diff --git a/cli/doc_scraper.py b/cli/doc_scraper.py
index 4702bec..fa4c059 100755
--- a/cli/doc_scraper.py
+++ b/cli/doc_scraper.py
@@ -257,15 +257,16 @@ class DocToSkillConverter:
                 paragraphs.append(text)
         
         page['content'] = '\n\n'.join(paragraphs)
-        
-        # Extract links
-        for link in main.find_all('a', href=True):
+
+        # Extract links from entire page (not just main content)
+        # This allows discovery of navigation links outside the main content area
+        for link in soup.find_all('a', href=True):
             href = urljoin(url, link['href'])
             # Strip anchor fragments to avoid treating #anchors as separate pages
             href = href.split('#')[0]
             if self.is_valid_url(href) and href not in page['links']:
                 page['links'].append(href)
-        
+
         return page
 
     def _extract_language_from_classes(self, classes):
@@ -1641,11 +1642,14 @@ def execute_scraping_and_building(config: Dict[str, Any], args: argparse.Namespa
     # Check for existing data
     exists, page_count = check_existing_data(config['name'])
 
-    if exists and not args.skip_scrape:
+    if exists and not args.skip_scrape and not args.fresh:
         logger.info("\n✓ Found existing data: %d pages", page_count)
         response = input("Use existing data? (y/n): ").strip().lower()
         if response == 'y':
             args.skip_scrape = True
+    elif exists and args.fresh:
+        logger.info("\n✓ Found existing data: %d pages", page_count)
+        logger.info("  --fresh flag set, will re-scrape from scratch")
 
     # Create converter
     converter = DocToSkillConverter(config, resume=args.resume)
diff --git a/skill_seeker_mcp/server.py b/skill_seeker_mcp/server.py
index a6f5c77..4307a2f 100644
--- a/skill_seeker_mcp/server.py
+++ b/skill_seeker_mcp/server.py
@@ -603,6 +603,10 @@ async def scrape_docs_tool(args: dict) -> list[TextContent]:
     if is_unified and merge_mode:
         cmd.extend(["--merge-mode", merge_mode])
 
+    # Add --fresh to avoid user input prompts when existing data found
+    if not skip_scrape:
+        cmd.append("--fresh")
+
     if enhance_local:
         cmd.append("--enhance-local")
     if skip_scrape: