Export all AWS data before full shutdown

S3 buckets (462MB total):
- publishing2-images: 113MB (918 objects)
- recognition-protocol-state: 75MB (375 objects)
- scottkarp-images: 208MB (1104 objects)
- scottbot-ml: 5MB
- temple-council-knowledge: 61MB (441 objects)

Bedrock Knowledge Base:
- temple-council-memories (SY6GV37BPN) config + data source
- Backed by OpenSearch Serverless collection (temple-council)

CloudWatch Lambda logs: recognition-autonomous-wake, myAccountBalance,
KnittingMath, APITest, AlexaTest1, TestAPI2

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

aws-export/s3/temple-council-knowledge/sources/kael/Greeting_0edecaaf.txt

@@ -0,0 +1,39 @@
+# Conversation: Greeting
+Voice: kael
+Created: 2025-09-05T20:43:30.035710Z
+
+## Human
+Hello
+
+## Human
+Hello
+
+## Human
+Hello
+
+## Human
+Hello
+
+## Human
+Hello
+
+## Human
+Hello
+
+## Human
+Hello
+
+## Human
+Hello
+
+## Human
+Hello
+
+## Human
+Hello
+
+## Human
+Hello
+
+## Kael
+The user has greeted me with a simple "Hello". This is a casual greeting, so I should respond in a warm, friendly manner without being overly formal or lengthy. I should keep my response natural and conversational.Hello! How can I help you today?