正解:A,C
Semantic Kernel supports multiple prompt template languages. Handlebars and Liquid both allow you to bind complex objects (with nested/sub-properties), iterate over collections, and use conditionals-ideal when your prompt needs structured data.
JSONL is a dataset/record format, not a prompt templating language.
YAML is a configuration/serialization format; while SK can store configs in YAML, YAML itself isn't a prompt templating engine for rendering nested objects in prompts.
"Semantic Kernel" as an option is not a template language; SK provides the runtime and also a simple legacy template syntax, but for complex/nested objects Microsoft recommends Handlebars (cross-language) or Liquid (.NET).
References (Microsoft Docs):
Handlebars prompt templates in Semantic Kernel (supports SK prompts, expressions, iteration, object binding). Microsoft Learn Liquid prompt templates in Semantic Kernel (example shows passing objects and iterating over nested data).
Microsoft Learn
SK prompt template syntax overview (context on SK templating options). Microsoft Learn