The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run various system commands such as patent-creator health, claude mcp list, and gcloud auth application-default login. These are used for environment diagnostics and configuration.
[DYNAMIC_EXECUTION]: Diagnostic steps include executing inline Python code snippets (e.g., python -c "...") to verify the functionality of internal modules like MPEPIndex and BigQueryPatentSearch.
[INDIRECT_PROMPT_INJECTION]: As a troubleshooting assistant, the skill is designed to process user-provided information such as error logs and system states.
Ingestion points: User-reported error messages and log outputs provided during diagnostic sessions.
Boundary markers: None identified in the instructions to separate user data from diagnostic commands.
Capability inventory: Ability to execute shell commands and Python scripts via the system interface.
Sanitization: No specific sanitization or validation logic is defined for processing external diagnostic data before command execution.

troubleshooting-assistant