The Agent Skills Directory

[SAFE]: The skill defines a standard task management workflow using internal agent tools such as write_note and search_notes. No external dependencies, network operations, or dangerous command executions are present.- [COMMAND_EXECUTION]: No shell commands or subprocess calls are initiated by this skill; it exclusively uses high-level agent tools for state management.- [DATA_EXFILTRATION]: No network operations or sensitive file access patterns were detected. The skill focuses on local note persistence.- [PROMPT_INJECTION]: The instructions do not contain patterns intended to bypass safety filters or override core agent behavior.

memory-tasks