The Agent Skills Directory

[SAFE]: The skill is designed to facilitate session continuity by querying a local knowledge graph. All operations (searching, reading notes, and building context) are performed through internal Model Context Protocol (MCP) tools (build_context, recent_activity, search_notes, read_note, list_memory_projects).
[SAFE]: No external network operations, credential exposures, or dangerous command executions were detected. The skill uses a custom memory:// URI scheme for internal data addressing.
[SAFE]: The skill instructions do not contain any prompt injection, obfuscation, or persistence mechanisms. It follows standard patterns for managing conversational state and project-specific documentation.

memory-continue