chore: update dataset prompt phrasing and add skills evaluation configs to run_config

Author: omkargaikwad23

evals/dataset.json

@@ -17,7 +17,7 @@
     {
       "id": "cloud-sql-schema-tables-explore",
       "starting_prompt": "I want to understand the structure of my database.",
-      "conversation_plan": "First, ask the agent to list the databases in the instance. After the agent provides the databases, ask it to list the tables specifically for the database.",
+      "conversation_plan": "First, ask the agent to list the databases in the instance. After the agent provides the databases, ask it to list the tables specifically for that database.",
       "expected_trajectory": [
         "list_databases",
         "list_tables"

evals/run_config.yaml

@@ -25,12 +25,15 @@ scorers:
     model_config: /workspace/evals/gemini_2.5_pro_model.yaml
   behavioral_metrics:
     model_config: /workspace/evals/gemini_2.5_pro_model.yaml
+  skills_best_practices:
+    model_config: /workspace/evals/gemini_2.5_pro_model.yaml
 
   # Performance
   turn_count: {}
   end_to_end_latency: {}
   tool_call_latency: {}
   token_consumption: {}
+  skills_trajectory: {}
 
 reporting:
   bigquery: