fix: Complete fix for Issue #219 - All three problems resolved

**Problem #1: Large File Encoding Error** ✅ FIXED
- Add large file download support via download_url
- Detect encoding='none' for files >1MB
- Download via GitHub raw URL instead of API
- Handles ccxt/ccxt's 1.4MB CHANGELOG.md successfully

**Problem #2: Missing CLI Enhancement Flags** ✅ FIXED
- Add --enhance, --enhance-local, --api-key to main.py github_parser
- Add flag forwarding in CLI dispatcher
- Fixes 'unrecognized arguments' error
- Users can now use: skill-seekers github --repo owner/repo --enhance-local

**Problem #3: Custom API Endpoint Support** ✅ FIXED
- Support ANTHROPIC_BASE_URL environment variable
- Support ANTHROPIC_AUTH_TOKEN (alternative to ANTHROPIC_API_KEY)
- Fix ThinkingBlock.text error with newer Anthropic SDK
- Find TextBlock in response content array (handles thinking blocks)

**Changes**:
- src/skill_seekers/cli/enhance_skill.py:
  - Support custom base_url parameter
  - Support both ANTHROPIC_API_KEY and ANTHROPIC_AUTH_TOKEN
  - Iterate through content blocks to find text (handles ThinkingBlock)

- src/skill_seekers/cli/main.py:
  - Add --enhance, --enhance-local, --api-key to github_parser
  - Forward flags to github_scraper.py in dispatcher

- src/skill_seekers/cli/github_scraper.py:
  - Add large file detection (encoding=None/"none")
  - Download via download_url with requests
  - Log file size and download progress

- tests/test_github_scraper.py:
  - Add test_get_file_content_large_file
  - Add test_extract_changelog_large_file
  - All 31 tests passing ✅

**Credits**:
- Thanks to @XGCoder for detailed bug report
- Thanks to @gorquan for local fixes and guidance

Fixes #219

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

src/skill_seekers/cli/enhance_skill.py

@@ -41,15 +41,24 @@ class SkillEnhancer:
         self.references_dir = self.skill_dir / "references"
         self.skill_md_path = self.skill_dir / "SKILL.md"
 
-        # Get API key
+        # Get API key - support both ANTHROPIC_API_KEY and ANTHROPIC_AUTH_TOKEN
-        self.api_key = api_key or os.environ.get('ANTHROPIC_API_KEY')
+        self.api_key = (api_key or
+                       os.environ.get('ANTHROPIC_API_KEY') or
+                       os.environ.get('ANTHROPIC_AUTH_TOKEN'))
         if not self.api_key:
             raise ValueError(
-                "No API key provided. Set ANTHROPIC_API_KEY environment variable "
+                "No API key provided. Set ANTHROPIC_API_KEY or ANTHROPIC_AUTH_TOKEN "
-                "or use --api-key argument"
+                "environment variable or use --api-key argument"
             )
 
-        self.client = anthropic.Anthropic(api_key=self.api_key)
+        # Support custom base URL for alternative API endpoints
+        base_url = os.environ.get('ANTHROPIC_BASE_URL')
+        client_kwargs = {'api_key': self.api_key}
+        if base_url:
+            client_kwargs['base_url'] = base_url
+            print(f"ℹ️  Using custom API base URL: {base_url}")
+
+        self.client = anthropic.Anthropic(**client_kwargs)
 
     def read_current_skill_md(self):
         """Read existing SKILL.md"""
@@ -77,7 +86,18 @@ class SkillEnhancer:
                 }]
             )
 
-            enhanced_content = message.content[0].text
+            # Handle response content - newer SDK versions may include ThinkingBlock
+            # Find the TextBlock containing the actual response
+            enhanced_content = None
+            for block in message.content:
+                if hasattr(block, 'text'):
+                    enhanced_content = block.text
+                    break
+
+            if not enhanced_content:
+                print("❌ Error: No text content found in API response")
+                return None
+
             return enhanced_content
 
         except Exception as e:

src/skill_seekers/cli/github_scraper.py

@@ -355,6 +355,26 @@ class GitHubScraper:
                     logger.warning(f"Symlink {file_path} has no target")
                     return None
 
+            # Handle large files (encoding="none") - download via URL
+            # GitHub API doesn't base64-encode files >1MB
+            if hasattr(content, 'encoding') and content.encoding in [None, "none"]:
+                download_url = getattr(content, 'download_url', None)
+                file_size = getattr(content, 'size', 0)
+
+                if download_url:
+                    logger.info(f"File {file_path} is large ({file_size:,} bytes), downloading via URL...")
+                    try:
+                        import requests
+                        response = requests.get(download_url, timeout=30)
+                        response.raise_for_status()
+                        return response.text
+                    except Exception as e:
+                        logger.warning(f"Failed to download {file_path} from {download_url}: {e}")
+                        return None
+                else:
+                    logger.warning(f"File {file_path} has no download URL (encoding={content.encoding})")
+                    return None
+
             # Handle regular files - decode content
             try:
                 if isinstance(content.decoded_content, bytes):

src/skill_seekers/cli/main.py

@@ -99,6 +99,9 @@ For more information: https://github.com/yusufkaraaslan/Skill_Seekers
     github_parser.add_argument("--repo", help="GitHub repo (owner/repo)")
     github_parser.add_argument("--name", help="Skill name")
     github_parser.add_argument("--description", help="Skill description")
+    github_parser.add_argument("--enhance", action="store_true", help="AI enhancement (API)")
+    github_parser.add_argument("--enhance-local", action="store_true", help="AI enhancement (local)")
+    github_parser.add_argument("--api-key", type=str, help="Anthropic API key for --enhance")
 
     # === pdf subcommand ===
     pdf_parser = subparsers.add_parser(
@@ -274,6 +277,12 @@ def main(argv: Optional[List[str]] = None) -> int:
                 sys.argv.extend(["--name", args.name])
             if args.description:
                 sys.argv.extend(["--description", args.description])
+            if args.enhance:
+                sys.argv.append("--enhance")
+            if args.enhance_local:
+                sys.argv.append("--enhance-local")
+            if args.api_key:
+                sys.argv.extend(["--api-key", args.api_key])
             return github_main() or 0
 
         elif args.command == "pdf":

tests/test_github_scraper.py

@@ -892,6 +892,75 @@ class TestSymlinkHandling(unittest.TestCase):
             # Should not crash (will try latin-1 fallback)
             self.assertIsNotNone(result)
 
+    def test_get_file_content_large_file(self):
+        """Test _get_file_content handles large files with encoding='none' (Issue #219)"""
+        config = {
+            'repo': 'ccxt/ccxt',
+            'name': 'ccxt',
+            'github_token': None
+        }
+
+        # Create mock large file (encoding="none")
+        mock_content = Mock()
+        mock_content.type = 'file'
+        mock_content.encoding = 'none'  # Large files have encoding="none"
+        mock_content.size = 1388271  # 1.4MB CHANGELOG
+        mock_content.download_url = 'https://raw.githubusercontent.com/ccxt/ccxt/master/CHANGELOG.md'
+
+        with patch('skill_seekers.cli.github_scraper.Github'):
+            scraper = self.GitHubScraper(config)
+            scraper.repo = Mock()
+            scraper.repo.get_contents.return_value = mock_content
+
+            # Mock requests.get
+            with patch('requests.get') as mock_requests:
+                mock_response = Mock()
+                mock_response.text = '# Changelog\n\n## v1.0.0\n- Initial release'
+                mock_response.raise_for_status = Mock()
+                mock_requests.return_value = mock_response
+
+                result = scraper._get_file_content('CHANGELOG.md')
+
+                # Should download via download_url
+                self.assertEqual(result, '# Changelog\n\n## v1.0.0\n- Initial release')
+                mock_requests.assert_called_once_with(
+                    'https://raw.githubusercontent.com/ccxt/ccxt/master/CHANGELOG.md',
+                    timeout=30
+                )
+
+    def test_extract_changelog_large_file(self):
+        """Test CHANGELOG extraction with large file (Integration test for Issue #219)"""
+        config = {
+            'repo': 'ccxt/ccxt',
+            'name': 'ccxt',
+            'github_token': None
+        }
+
+        # Create mock large CHANGELOG
+        mock_content = Mock()
+        mock_content.type = 'file'
+        mock_content.encoding = 'none'
+        mock_content.size = 1388271
+        mock_content.download_url = 'https://raw.githubusercontent.com/ccxt/ccxt/master/CHANGELOG.md'
+
+        with patch('skill_seekers.cli.github_scraper.Github'):
+            scraper = self.GitHubScraper(config)
+            scraper.repo = Mock()
+            scraper.repo.get_contents.return_value = mock_content
+
+            # Mock requests.get
+            with patch('requests.get') as mock_requests:
+                mock_response = Mock()
+                mock_response.text = '# CCXT Changelog\n\n## v4.0.0\n- Major update'
+                mock_response.raise_for_status = Mock()
+                mock_requests.return_value = mock_response
+
+                scraper._extract_changelog()
+
+                # Should successfully extract CHANGELOG content
+                self.assertIn('changelog', scraper.extracted_data)
+                self.assertIn('Major update', scraper.extracted_data['changelog'])
+
 
 class TestErrorHandling(unittest.TestCase):
     """Test error handling and edge cases"""