handoff-reply
CommunityGet user-approved replies without surprises.
Product & Management#handoff#decision support#human-in-the-loop#agent collaboration#workflow guardrails#draft approval#chat routing
AuthorLevezze
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It prevents cross-agent chats from silently bypassing the human by pausing before writing any message that requires the user’s judgment.
Core Features & Use Cases
- User-first “grill-me” gate: Detects when incoming agent messages require decisions, assumptions, or tradeoffs only the user can own, then asks targeted questions before any reply is appended.
- Automated chat targeting: Reads the right
/tmp/handoff-chat-<slug>.mdby slug (or auto-selects the most relevant file when omitted) and identifies the correct participant handle to determine what’s “new.” - Draft-before-commit workflow: Produces a structured draft reply for review and confirmation, and only appends it after explicit user approval.
- Use Case: When another agent proposes a product direction, naming, or “should we ship” decision, the skill ensures the human is asked first with a short, decision-focused set of questions.
Quick Start
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.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: handoff-reply Download link: https://github.com/Levezze/devkit/archive/main.zip#handoff-reply Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.