diff --git a/src/skill_seekers/cli/arguments/common.py b/src/skill_seekers/cli/arguments/common.py
index 7fbdb36..309f993 100644
--- a/src/skill_seekers/cli/arguments/common.py
+++ b/src/skill_seekers/cli/arguments/common.py
@@ -101,8 +101,8 @@ RAG_ARGUMENTS: dict[str, dict[str, Any]] = {
             "help": "Enable semantic chunking for RAG pipelines",
         },
     },
-    "chunk_size": {
-        "flags": ("--chunk-size",),
+    "chunk_tokens": {
+        "flags": ("--chunk-tokens",),
         "kwargs": {
             "type": int,
             "default": 512,
@@ -110,8 +110,8 @@ RAG_ARGUMENTS: dict[str, dict[str, Any]] = {
             "help": "Chunk size in tokens for RAG (default: 512)",
         },
     },
-    "chunk_overlap": {
-        "flags": ("--chunk-overlap",),
+    "chunk_overlap_tokens": {
+        "flags": ("--chunk-overlap-tokens",),
         "kwargs": {
             "type": int,
             "default": 50,
@@ -183,7 +183,7 @@ def add_rag_arguments(parser: argparse.ArgumentParser) -> None:
     Example:
         >>> parser = argparse.ArgumentParser()
         >>> add_rag_arguments(parser)
-        >>> # Now parser has --chunk-for-rag, --chunk-size, --chunk-overlap
+        >>> # Now parser has --chunk-for-rag, --chunk-tokens, --chunk-overlap-tokens
     """
     for arg_name, arg_def in RAG_ARGUMENTS.items():
         flags = arg_def["flags"]
@@ -195,7 +195,7 @@ def get_rag_argument_names() -> set:
     """Get the set of RAG argument destination names.
 
     Returns:
-        Set of argument dest names (e.g., {'chunk_for_rag', 'chunk_size', 'chunk_overlap'})
+        Set of argument dest names (e.g., {'chunk_for_rag', 'chunk_tokens', 'chunk_overlap_tokens'})
     """
     return set(RAG_ARGUMENTS.keys())
 
diff --git a/src/skill_seekers/cli/arguments/package.py b/src/skill_seekers/cli/arguments/package.py
index d51b3be..6b1387e 100644
--- a/src/skill_seekers/cli/arguments/package.py
+++ b/src/skill_seekers/cli/arguments/package.py
@@ -70,8 +70,8 @@ PACKAGE_ARGUMENTS: dict[str, dict[str, Any]] = {
             "help": "Use streaming ingestion for large docs (memory-efficient)",
         },
     },
-    "streaming_chunk_size": {
-        "flags": ("--streaming-chunk-size",),
+    "streaming_chunk_chars": {
+        "flags": ("--streaming-chunk-chars",),
         "kwargs": {
             "type": int,
             "default": 4000,
@@ -79,8 +79,8 @@ PACKAGE_ARGUMENTS: dict[str, dict[str, Any]] = {
             "metavar": "N",
         },
     },
-    "streaming_overlap": {
-        "flags": ("--streaming-overlap",),
+    "streaming_overlap_chars": {
+        "flags": ("--streaming-overlap-chars",),
         "kwargs": {
             "type": int,
             "default": 200,
@@ -98,8 +98,8 @@ PACKAGE_ARGUMENTS: dict[str, dict[str, Any]] = {
         },
     },
     # RAG chunking options
-    "chunk": {
-        "flags": ("--chunk",),
+    "chunk_for_rag": {
+        "flags": ("--chunk-for-rag",),
         "kwargs": {
             "action": "store_true",
             "help": "Enable intelligent chunking for RAG platforms (auto-enabled for RAG adaptors)",
diff --git a/src/skill_seekers/cli/create_command.py b/src/skill_seekers/cli/create_command.py
index 0dd69f4..8ef8475 100644
--- a/src/skill_seekers/cli/create_command.py
+++ b/src/skill_seekers/cli/create_command.py
@@ -106,8 +106,8 @@ class CreateCommand:
         # Check against common defaults
         defaults = {
             "max_issues": 100,
-            "chunk_size": 512,
-            "chunk_overlap": 50,
+            "chunk_tokens": 512,
+            "chunk_overlap_tokens": 50,
             "output": None,
         }
 
@@ -158,10 +158,10 @@ class CreateCommand:
         # RAG arguments (web scraper only)
         if getattr(self.args, "chunk_for_rag", False):
             argv.append("--chunk-for-rag")
-        if getattr(self.args, "chunk_size", None) and self.args.chunk_size != 512:
-            argv.extend(["--chunk-size", str(self.args.chunk_size)])
-        if getattr(self.args, "chunk_overlap", None) and self.args.chunk_overlap != 50:
-            argv.extend(["--chunk-overlap", str(self.args.chunk_overlap)])
+        if getattr(self.args, "chunk_tokens", None) and self.args.chunk_tokens != 512:
+            argv.extend(["--chunk-tokens", str(self.args.chunk_tokens)])
+        if getattr(self.args, "chunk_overlap_tokens", None) and self.args.chunk_overlap_tokens != 50:
+            argv.extend(["--chunk-overlap-tokens", str(self.args.chunk_overlap_tokens)])
 
         # Advanced web-specific arguments
         if getattr(self.args, "no_preserve_code_blocks", False):
diff --git a/src/skill_seekers/cli/doc_scraper.py b/src/skill_seekers/cli/doc_scraper.py
index 2595c30..72c06df 100755
--- a/src/skill_seekers/cli/doc_scraper.py
+++ b/src/skill_seekers/cli/doc_scraper.py
@@ -2227,8 +2227,8 @@ def execute_scraping_and_building(
         from skill_seekers.cli.rag_chunker import RAGChunker
 
         chunker = RAGChunker(
-            chunk_size=args.chunk_size,
-            chunk_overlap=args.chunk_overlap,
+            chunk_size=args.chunk_tokens,
+            chunk_overlap=args.chunk_overlap_tokens,
             preserve_code_blocks=not args.no_preserve_code_blocks,
             preserve_paragraphs=not args.no_preserve_paragraphs,
         )
diff --git a/src/skill_seekers/cli/package_skill.py b/src/skill_seekers/cli/package_skill.py
index 00ee167..c8ebe4a 100644
--- a/src/skill_seekers/cli/package_skill.py
+++ b/src/skill_seekers/cli/package_skill.py
@@ -221,10 +221,10 @@ Examples:
         skip_quality_check=args.skip_quality_check,
         target=args.target,
         streaming=args.streaming,
-        chunk_size=args.streaming_chunk_size,
-        chunk_overlap=args.streaming_overlap,
+        chunk_size=args.streaming_chunk_chars,
+        chunk_overlap=args.streaming_overlap_chars,
         batch_size=args.batch_size,
-        enable_chunking=args.chunk,
+        enable_chunking=args.chunk_for_rag,
         chunk_max_tokens=args.chunk_tokens,
         preserve_code_blocks=not args.no_preserve_code,
     )
diff --git a/src/skill_seekers/cli/parsers/stream_parser.py b/src/skill_seekers/cli/parsers/stream_parser.py
index 6ee513a..52823e6 100644
--- a/src/skill_seekers/cli/parsers/stream_parser.py
+++ b/src/skill_seekers/cli/parsers/stream_parser.py
@@ -21,5 +21,5 @@ class StreamParser(SubcommandParser):
     def add_arguments(self, parser):
         """Add stream-specific arguments."""
         parser.add_argument("input_file", help="Large file to stream")
-        parser.add_argument("--chunk-size", type=int, default=1024, help="Chunk size in KB")
+        parser.add_argument("--streaming-chunk-chars", type=int, default=4000, help="Maximum characters per chunk (default: 4000)")
         parser.add_argument("--output", help="Output directory")
diff --git a/src/skill_seekers/cli/pdf_extractor_poc.py b/src/skill_seekers/cli/pdf_extractor_poc.py
index 58c62a1..b39a82e 100755
--- a/src/skill_seekers/cli/pdf_extractor_poc.py
+++ b/src/skill_seekers/cli/pdf_extractor_poc.py
@@ -44,7 +44,7 @@ Usage:
 
 Example:
     python3 pdf_extractor_poc.py docs/manual.pdf -o output.json -v \
-        --chunk-size 15 --min-quality 6.0 --extract-images \
+        --pdf-pages-per-chunk 15 --min-quality 6.0 --extract-images \
         --extract-tables --parallel
 """
 
@@ -1079,7 +1079,7 @@ Examples:
     parser.add_argument("-v", "--verbose", action="store_true", help="Verbose output")
     parser.add_argument("--pretty", action="store_true", help="Pretty-print JSON output")
     parser.add_argument(
-        "--chunk-size", type=int, default=10, help="Pages per chunk (0 = no chunking, default: 10)"
+        "--pdf-pages-per-chunk", type=int, default=10, help="Pages per chunk (0 = no chunking, default: 10)"
     )
     parser.add_argument(
         "--no-merge", action="store_true", help="Disable merging code blocks across pages"
@@ -1138,7 +1138,7 @@ Examples:
     extractor = PDFExtractor(
         args.pdf_file,
         verbose=args.verbose,
-        chunk_size=args.chunk_size,
+        chunk_size=args.pdf_pages_per_chunk,
         min_quality=args.min_quality,
         extract_images=args.extract_images,
         image_dir=args.image_dir,
diff --git a/src/skill_seekers/cli/rag_chunker.py b/src/skill_seekers/cli/rag_chunker.py
index 23f8340..dcbf782 100644
--- a/src/skill_seekers/cli/rag_chunker.py
+++ b/src/skill_seekers/cli/rag_chunker.py
@@ -383,8 +383,8 @@ def main():
     )
     parser.add_argument("skill_dir", type=Path, help="Path to skill directory")
     parser.add_argument("--output", "-o", type=Path, help="Output JSON file")
-    parser.add_argument("--chunk-size", type=int, default=512, help="Target chunk size in tokens")
-    parser.add_argument("--chunk-overlap", type=int, default=50, help="Overlap size in tokens")
+    parser.add_argument("--chunk-tokens", type=int, default=512, help="Target chunk size in tokens")
+    parser.add_argument("--chunk-overlap-tokens", type=int, default=50, help="Overlap size in tokens")
     parser.add_argument("--no-code-blocks", action="store_true", help="Don't preserve code blocks")
     parser.add_argument("--no-paragraphs", action="store_true", help="Don't preserve paragraphs")
 
@@ -392,8 +392,8 @@ def main():
 
     # Create chunker
     chunker = RAGChunker(
-        chunk_size=args.chunk_size,
-        chunk_overlap=args.chunk_overlap,
+        chunk_size=args.chunk_tokens,
+        chunk_overlap=args.chunk_overlap_tokens,
         preserve_code_blocks=not args.no_code_blocks,
         preserve_paragraphs=not args.no_paragraphs,
     )
diff --git a/src/skill_seekers/cli/streaming_ingest.py b/src/skill_seekers/cli/streaming_ingest.py
index 9720d35..ab81800 100644
--- a/src/skill_seekers/cli/streaming_ingest.py
+++ b/src/skill_seekers/cli/streaming_ingest.py
@@ -380,9 +380,9 @@ def main():
 
     parser = argparse.ArgumentParser(description="Stream and chunk skill documents")
     parser.add_argument("input", help="Input file or directory path")
-    parser.add_argument("--chunk-size", type=int, default=4000, help="Chunk size in characters")
+    parser.add_argument("--streaming-chunk-chars", type=int, default=4000, help="Chunk size in characters")
     parser.add_argument(
-        "--chunk-overlap", type=int, default=200, help="Chunk overlap in characters"
+        "--streaming-overlap-chars", type=int, default=200, help="Chunk overlap in characters"
     )
     parser.add_argument("--batch-size", type=int, default=100, help="Batch size for processing")
     parser.add_argument("--checkpoint", help="Checkpoint file path")
@@ -390,7 +390,7 @@ def main():
 
     # Initialize ingester
     ingester = StreamingIngester(
-        chunk_size=args.chunk_size, chunk_overlap=args.chunk_overlap, batch_size=args.batch_size
+        chunk_size=args.streaming_chunk_chars, chunk_overlap=args.streaming_overlap_chars, batch_size=args.batch_size
     )
 
     # Progress callback
diff --git a/tests/test_chunking_integration.py b/tests/test_chunking_integration.py
index 9a19128..42a1c1b 100644
--- a/tests/test_chunking_integration.py
+++ b/tests/test_chunking_integration.py
@@ -291,7 +291,7 @@ class TestChunkingCLIIntegration:
     """Test chunking via CLI arguments."""
 
     def test_chunk_flag(self, tmp_path):
-        """Test --chunk flag enables chunking."""
+        """Test --chunk-for-rag flag enables chunking."""
         from skill_seekers.cli.package_skill import package_skill
 
         skill_dir = create_test_skill(tmp_path, large_doc=True)
@@ -301,7 +301,7 @@ class TestChunkingCLIIntegration:
             open_folder_after=False,
             skip_quality_check=True,
             target="langchain",
-            enable_chunking=True,  # --chunk flag
+            enable_chunking=True,  # --chunk-for-rag flag
             chunk_max_tokens=512,
             preserve_code_blocks=True,
         )
diff --git a/tests/test_cli_refactor_e2e.py b/tests/test_cli_refactor_e2e.py
index e2d937b..082a8f0 100644
--- a/tests/test_cli_refactor_e2e.py
+++ b/tests/test_cli_refactor_e2e.py
@@ -32,8 +32,8 @@ class TestParserSync:
             ["skill-seekers", "scrape", "--help"], capture_output=True, text=True
         )
         assert "--chunk-for-rag" in result.stdout, "Help should show --chunk-for-rag flag"
-        assert "--chunk-size" in result.stdout, "Help should show --chunk-size flag"
-        assert "--chunk-overlap" in result.stdout, "Help should show --chunk-overlap flag"
+        assert "--chunk-tokens" in result.stdout, "Help should show --chunk-tokens flag"
+        assert "--chunk-overlap-tokens" in result.stdout, "Help should show --chunk-overlap-tokens flag"
 
     def test_scrape_verbose_flag_works(self):
         """Test that --verbose flag (previously missing) now works."""
diff --git a/tests/test_create_arguments.py b/tests/test_create_arguments.py
index 348d9d1..b297721 100644
--- a/tests/test_create_arguments.py
+++ b/tests/test_create_arguments.py
@@ -40,8 +40,8 @@ class TestUniversalArguments:
             "verbose",
             "quiet",
             "chunk_for_rag",
-            "chunk_size",
-            "chunk_overlap",  # Phase 2: RAG args from common.py
+            "chunk_tokens",
+            "chunk_overlap_tokens",  # Phase 2: RAG args from common.py
             "preset",
             "config",
             # Phase 2: Workflow arguments (universal workflow support)