What problem does it solve? When a conversation with an AI agent grows long or a session must end, context is lost and the next session starts from scratch. This Skill compacts the current conversation into a structured handoff document so a fresh agent can pick up the work without losing progress. ## Core Features & Use Cases - Conversation Compaction: Summarizes the current conversation into a handoff document saved to the operating system's temporary directory, keeping the workspace clean. - Suggested Skills Section: Recommends which skills the next agent should invoke to continue the work effectively. - Deduplication and Redaction: References existing artifacts (specs, plans, ADRs, commits) by path instead of duplicating them, and strips sensitive data such as API keys, passwords, and personally identifiable information. - Use Case: You finish a long debugging session and want a colleague's agent to continue tomorrow. Run the handoff skill with a note like "next session: implement the failing tests" to produce a tailored continuation document. ## Quick Start Ask the agent to create a handoff document for the next session, optionally describing what the next session will focus on.
