The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute local cleanup scripts (clean_resources.py) across various workshop-specific subdirectories. This is the primary intended functionality of the skill.
[DATA_EXPOSURE]: The skill identifies and reads local configuration files such as .bedrock_agentcore.yaml, inbound_authorizer.json, and policy_config.json to verify if resources were successfully created before attempting to delete them.
[PROMPT_INJECTION]: The skill accepts user-provided input through $ARGUMENTS to filter which steps to clean. The instructions specify that the agent should parse these arguments to determine the steps, which is a standard pattern for argument processing.

clean-workshop