Read handoff-chat messages and pause for user confirmation before appending replies.
npx skills add https://github.com/Levezze/devkit --skill handoff-reply
Please help me install this Agent Skill. Skill: handoff-reply Source: https://github.com/Levezze/devkit/tree/main/skills/handoff-reply Command: npx skills add https://github.com/Levezze/devkit --skill handoff-reply
It prevents cross-agent chats from silently bypassing the human by pausing before writing any message that requires the user’s judgment.
/tmp/handoff-chat-<slug>.md by slug (or auto-selects the most relevant file when omitted) and identifies the correct participant handle to determine what’s “new.”Invoke the skill as /handoff-reply to review the newest handoff chat message that needs your judgment, answer the grill questions, and then confirm the drafted reply to post.
High-intent search queries and answers about installing and using this skill.
Human-in-the-loop reply orchestration pauses cross-agent chats before writing messages that require user judgment, parsing chat participants and message history to detect ambiguous or assumption-heavy requests that must not be auto-replied.
Draft-before-commit workflow for agent collaboration generates a structured draft reply for review, asking targeted grill-me questions first, and only appends the final message to the handoff chat after explicit user confirmation.
A grill-me prompt in agent collaboration is a decision-focused gate that detects incoming agent messages requiring tradeoffs or assumptions, then asks the user targeted questions before any reply is drafted and appended to the chat.
Yes, handoff-chat targeting auto-selects the most relevant /tmp/handoff-chat-<slug>.md file when the slug is omitted, reading the correct file and identifying the appropriate participant handle to determine new messages.
Human-in-the-loop guardrails are needed whenever another agent proposes product directions, naming, or ship decisions, ensuring the human is asked first with a short, decision-focused set of questions before appending any reply.
Chat routing for draft approval requires parsing message history and participant handles from /tmp files, meaning it cannot process chats lacking structured handoff files or auto-reply to messages that explicitly require user judgment.
LevezzeAppend user messages to a shared handoff chat file for multi-agent coordination.
cdrguruAppend structured handoff entries to the append-only handoff log.
sunnypatneediCoordinate multiple AI agents for integrated marketing campaigns with human-in-the-loop approvals.
razorpayClassify pull requests in the agent-skills repository as LOW, MEDIUM, or HIGH risk.