fix: resolve 18 bugs and code quality issues across adaptors, CLI, and chunking pipeline

Bug fixes:
- Fix --var flag silently dropped in create routing (args.workflow_var → args.var)
- Fix double _score_code_quality() call in word scraper
- Add .docx file extension validation in WordToSkillConverter
- Fix weaviate ImportError masked by generic Exception handler
- Fix RAG chunking crash using non-existent converter.output_dir

Chunking pipeline improvements:
- Wire --chunk-overlap-tokens through entire package pipeline
  (package_skill → adaptor.package → format_skill_md → _maybe_chunk_content → RAGChunker)
- Add auto-scaling overlap: max(50, chunk_tokens//10) when chunk size is non-default
- Rename --no-preserve-code to --no-preserve-code-blocks (backward-compat alias kept)
- Replace hardcoded 512/50 chunk defaults with DEFAULT_CHUNK_TOKENS/DEFAULT_CHUNK_OVERLAP_TOKENS
  constants across all 12 concrete adaptors, rag_chunker, base, and package_skill

Code quality:
- Extract shared _generate_openai_embeddings() and _generate_st_embeddings() to SkillAdaptor
  base class, removing ~150 lines of duplication from chroma/weaviate/pinecone
- Add Pinecone adaptor with full upload support (pinecone_adaptor.py)

Tests (14 new):
- chunk_overlap_tokens parameter wiring, auto-scaling overlap, preserve_code_blocks flag
- .docx/.doc/no-extension file validation, --var flag routing E2E
- Embedding method inheritance verification, backward-compatible flag aliases

Docs:
- Update CHANGELOG, CLI_REFERENCE, API_REFERENCE, packaging guide (EN+ZH)
- Update README test count badge (1880+ → 2283+)

All 2283 tests passing, 8 skipped, 0 failures.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/skill_seekers/cli/create_command.py

@@ -13,6 +13,7 @@ from skill_seekers.cli.arguments.create import (
     get_compatible_arguments,
     get_universal_argument_names,
 )
+from skill_seekers.cli.arguments.common import DEFAULT_CHUNK_TOKENS, DEFAULT_CHUNK_OVERLAP_TOKENS
 
 logger = logging.getLogger(__name__)
 
@@ -106,8 +107,8 @@ class CreateCommand:
         # Check against common defaults
         defaults = {
             "max_issues": 100,
-            "chunk_tokens": 512,
-            "chunk_overlap_tokens": 50,
+            "chunk_tokens": DEFAULT_CHUNK_TOKENS,
+            "chunk_overlap_tokens": DEFAULT_CHUNK_OVERLAP_TOKENS,
             "output": None,
         }
 
@@ -160,11 +161,11 @@ 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_tokens", None) and self.args.chunk_tokens != 512:
+        if getattr(self.args, "chunk_tokens", None) and self.args.chunk_tokens != DEFAULT_CHUNK_TOKENS:
             argv.extend(["--chunk-tokens", str(self.args.chunk_tokens)])
         if (
             getattr(self.args, "chunk_overlap_tokens", None)
-            and self.args.chunk_overlap_tokens != 50
+            and self.args.chunk_overlap_tokens != DEFAULT_CHUNK_OVERLAP_TOKENS
         ):
             argv.extend(["--chunk-overlap-tokens", str(self.args.chunk_overlap_tokens)])
 
@@ -428,6 +429,10 @@ class CreateCommand:
         if self.args.quiet:
             argv.append("--quiet")
 
+        # Documentation version metadata
+        if getattr(self.args, "doc_version", ""):
+            argv.extend(["--doc-version", self.args.doc_version])
+
         # Enhancement Workflow arguments
         if getattr(self.args, "enhance_workflow", None):
             for wf in self.args.enhance_workflow: