Split Hamilton Claude plugin into 5 focused skills

Replace single monolithic skill with 5 specialized skills for better organization:

- **core**: Basic Hamilton patterns (DAG creation, decorators, testing, debugging)
- **scale**: Performance & parallelization (async, Spark, Ray, Dask, caching, multithreading)
- **llm**: AI/ML workflows (RAG pipelines, embeddings, vector DBs, prompt engineering)
- **observability**: Hamilton UI & SDK (tracking, monitoring, lineage, debugging)
- **integrations**: Orchestrators & frameworks (Airflow, FastAPI, Streamlit, Jupyter)

Each skill is ~200-400 lines, focused, and independently invocable via:
- /hamilton-core
- /hamilton-scale
- /hamilton-llm
- /hamilton-observability
- /hamilton-integrations

Benefits:
- Faster skill loading (only load what's needed)
- Better context relevance (focused expertise)
- Easier maintenance (separate concerns)
- Scales with Hamilton's growth (can add more skills)

Updated plugin.json to v2.0.0 with array of skill paths.

Author: skrawcz

.claude/plugins/hamilton/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "hamilton",
-  "version": "1.0.0",
+  "version": "2.0.0",
   "description": "Expert AI assistant for Apache Hamilton framework development - create DAGs, apply decorators, debug dataflows, and optimize pipelines",
   "author": {
     "name": "Hamilton Team",
@@ -17,7 +17,18 @@
     "pipeline",
     "data-engineering",
     "ml-ops",
-    "feature-engineering"
+    "feature-engineering",
+    "llm",
+    "rag",
+    "async",
+    "spark",
+    "observability"
   ],
-  "skills": "./skills/"
+  "skills": [
+    "./skills/core",
+    "./skills/scale",
+    "./skills/llm",
+    "./skills/observability",
+    "./skills/integrations"
+  ]
 }