@ function auditGroundingSignals(page) {
     )
   );
   const numericCount = countPatternMatches(text, NUMERIC_CLAIM_PATTERNS);
-  const numScore = thresholdScore(numericCount, [
+  const totalNumericSignals = numericCount + numberCount;
+  const numScore = thresholdScore(totalNumericSignals, [
     [9, 13],
     [4, 9],
     [1, 5],
@@ -1154,7 +1218,7 @@ function auditGroundingSignals(page) {
       "Numeric Claims",
       numScore,
       13,
-      `${numericCount} statistical references`
+      `${numericCount} statistical references, ${numberCount} numeric values`
     )
   );
   const attrCount = countPatternMatches(text, ATTRIBUTION_PATTERNS);
@@ -1359,7 +1423,11 @@ function removeBoilerplate($) {
 function normalizeWhitespace(text) {
   return text.replace(/\s+/g, " ").trim();
 }
+var BLOCK_ELEMENTS = "p,div,td,th,li,h1,h2,h3,h4,h5,h6,dt,dd,br,blockquote,section,article";
 function extractCleanText($) {
+  $(BLOCK_ELEMENTS).each((_, el) => {
+    $(el).append(" ");
+  });
   return normalizeWhitespace($("body").text());
 }
 
@@ -1368,7 +1436,9 @@ function extractPage(html, url) {
   const $ = cheerio.load(html);
   const title = $("title").text().trim() || $('meta[property="og:title"]').attr("content")?.trim() || "";
   const metaDescription = $('meta[name="description"]').attr("content")?.trim() || $('meta[property="og:description"]').attr("content")?.trim() || "";
-  const rawText = $("body").text().replace(/\s+/g, " ").trim();
+  const $raw = cheerio.load(html);
+  $raw("script, style, noscript").remove();
+  const rawText = $raw("body").text().replace(/\s+/g, " ").trim();
   const rawByteLength = Buffer.byteLength(html, "utf-8");
   const h1Count = $("h1").length;
   const h2Count = $("h2").length;
@@ -1380,9 +1450,22 @@ function extractPage(html, url) {
   const listItemCount = $("li").length;
   const tableCount = $("table").length;
   const paragraphCount = $("p").length;
+  const GENERIC_ALT_VALUES = /* @__PURE__ */ new Set([
+    "image",
+    "photo",
+    "logo",
+    "icon",
+    "picture",
+    "img",
+    "graphic",
+    "thumbnail"
+  ]);
   let imagesWithAlt = 0;
   $("img").each((_, el) => {
-    if ($(el).attr("alt")) imagesWithAlt++;
+    const alt = $(el).attr("alt")?.trim() ?? "";
+    const words = alt.split(/\s+/).filter((w) => w.length > 0);
+    const isMeaningful = words.length > 1 && alt.length < 200 && !GENERIC_ALT_VALUES.has(alt.toLowerCase());
+    if (isMeaningful) imagesWithAlt++;
   });
   const pageDomain = getDomain(url);
   const externalLinks = [];
@@ -1516,9 +1599,19 @@ var RECOMMENDATION_BUILDERS = {
     }
     return `Your robots.txt is blocking ${blocked}. Blocking these crawlers means your content cannot be discovered or cited by AI engines.`;
   },
-  "LLMs.txt Presence": static_(
-    "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site, helping them understand and reference your content more effectively."
-  ),
+  "LLMs.txt Presence": (rawData) => {
+    const llms = rawData.llmsTxt;
+    if (!llms) {
+      return "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site.";
+    }
+    if (llms.llmsTxtExists && !llms.llmsFullTxtExists) {
+      return "You have llms.txt but are missing llms-full.txt. Adding llms-full.txt provides AI systems with a comprehensive version of your site documentation for deeper ingestion.";
+    }
+    if (!llms.llmsTxtExists && llms.llmsFullTxtExists) {
+      return "You have llms-full.txt but are missing llms.txt. Adding llms.txt provides AI systems with a concise structured overview of your site's purpose and key pages.";
+    }
+    return "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site.";
+  },
   "Image Accessibility": (rawData) => {
     const images = rawData.imageAccessibility;
     if (!images || images.imageCount === 0) {

package/dist/cli.mjs

@@ -3,7 +3,7 @@ import { Command } from "commander";
 
 // src/modules/analyzer/constants.ts
 var DOMAIN_SIGNAL_TIMEOUT_CAP = 5e3;
-var VERSION = true ? "1.2.7" : "0.0.0";
+var VERSION = true ? "1.3.0" : "0.0.0";
 
 // src/modules/fetcher/constants.ts
 var MAX_RESPONSE_SIZE = 10 * 1024 * 1024;
@@ -342,7 +342,16 @@ function extractEntities(text) {
     0,
     15
   );
-  return { people, organizations, places, topics };
+  const imperativeVerbCount = doc.verbs().isImperative().length;
+  const numberCount = doc.numbers().length;
+  return {
+    people,
+    organizations,
+    places,
+    topics,
+    imperativeVerbCount,
+    numberCount
+  };
 }
 function computeFleschReadingEase(text) {
   const words = text.split(/\s+/).filter((w) => w.length > 0);
@@ -411,6 +420,7 @@ function auditAnswerability(page) {
   const text = page.cleanText;
   const $ = page.$;
   const factors = [];
+  const { imperativeVerbCount = 0 } = extractEntities(text);
   const defCount = countPatternMatches(text, DEFINITION_PATTERNS);
   const defScore = thresholdScore(defCount, [
     [6, 10],
@@ -455,7 +465,7 @@ function auditAnswerability(page) {
   );
   const stepCount = countPatternMatches(text, STEP_PATTERNS);
   const hasOl = $("ol").length > 0;
-  const stepTotal = stepCount + (hasOl ? 2 : 0);
+  const stepTotal = stepCount + imperativeVerbCount + (hasOl ? 2 : 0);
   const stepScore = thresholdScore(stepTotal, [
     [5, 10],
     [2, 7],
@@ -467,7 +477,7 @@ function auditAnswerability(page) {
       "Step-by-Step Content",
       stepScore,
       10,
-      `${stepCount} step indicators${hasOl ? ", ordered lists found" : ""}`
+      `${stepCount} step indicators, ${imperativeVerbCount} instruction verbs${hasOl ? ", ordered lists found" : ""}`
     )
   );
   const questionMatches = text.match(/[^.!?]*\?/g) || [];
@@ -766,51 +776,99 @@ function auditAuthorityContext(page) {
 }
 
 // src/modules/audits/support/robots.ts
+function parseRobotGroups(robotsTxt) {
+  const groups = [];
+  let current = null;
+  for (const raw of robotsTxt.split("\n")) {
+    const line = raw.split("#")[0].trim();
+    if (!line) {
+      current = null;
+      continue;
+    }
+    const colonAt = line.indexOf(":");
+    if (colonAt === -1) continue;
+    const field = line.slice(0, colonAt).trim().toLowerCase();
+    const value = line.slice(colonAt + 1).trim();
+    if (field === "user-agent") {
+      if (!current) {
+        current = { agents: [], rules: [] };
+        groups.push(current);
+      }
+      current.agents.push(value.toLowerCase());
+    } else if (field === "disallow" || field === "allow") {
+      if (current) {
+        current.rules.push({ type: field, path: value });
+      }
+    }
+  }
+  return groups;
+}
+function matchingRulesForCrawler(groups, crawlerLower) {
+  const specific = [];
+  const wildcard = [];
+  for (const group of groups) {
+    if (group.agents.includes(crawlerLower)) specific.push(...group.rules);
+    else if (group.agents.includes("*")) wildcard.push(...group.rules);
+  }
+  return { specific, wildcard };
+}
+function resolvesPathAsBlocked(rules, path) {
+  let bestMatchLength = -1;
+  let bestMatchIsDisallow = false;
+  for (const rule of rules) {
+    const rulePath = rule.path;
+    if (!rulePath || !path.startsWith(rulePath)) continue;
+    if (rulePath.length > bestMatchLength) {
+      bestMatchLength = rulePath.length;
+      bestMatchIsDisallow = rule.type === "disallow";
+    } else if (rulePath.length === bestMatchLength && rule.type === "allow") {
+      bestMatchIsDisallow = false;
+    }
+  }
+  return bestMatchLength >= 0 && bestMatchIsDisallow;
+}
+function findPartialBlocks(rules) {
+  return rules.filter((r) => r.type === "disallow" && r.path && r.path !== "/").map((r) => r.path);
+}
 function checkCrawlerAccess(robotsTxt) {
   if (!robotsTxt)
     return { allowed: [], blocked: [], unknown: [...AI_CRAWLERS] };
-  const lines = robotsTxt.split("\n").map((l) => l.trim());
+  const groups = parseRobotGroups(robotsTxt);
   const allowed = [];
   const blocked = [];
   const unknown = [];
+  const partiallyBlocked = [];
   for (const crawler of AI_CRAWLERS) {
     const crawlerLower = crawler.toLowerCase();
-    let currentAgent = "";
-    let isBlocked = false;
-    let found = false;
-    for (const line of lines) {
-      const lower = line.toLowerCase();
-      if (lower.startsWith("user-agent:")) {
-        currentAgent = lower.split(":")[1]?.trim() || "";
-      } else if (currentAgent === crawlerLower || currentAgent === "*") {
-        if (lower.startsWith("disallow:")) {
-          const path = lower.split(":")[1]?.trim();
-          if (path === "/") {
-            if (currentAgent === crawlerLower) {
-              isBlocked = true;
-              found = true;
-            } else if (currentAgent === "*" && !found) {
-              isBlocked = true;
-            }
-          }
-        } else if (lower.startsWith("allow:")) {
-          if (currentAgent === crawlerLower) {
-            found = true;
-            isBlocked = false;
-          }
-        }
-      }
+    const { specific, wildcard } = matchingRulesForCrawler(
+      groups,
+      crawlerLower
+    );
+    const applicableRules = specific.length > 0 ? specific : wildcard;
+    if (applicableRules.length === 0) {
+      unknown.push(crawler);
+      continue;
     }
-    if (found) {
-      if (isBlocked) blocked.push(crawler);
-      else allowed.push(crawler);
-    } else if (isBlocked) {
+    const isSiteBlocked = resolvesPathAsBlocked(applicableRules, "/");
+    if (isSiteBlocked) {
       blocked.push(crawler);
     } else {
-      unknown.push(crawler);
+      allowed.push(crawler);
+      const pathBlocks = findPartialBlocks(applicableRules);
+      for (const path of pathBlocks) {
+        const entry = `${crawler}: ${path}`;
+        if (!partiallyBlocked.includes(entry)) {
+          partiallyBlocked.push(entry);
+        }
+      }
     }
   }
-  return { allowed, blocked, unknown };
+  return {
+    allowed,
+    blocked,
+    unknown,
+    ...partiallyBlocked.length > 0 && { partiallyBlocked }
+  };
 }
 
 // src/modules/audits/categories/content-extractability.ts
@@ -827,7 +885,7 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
     )
   );
   const extractRatio = page.stats.rawByteLength > 0 ? page.stats.cleanTextLength / page.stats.rawByteLength : 0;
-  const extractScore = extractRatio >= 0.05 && extractRatio <= 0.15 ? 12 : extractRatio >= 0.01 ? 8 : extractRatio > 0.15 ? 10 : 2;
+  const extractScore = extractRatio >= 0.05 && extractRatio <= 0.15 ? 12 : extractRatio > 0.15 ? 10 : extractRatio >= 0.01 ? 8 : 2;
   factors.push(
     makeFactor(
       "Text Extraction Quality",
@@ -852,7 +910,7 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
     )
   );
   const wc = page.stats.wordCount;
-  const wcScore = wc >= 300 && wc <= 3e3 ? 12 : wc >= 100 ? 8 : wc > 3e3 ? 10 : 2;
+  const wcScore = wc >= 300 && wc <= 3e3 ? 12 : wc > 3e3 ? 10 : wc >= 100 ? 8 : 2;
   factors.push(makeFactor("Word Count Adequacy", wcScore, 12, `${wc} words`));
   if (domainSignals) {
     const access2 = checkCrawlerAccess(domainSignals.robotsTxt);
@@ -867,6 +925,10 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
       )
     );
     rawData.crawlerAccess = access2;
+    rawData.llmsTxt = {
+      llmsTxtExists: domainSignals.llmsTxtExists,
+      llmsFullTxtExists: domainSignals.llmsFullTxtExists
+    };
     const hasLlms = domainSignals.llmsTxtExists;
     const hasLlmsFull = domainSignals.llmsFullTxtExists;
     const llmsScore = hasLlms && hasLlmsFull ? 6 : hasLlms || hasLlmsFull ? 4 : 0;
@@ -1086,6 +1148,7 @@ function auditGroundingSignals(page) {
   const $ = page.$;
   const text = page.cleanText;
   const factors = [];
+  const { numberCount = 0 } = extractEntities(text);
   const externalLinks = page.externalLinks;
   const extScore = thresholdScore(externalLinks.length, [
     [6, 13],
@@ -1119,7 +1182,8 @@ function auditGroundingSignals(page) {
     )
   );
   const numericCount = countPatternMatches(text, NUMERIC_CLAIM_PATTERNS);
-  const numScore = thresholdScore(numericCount, [
+  const totalNumericSignals = numericCount + numberCount;
+  const numScore = thresholdScore(totalNumericSignals, [
     [9, 13],
     [4, 9],
     [1, 5],
@@ -1130,7 +1194,7 @@ function auditGroundingSignals(page) {
       "Numeric Claims",
       numScore,
       13,
-      `${numericCount} statistical references`
+      `${numericCount} statistical references, ${numberCount} numeric values`
     )
   );
   const attrCount = countPatternMatches(text, ATTRIBUTION_PATTERNS);
@@ -1335,7 +1399,11 @@ function removeBoilerplate($) {
 function normalizeWhitespace(text) {
   return text.replace(/\s+/g, " ").trim();
 }
+var BLOCK_ELEMENTS = "p,div,td,th,li,h1,h2,h3,h4,h5,h6,dt,dd,br,blockquote,section,article";
 function extractCleanText($) {
+  $(BLOCK_ELEMENTS).each((_, el) => {
+    $(el).append(" ");
+  });
   return normalizeWhitespace($("body").text());
 }
 
@@ -1344,7 +1412,9 @@ function extractPage(html, url) {
   const $ = cheerio.load(html);
   const title = $("title").text().trim() || $('meta[property="og:title"]').attr("content")?.trim() || "";
   const metaDescription = $('meta[name="description"]').attr("content")?.trim() || $('meta[property="og:description"]').attr("content")?.trim() || "";
-  const rawText = $("body").text().replace(/\s+/g, " ").trim();
+  const $raw = cheerio.load(html);
+  $raw("script, style, noscript").remove();
+  const rawText = $raw("body").text().replace(/\s+/g, " ").trim();
   const rawByteLength = Buffer.byteLength(html, "utf-8");
   const h1Count = $("h1").length;
   const h2Count = $("h2").length;
@@ -1356,9 +1426,22 @@ function extractPage(html, url) {
   const listItemCount = $("li").length;
   const tableCount = $("table").length;
   const paragraphCount = $("p").length;
+  const GENERIC_ALT_VALUES = /* @__PURE__ */ new Set([
+    "image",
+    "photo",
+    "logo",
+    "icon",
+    "picture",
+    "img",
+    "graphic",
+    "thumbnail"
+  ]);
   let imagesWithAlt = 0;
   $("img").each((_, el) => {
-    if ($(el).attr("alt")) imagesWithAlt++;
+    const alt = $(el).attr("alt")?.trim() ?? "";
+    const words = alt.split(/\s+/).filter((w) => w.length > 0);
+    const isMeaningful = words.length > 1 && alt.length < 200 && !GENERIC_ALT_VALUES.has(alt.toLowerCase());
+    if (isMeaningful) imagesWithAlt++;
   });
   const pageDomain = getDomain(url);
   const externalLinks = [];
@@ -1492,9 +1575,19 @@ var RECOMMENDATION_BUILDERS = {
     }
     return `Your robots.txt is blocking ${blocked}. Blocking these crawlers means your content cannot be discovered or cited by AI engines.`;
   },
-  "LLMs.txt Presence": static_(
-    "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site, helping them understand and reference your content more effectively."
-  ),
+  "LLMs.txt Presence": (rawData) => {
+    const llms = rawData.llmsTxt;
+    if (!llms) {
+      return "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site.";
+    }
+    if (llms.llmsTxtExists && !llms.llmsFullTxtExists) {
+      return "You have llms.txt but are missing llms-full.txt. Adding llms-full.txt provides AI systems with a comprehensive version of your site documentation for deeper ingestion.";
+    }
+    if (!llms.llmsTxtExists && llms.llmsFullTxtExists) {
+      return "You have llms-full.txt but are missing llms.txt. Adding llms.txt provides AI systems with a concise structured overview of your site's purpose and key pages.";
+    }
+    return "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site.";
+  },
   "Image Accessibility": (rawData) => {
     const images = rawData.imageAccessibility;
     if (!images || images.imageCount === 0) {

package/dist/index.d.mts

@@ -90,6 +90,11 @@ declare const AnalyzerResultSchema: z.ZodObject<{
             allowed: z.ZodArray<z.ZodString>;
             blocked: z.ZodArray<z.ZodString>;
             unknown: z.ZodArray<z.ZodString>;
+            partiallyBlocked: z.ZodOptional<z.ZodArray<z.ZodString>>;
+        }, z.core.$strip>>;
+        llmsTxt: z.ZodOptional<z.ZodObject<{
+            llmsTxtExists: z.ZodBoolean;
+            llmsFullTxtExists: z.ZodBoolean;
         }, z.core.$strip>>;
         sectionLengths: z.ZodOptional<z.ZodObject<{
             sectionCount: z.ZodNumber;
@@ -105,6 +110,8 @@ declare const AnalyzerResultSchema: z.ZodObject<{
             organizations: z.ZodArray<z.ZodString>;
             places: z.ZodArray<z.ZodString>;
             topics: z.ZodArray<z.ZodString>;
+            imperativeVerbCount: z.ZodOptional<z.ZodNumber>;
+            numberCount: z.ZodOptional<z.ZodNumber>;
         }, z.core.$strip>>;
         externalLinks: z.ZodOptional<z.ZodArray<z.ZodObject<{
             url: z.ZodString;
@@ -266,6 +273,11 @@ declare const AuditResultSchema: z.ZodObject<{
             allowed: z.ZodArray<z.ZodString>;
             blocked: z.ZodArray<z.ZodString>;
             unknown: z.ZodArray<z.ZodString>;
+            partiallyBlocked: z.ZodOptional<z.ZodArray<z.ZodString>>;
+        }, z.core.$strip>>;
+        llmsTxt: z.ZodOptional<z.ZodObject<{
+            llmsTxtExists: z.ZodBoolean;
+            llmsFullTxtExists: z.ZodBoolean;
         }, z.core.$strip>>;
         sectionLengths: z.ZodOptional<z.ZodObject<{
             sectionCount: z.ZodNumber;
@@ -281,6 +293,8 @@ declare const AuditResultSchema: z.ZodObject<{
             organizations: z.ZodArray<z.ZodString>;
             places: z.ZodArray<z.ZodString>;
             topics: z.ZodArray<z.ZodString>;
+            imperativeVerbCount: z.ZodOptional<z.ZodNumber>;
+            numberCount: z.ZodOptional<z.ZodNumber>;
         }, z.core.$strip>>;
         externalLinks: z.ZodOptional<z.ZodArray<z.ZodObject<{
             url: z.ZodString;

package/dist/index.d.ts

@@ -90,6 +90,11 @@ declare const AnalyzerResultSchema: z.ZodObject<{
             allowed: z.ZodArray<z.ZodString>;
             blocked: z.ZodArray<z.ZodString>;
             unknown: z.ZodArray<z.ZodString>;
+            partiallyBlocked: z.ZodOptional<z.ZodArray<z.ZodString>>;
+        }, z.core.$strip>>;
+        llmsTxt: z.ZodOptional<z.ZodObject<{
+            llmsTxtExists: z.ZodBoolean;
+            llmsFullTxtExists: z.ZodBoolean;
         }, z.core.$strip>>;
         sectionLengths: z.ZodOptional<z.ZodObject<{
             sectionCount: z.ZodNumber;
@@ -105,6 +110,8 @@ declare const AnalyzerResultSchema: z.ZodObject<{
             organizations: z.ZodArray<z.ZodString>;
             places: z.ZodArray<z.ZodString>;
             topics: z.ZodArray<z.ZodString>;
+            imperativeVerbCount: z.ZodOptional<z.ZodNumber>;
+            numberCount: z.ZodOptional<z.ZodNumber>;
         }, z.core.$strip>>;
         externalLinks: z.ZodOptional<z.ZodArray<z.ZodObject<{
             url: z.ZodString;
@@ -266,6 +273,11 @@ declare const AuditResultSchema: z.ZodObject<{
             allowed: z.ZodArray<z.ZodString>;
             blocked: z.ZodArray<z.ZodString>;
             unknown: z.ZodArray<z.ZodString>;
+            partiallyBlocked: z.ZodOptional<z.ZodArray<z.ZodString>>;
+        }, z.core.$strip>>;
+        llmsTxt: z.ZodOptional<z.ZodObject<{
+            llmsTxtExists: z.ZodBoolean;
+            llmsFullTxtExists: z.ZodBoolean;
         }, z.core.$strip>>;
         sectionLengths: z.ZodOptional<z.ZodObject<{
             sectionCount: z.ZodNumber;
@@ -281,6 +293,8 @@ declare const AuditResultSchema: z.ZodObject<{
             organizations: z.ZodArray<z.ZodString>;
             places: z.ZodArray<z.ZodString>;
             topics: z.ZodArray<z.ZodString>;
+            imperativeVerbCount: z.ZodOptional<z.ZodNumber>;
+            numberCount: z.ZodOptional<z.ZodNumber>;
         }, z.core.$strip>>;
         externalLinks: z.ZodOptional<z.ZodArray<z.ZodObject<{
             url: z.ZodString;

package/dist/index.js

@@ -364,7 +364,16 @@ function extractEntities(text) {
     0,
     15
   );
-  return { people, organizations, places, topics };
+  const imperativeVerbCount = doc.verbs().isImperative().length;
+  const numberCount = doc.numbers().length;
+  return {
+    people,
+    organizations,
+    places,
+    topics,
+    imperativeVerbCount,
+    numberCount
+  };
 }
 function computeFleschReadingEase(text) {
   const words = text.split(/\s+/).filter((w) => w.length > 0);
@@ -433,6 +442,7 @@ function auditAnswerability(page) {
   const text = page.cleanText;
   const $ = page.$;
   const factors = [];
+  const { imperativeVerbCount = 0 } = extractEntities(text);
   const defCount = countPatternMatches(text, DEFINITION_PATTERNS);
   const defScore = thresholdScore(defCount, [
     [6, 10],
@@ -477,7 +487,7 @@ function auditAnswerability(page) {
   );
   const stepCount = countPatternMatches(text, STEP_PATTERNS);
   const hasOl = $("ol").length > 0;
-  const stepTotal = stepCount + (hasOl ? 2 : 0);
+  const stepTotal = stepCount + imperativeVerbCount + (hasOl ? 2 : 0);
   const stepScore = thresholdScore(stepTotal, [
     [5, 10],
     [2, 7],
@@ -489,7 +499,7 @@ function auditAnswerability(page) {
       "Step-by-Step Content",
       stepScore,
       10,
-      `${stepCount} step indicators${hasOl ? ", ordered lists found" : ""}`
+      `${stepCount} step indicators, ${imperativeVerbCount} instruction verbs${hasOl ? ", ordered lists found" : ""}`
     )
   );
   const questionMatches = text.match(/[^.!?]*\?/g) || [];
@@ -788,51 +798,99 @@ function auditAuthorityContext(page) {
 }
 
 // src/modules/audits/support/robots.ts
+function parseRobotGroups(robotsTxt) {
+  const groups = [];
+  let current = null;
+  for (const raw of robotsTxt.split("\n")) {
+    const line = raw.split("#")[0].trim();
+    if (!line) {
+      current = null;
+      continue;
+    }
+    const colonAt = line.indexOf(":");
+    if (colonAt === -1) continue;
+    const field = line.slice(0, colonAt).trim().toLowerCase();
+    const value = line.slice(colonAt + 1).trim();
+    if (field === "user-agent") {
+      if (!current) {
+        current = { agents: [], rules: [] };
+        groups.push(current);
+      }
+      current.agents.push(value.toLowerCase());
+    } else if (field === "disallow" || field === "allow") {
+      if (current) {
+        current.rules.push({ type: field, path: value });
+      }
+    }
+  }
+  return groups;
+}
+function matchingRulesForCrawler(groups, crawlerLower) {
+  const specific = [];
+  const wildcard = [];
+  for (const group of groups) {
+    if (group.agents.includes(crawlerLower)) specific.push(...group.rules);
+    else if (group.agents.includes("*")) wildcard.push(...group.rules);
+  }
+  return { specific, wildcard };
+}
+function resolvesPathAsBlocked(rules, path) {
+  let bestMatchLength = -1;
+  let bestMatchIsDisallow = false;
+  for (const rule of rules) {
+    const rulePath = rule.path;
+    if (!rulePath || !path.startsWith(rulePath)) continue;
+    if (rulePath.length > bestMatchLength) {
+      bestMatchLength = rulePath.length;
+      bestMatchIsDisallow = rule.type === "disallow";
+    } else if (rulePath.length === bestMatchLength && rule.type === "allow") {
+      bestMatchIsDisallow = false;
+    }
+  }
+  return bestMatchLength >= 0 && bestMatchIsDisallow;
+}
+function findPartialBlocks(rules) {
+  return rules.filter((r) => r.type === "disallow" && r.path && r.path !== "/").map((r) => r.path);
+}
 function checkCrawlerAccess(robotsTxt) {
   if (!robotsTxt)
     return { allowed: [], blocked: [], unknown: [...AI_CRAWLERS] };
-  const lines = robotsTxt.split("\n").map((l) => l.trim());
+  const groups = parseRobotGroups(robotsTxt);
   const allowed = [];
   const blocked = [];
   const unknown = [];
+  const partiallyBlocked = [];
   for (const crawler of AI_CRAWLERS) {
     const crawlerLower = crawler.toLowerCase();
-    let currentAgent = "";
-    let isBlocked = false;
-    let found = false;
-    for (const line of lines) {
-      const lower = line.toLowerCase();
-      if (lower.startsWith("user-agent:")) {
-        currentAgent = lower.split(":")[1]?.trim() || "";
-      } else if (currentAgent === crawlerLower || currentAgent === "*") {
-        if (lower.startsWith("disallow:")) {
-          const path = lower.split(":")[1]?.trim();
-          if (path === "/") {
-            if (currentAgent === crawlerLower) {
-              isBlocked = true;
-              found = true;
-            } else if (currentAgent === "*" && !found) {
-              isBlocked = true;
-            }
-          }
-        } else if (lower.startsWith("allow:")) {
-          if (currentAgent === crawlerLower) {
-            found = true;
-            isBlocked = false;
-          }
-        }
-      }
+    const { specific, wildcard } = matchingRulesForCrawler(
+      groups,
+      crawlerLower
+    );
+    const applicableRules = specific.length > 0 ? specific : wildcard;
+    if (applicableRules.length === 0) {
+      unknown.push(crawler);
+      continue;
     }
-    if (found) {
-      if (isBlocked) blocked.push(crawler);
-      else allowed.push(crawler);
-    } else if (isBlocked) {
+    const isSiteBlocked = resolvesPathAsBlocked(applicableRules, "/");
+    if (isSiteBlocked) {
       blocked.push(crawler);
     } else {
-      unknown.push(crawler);
+      allowed.push(crawler);
+      const pathBlocks = findPartialBlocks(applicableRules);
+      for (const path of pathBlocks) {
+        const entry = `${crawler}: ${path}`;
+        if (!partiallyBlocked.includes(entry)) {
+          partiallyBlocked.push(entry);
+        }
+      }
     }
   }
-  return { allowed, blocked, unknown };
+  return {
+    allowed,
+    blocked,
+    unknown,
+    ...partiallyBlocked.length > 0 && { partiallyBlocked }
+  };
 }
 
 // src/modules/audits/categories/content-extractability.ts
@@ -849,7 +907,7 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
     )
   );
   const extractRatio = page.stats.rawByteLength > 0 ? page.stats.cleanTextLength / page.stats.rawByteLength : 0;
-  const extractScore = extractRatio >= 0.05 && extractRatio <= 0.15 ? 12 : extractRatio >= 0.01 ? 8 : extractRatio > 0.15 ? 10 : 2;
+  const extractScore = extractRatio >= 0.05 && extractRatio <= 0.15 ? 12 : extractRatio > 0.15 ? 10 : extractRatio >= 0.01 ? 8 : 2;
   factors.push(
     makeFactor(
       "Text Extraction Quality",
@@ -874,7 +932,7 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
     )
   );
   const wc = page.stats.wordCount;
-  const wcScore = wc >= 300 && wc <= 3e3 ? 12 : wc >= 100 ? 8 : wc > 3e3 ? 10 : 2;
+  const wcScore = wc >= 300 && wc <= 3e3 ? 12 : wc > 3e3 ? 10 : wc >= 100 ? 8 : 2;
   factors.push(makeFactor("Word Count Adequacy", wcScore, 12, `${wc} words`));
   if (domainSignals) {
     const access2 = checkCrawlerAccess(domainSignals.robotsTxt);
@@ -889,6 +947,10 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
       )
     );
     rawData.crawlerAccess = access2;
+    rawData.llmsTxt = {
+      llmsTxtExists: domainSignals.llmsTxtExists,
+      llmsFullTxtExists: domainSignals.llmsFullTxtExists
+    };
     const hasLlms = domainSignals.llmsTxtExists;
     const hasLlmsFull = domainSignals.llmsFullTxtExists;
     const llmsScore = hasLlms && hasLlmsFull ? 6 : hasLlms || hasLlmsFull ? 4 : 0;
@@ -1108,6 +1170,7 @@ function auditGroundingSignals(page) {
   const $ = page.$;
   const text = page.cleanText;
   const factors = [];
+  const { numberCount = 0 } = extractEntities(text);
   const externalLinks = page.externalLinks;
   const extScore = thresholdScore(externalLinks.length, [
     [6, 13],
@@ -1141,7 +1204,8 @@ function auditGroundingSignals(page) {
     )
   );
   const numericCount = countPatternMatches(text, NUMERIC_CLAIM_PATTERNS);
-  const numScore = thresholdScore(numericCount, [
+  const totalNumericSignals = numericCount + numberCount;
+  const numScore = thresholdScore(totalNumericSignals, [
     [9, 13],
     [4, 9],
     [1, 5],
@@ -1152,7 +1216,7 @@ function auditGroundingSignals(page) {
       "Numeric Claims",
       numScore,
       13,
-      `${numericCount} statistical references`
+      `${numericCount} statistical references, ${numberCount} numeric values`
     )
   );
   const attrCount = countPatternMatches(text, ATTRIBUTION_PATTERNS);
@@ -1357,7 +1421,11 @@ function removeBoilerplate($) {
 function normalizeWhitespace(text) {
   return text.replace(/\s+/g, " ").trim();
 }
+var BLOCK_ELEMENTS = "p,div,td,th,li,h1,h2,h3,h4,h5,h6,dt,dd,br,blockquote,section,article";
 function extractCleanText($) {
+  $(BLOCK_ELEMENTS).each((_, el) => {
+    $(el).append(" ");
+  });
   return normalizeWhitespace($("body").text());
 }
 
@@ -1366,7 +1434,9 @@ function extractPage(html, url) {
   const $ = cheerio.load(html);
   const title = $("title").text().trim() || $('meta[property="og:title"]').attr("content")?.trim() || "";
   const metaDescription = $('meta[name="description"]').attr("content")?.trim() || $('meta[property="og:description"]').attr("content")?.trim() || "";
-  const rawText = $("body").text().replace(/\s+/g, " ").trim();
+  const $raw = cheerio.load(html);
+  $raw("script, style, noscript").remove();
+  const rawText = $raw("body").text().replace(/\s+/g, " ").trim();
   const rawByteLength = Buffer.byteLength(html, "utf-8");
   const h1Count = $("h1").length;
   const h2Count = $("h2").length;
@@ -1378,9 +1448,22 @@ function extractPage(html, url) {
   const listItemCount = $("li").length;
   const tableCount = $("table").length;
   const paragraphCount = $("p").length;
+  const GENERIC_ALT_VALUES = /* @__PURE__ */ new Set([
+    "image",
+    "photo",
+    "logo",
+    "icon",
+    "picture",
+    "img",
+    "graphic",
+    "thumbnail"
+  ]);
   let imagesWithAlt = 0;
   $("img").each((_, el) => {
-    if ($(el).attr("alt")) imagesWithAlt++;
+    const alt = $(el).attr("alt")?.trim() ?? "";
+    const words = alt.split(/\s+/).filter((w) => w.length > 0);
+    const isMeaningful = words.length > 1 && alt.length < 200 && !GENERIC_ALT_VALUES.has(alt.toLowerCase());
+    if (isMeaningful) imagesWithAlt++;
   });
   const pageDomain = getDomain(url);
   const externalLinks = [];
@@ -1440,7 +1523,7 @@ var import_zod = require("zod");
 
 // src/modules/analyzer/constants.ts
 var DOMAIN_SIGNAL_TIMEOUT_CAP = 5e3;
-var VERSION = true ? "1.2.7" : "0.0.0";
+var VERSION = true ? "1.3.0" : "0.0.0";
 
 // src/modules/fetcher/schema.ts
 var FetchOptionsSchema = import_zod.z.object({
@@ -1520,9 +1603,19 @@ var RECOMMENDATION_BUILDERS = {
     }
     return `Your robots.txt is blocking ${blocked}. Blocking these crawlers means your content cannot be discovered or cited by AI engines.`;
   },
-  "LLMs.txt Presence": static_(
-    "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site, helping them understand and reference your content more effectively."
-  ),
+  "LLMs.txt Presence": (rawData) => {
+    const llms = rawData.llmsTxt;
+    if (!llms) {
+      return "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site.";
+    }
+    if (llms.llmsTxtExists && !llms.llmsFullTxtExists) {
+      return "You have llms.txt but are missing llms-full.txt. Adding llms-full.txt provides AI systems with a comprehensive version of your site documentation for deeper ingestion.";
+    }
+    if (!llms.llmsTxtExists && llms.llmsFullTxtExists) {
+      return "You have llms-full.txt but are missing llms.txt. Adding llms.txt provides AI systems with a concise structured overview of your site's purpose and key pages.";
+    }
+    return "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site.";
+  },
   "Image Accessibility": (rawData) => {
     const images = rawData.imageAccessibility;
     if (!images || images.imageCount === 0) {

package/dist/index.mjs

@@ -326,7 +326,16 @@ function extractEntities(text) {
     0,
     15
   );
-  return { people, organizations, places, topics };
+  const imperativeVerbCount = doc.verbs().isImperative().length;
+  const numberCount = doc.numbers().length;
+  return {
+    people,
+    organizations,
+    places,
+    topics,
+    imperativeVerbCount,
+    numberCount
+  };
 }
 function computeFleschReadingEase(text) {
   const words = text.split(/\s+/).filter((w) => w.length > 0);
@@ -395,6 +404,7 @@ function auditAnswerability(page) {
   const text = page.cleanText;
   const $ = page.$;
   const factors = [];
+  const { imperativeVerbCount = 0 } = extractEntities(text);
   const defCount = countPatternMatches(text, DEFINITION_PATTERNS);
   const defScore = thresholdScore(defCount, [
     [6, 10],
@@ -439,7 +449,7 @@ function auditAnswerability(page) {
   );
   const stepCount = countPatternMatches(text, STEP_PATTERNS);
   const hasOl = $("ol").length > 0;
-  const stepTotal = stepCount + (hasOl ? 2 : 0);
+  const stepTotal = stepCount + imperativeVerbCount + (hasOl ? 2 : 0);
   const stepScore = thresholdScore(stepTotal, [
     [5, 10],
     [2, 7],
@@ -451,7 +461,7 @@ function auditAnswerability(page) {
       "Step-by-Step Content",
       stepScore,
       10,
-      `${stepCount} step indicators${hasOl ? ", ordered lists found" : ""}`
+      `${stepCount} step indicators, ${imperativeVerbCount} instruction verbs${hasOl ? ", ordered lists found" : ""}`
     )
   );
   const questionMatches = text.match(/[^.!?]*\?/g) || [];
@@ -750,51 +760,99 @@ function auditAuthorityContext(page) {
 }
 
 // src/modules/audits/support/robots.ts
+function parseRobotGroups(robotsTxt) {
+  const groups = [];
+  let current = null;
+  for (const raw of robotsTxt.split("\n")) {
+    const line = raw.split("#")[0].trim();
+    if (!line) {
+      current = null;
+      continue;
+    }
+    const colonAt = line.indexOf(":");
+    if (colonAt === -1) continue;
+    const field = line.slice(0, colonAt).trim().toLowerCase();
+    const value = line.slice(colonAt + 1).trim();
+    if (field === "user-agent") {
+      if (!current) {
+        current = { agents: [], rules: [] };
+        groups.push(current);
+      }
+      current.agents.push(value.toLowerCase());
+    } else if (field === "disallow" || field === "allow") {
+      if (current) {
+        current.rules.push({ type: field, path: value });
+      }
+    }
+  }
+  return groups;
+}
+function matchingRulesForCrawler(groups, crawlerLower) {
+  const specific = [];
+  const wildcard = [];
+  for (const group of groups) {
+    if (group.agents.includes(crawlerLower)) specific.push(...group.rules);
+    else if (group.agents.includes("*")) wildcard.push(...group.rules);
+  }
+  return { specific, wildcard };
+}
+function resolvesPathAsBlocked(rules, path) {
+  let bestMatchLength = -1;
+  let bestMatchIsDisallow = false;
+  for (const rule of rules) {
+    const rulePath = rule.path;
+    if (!rulePath || !path.startsWith(rulePath)) continue;
+    if (rulePath.length > bestMatchLength) {
+      bestMatchLength = rulePath.length;
+      bestMatchIsDisallow = rule.type === "disallow";
+    } else if (rulePath.length === bestMatchLength && rule.type === "allow") {
+      bestMatchIsDisallow = false;
+    }
+  }
+  return bestMatchLength >= 0 && bestMatchIsDisallow;
+}
+function findPartialBlocks(rules) {
+  return rules.filter((r) => r.type === "disallow" && r.path && r.path !== "/").map((r) => r.path);
+}
 function checkCrawlerAccess(robotsTxt) {
   if (!robotsTxt)
     return { allowed: [], blocked: [], unknown: [...AI_CRAWLERS] };
-  const lines = robotsTxt.split("\n").map((l) => l.trim());
+  const groups = parseRobotGroups(robotsTxt);
   const allowed = [];
   const blocked = [];
   const unknown = [];
+  const partiallyBlocked = [];
   for (const crawler of AI_CRAWLERS) {
     const crawlerLower = crawler.toLowerCase();
-    let currentAgent = "";
-    let isBlocked = false;
-    let found = false;
-    for (const line of lines) {
-      const lower = line.toLowerCase();
-      if (lower.startsWith("user-agent:")) {
-        currentAgent = lower.split(":")[1]?.trim() || "";
-      } else if (currentAgent === crawlerLower || currentAgent === "*") {
-        if (lower.startsWith("disallow:")) {
-          const path = lower.split(":")[1]?.trim();
-          if (path === "/") {
-            if (currentAgent === crawlerLower) {
-              isBlocked = true;
-              found = true;
-            } else if (currentAgent === "*" && !found) {
-              isBlocked = true;
-            }
-          }
-        } else if (lower.startsWith("allow:")) {
-          if (currentAgent === crawlerLower) {
-            found = true;
-            isBlocked = false;
-          }
-        }
-      }
+    const { specific, wildcard } = matchingRulesForCrawler(
+      groups,
+      crawlerLower
+    );
+    const applicableRules = specific.length > 0 ? specific : wildcard;
+    if (applicableRules.length === 0) {
+      unknown.push(crawler);
+      continue;
     }
-    if (found) {
-      if (isBlocked) blocked.push(crawler);
-      else allowed.push(crawler);
-    } else if (isBlocked) {
+    const isSiteBlocked = resolvesPathAsBlocked(applicableRules, "/");
+    if (isSiteBlocked) {
       blocked.push(crawler);
     } else {
-      unknown.push(crawler);
+      allowed.push(crawler);
+      const pathBlocks = findPartialBlocks(applicableRules);
+      for (const path of pathBlocks) {
+        const entry = `${crawler}: ${path}`;
+        if (!partiallyBlocked.includes(entry)) {
+          partiallyBlocked.push(entry);
+        }
+      }
     }
   }
-  return { allowed, blocked, unknown };
+  return {
+    allowed,
+    blocked,
+    unknown,
+    ...partiallyBlocked.length > 0 && { partiallyBlocked }
+  };
 }
 
 // src/modules/audits/categories/content-extractability.ts
@@ -811,7 +869,7 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
     )
   );
   const extractRatio = page.stats.rawByteLength > 0 ? page.stats.cleanTextLength / page.stats.rawByteLength : 0;
-  const extractScore = extractRatio >= 0.05 && extractRatio <= 0.15 ? 12 : extractRatio >= 0.01 ? 8 : extractRatio > 0.15 ? 10 : 2;
+  const extractScore = extractRatio >= 0.05 && extractRatio <= 0.15 ? 12 : extractRatio > 0.15 ? 10 : extractRatio >= 0.01 ? 8 : 2;
   factors.push(
     makeFactor(
       "Text Extraction Quality",
@@ -836,7 +894,7 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
     )
   );
   const wc = page.stats.wordCount;
-  const wcScore = wc >= 300 && wc <= 3e3 ? 12 : wc >= 100 ? 8 : wc > 3e3 ? 10 : 2;
+  const wcScore = wc >= 300 && wc <= 3e3 ? 12 : wc > 3e3 ? 10 : wc >= 100 ? 8 : 2;
   factors.push(makeFactor("Word Count Adequacy", wcScore, 12, `${wc} words`));
   if (domainSignals) {
     const access2 = checkCrawlerAccess(domainSignals.robotsTxt);
@@ -851,6 +909,10 @@ function auditContentExtractability(page, fetchResult, domainSignals) {
       )
     );
     rawData.crawlerAccess = access2;
+    rawData.llmsTxt = {
+      llmsTxtExists: domainSignals.llmsTxtExists,
+      llmsFullTxtExists: domainSignals.llmsFullTxtExists
+    };
     const hasLlms = domainSignals.llmsTxtExists;
     const hasLlmsFull = domainSignals.llmsFullTxtExists;
     const llmsScore = hasLlms && hasLlmsFull ? 6 : hasLlms || hasLlmsFull ? 4 : 0;
@@ -1070,6 +1132,7 @@ function auditGroundingSignals(page) {
   const $ = page.$;
   const text = page.cleanText;
   const factors = [];
+  const { numberCount = 0 } = extractEntities(text);
   const externalLinks = page.externalLinks;
   const extScore = thresholdScore(externalLinks.length, [
     [6, 13],
@@ -1103,7 +1166,8 @@ function auditGroundingSignals(page) {
     )
   );
   const numericCount = countPatternMatches(text, NUMERIC_CLAIM_PATTERNS);
-  const numScore = thresholdScore(numericCount, [
+  const totalNumericSignals = numericCount + numberCount;
+  const numScore = thresholdScore(totalNumericSignals, [
     [9, 13],
     [4, 9],
     [1, 5],
@@ -1114,7 +1178,7 @@ function auditGroundingSignals(page) {
       "Numeric Claims",
       numScore,
       13,
-      `${numericCount} statistical references`
+      `${numericCount} statistical references, ${numberCount} numeric values`
     )
   );
   const attrCount = countPatternMatches(text, ATTRIBUTION_PATTERNS);
@@ -1319,7 +1383,11 @@ function removeBoilerplate($) {
 function normalizeWhitespace(text) {
   return text.replace(/\s+/g, " ").trim();
 }
+var BLOCK_ELEMENTS = "p,div,td,th,li,h1,h2,h3,h4,h5,h6,dt,dd,br,blockquote,section,article";
 function extractCleanText($) {
+  $(BLOCK_ELEMENTS).each((_, el) => {
+    $(el).append(" ");
+  });
   return normalizeWhitespace($("body").text());
 }
 
@@ -1328,7 +1396,9 @@ function extractPage(html, url) {
   const $ = cheerio.load(html);
   const title = $("title").text().trim() || $('meta[property="og:title"]').attr("content")?.trim() || "";
   const metaDescription = $('meta[name="description"]').attr("content")?.trim() || $('meta[property="og:description"]').attr("content")?.trim() || "";
-  const rawText = $("body").text().replace(/\s+/g, " ").trim();
+  const $raw = cheerio.load(html);
+  $raw("script, style, noscript").remove();
+  const rawText = $raw("body").text().replace(/\s+/g, " ").trim();
   const rawByteLength = Buffer.byteLength(html, "utf-8");
   const h1Count = $("h1").length;
   const h2Count = $("h2").length;
@@ -1340,9 +1410,22 @@ function extractPage(html, url) {
   const listItemCount = $("li").length;
   const tableCount = $("table").length;
   const paragraphCount = $("p").length;
+  const GENERIC_ALT_VALUES = /* @__PURE__ */ new Set([
+    "image",
+    "photo",
+    "logo",
+    "icon",
+    "picture",
+    "img",
+    "graphic",
+    "thumbnail"
+  ]);
   let imagesWithAlt = 0;
   $("img").each((_, el) => {
-    if ($(el).attr("alt")) imagesWithAlt++;
+    const alt = $(el).attr("alt")?.trim() ?? "";
+    const words = alt.split(/\s+/).filter((w) => w.length > 0);
+    const isMeaningful = words.length > 1 && alt.length < 200 && !GENERIC_ALT_VALUES.has(alt.toLowerCase());
+    if (isMeaningful) imagesWithAlt++;
   });
   const pageDomain = getDomain(url);
   const externalLinks = [];
@@ -1402,7 +1485,7 @@ import { z } from "zod";
 
 // src/modules/analyzer/constants.ts
 var DOMAIN_SIGNAL_TIMEOUT_CAP = 5e3;
-var VERSION = true ? "1.2.7" : "0.0.0";
+var VERSION = true ? "1.3.0" : "0.0.0";
 
 // src/modules/fetcher/schema.ts
 var FetchOptionsSchema = z.object({
@@ -1482,9 +1565,19 @@ var RECOMMENDATION_BUILDERS = {
     }
     return `Your robots.txt is blocking ${blocked}. Blocking these crawlers means your content cannot be discovered or cited by AI engines.`;
   },
-  "LLMs.txt Presence": static_(
-    "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site, helping them understand and reference your content more effectively."
-  ),
+  "LLMs.txt Presence": (rawData) => {
+    const llms = rawData.llmsTxt;
+    if (!llms) {
+      return "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site.";
+    }
+    if (llms.llmsTxtExists && !llms.llmsFullTxtExists) {
+      return "You have llms.txt but are missing llms-full.txt. Adding llms-full.txt provides AI systems with a comprehensive version of your site documentation for deeper ingestion.";
+    }
+    if (!llms.llmsTxtExists && llms.llmsFullTxtExists) {
+      return "You have llms-full.txt but are missing llms.txt. Adding llms.txt provides AI systems with a concise structured overview of your site's purpose and key pages.";
+    }
+    return "Consider adding llms.txt and llms-full.txt files at your domain root. This emerging standard provides AI systems with a structured overview of your site.";
+  },
   "Image Accessibility": (rawData) => {
     const images = rawData.imageAccessibility;
     if (!images || images.imageCount === 0) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "aiseo-audit",
-  "version": "1.2.7",
+  "version": "1.3.0",
   "description": "Lighthouse for AI SEO. Audit any webpage for AI search readiness. 7 categories, 30+ factors, research-backed scoring. Deterministic, engine-agnostic, zero API keys.",
   "main": "./dist/index.js",
   "module": "./dist/index.mjs",