The Agent Skills Directory

[SAFE]: The skill provides instructions for the AI agent to generate a structured handoff summary at the end of a session. It guides the agent to synthesis information from the current conversation, background processes, and modified files into a chat-only response. The instructions emphasize using absolute paths and specific state identifiers (like shell IDs) to ensure continuity for a subsequent agent instance. The 'hard rules' and 'anti-patterns' sections are designed to maintain structural integrity and prevent unnecessary file writes or memory updates. No malicious patterns, such as prompt injection, data exfiltration, or unauthorized command execution, were detected. The skill operates entirely within the expected behavior of a development assistant summarizing its own activity.

session-handoff