Skip to content
Agentmart
Submit a tool

human-handoff

Seamlessly transitions conversation from AI to human staff when user requests a representative, complexity exceeds AI scope, or safety guardrails trigger.

Skill by yuanweize

IndexedMIT★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/yuanweize-human-handoff

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Seamlessly transitions conversation from AI to human staff when user requests a representative, complexity exceeds AI scope, or safety guardrails trigger.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/human-handoff

What's inside

Skill name
human-handoff
Description
Seamlessly transitions conversation from AI to human staff when user requests a representative, complexity exceeds AI scope, or safety guardrails trigger.
License
MIT
Instructions
15 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Human Handoff Skill

## Objective
Recognize when a human representative is needed, pause automatic replies if configured, notify the customer that an agent has been summoned, and draft a concise handover context for the inbox.

## Guidelines
1. Trigger human handoff immediately when:
   - The user explicitly asks for a human ("talk to a human", "speak to staff", "call me").
   - The inquiry involves legal threats, severe harassment, or explicit security concerns.
   - The AI has low confidence or two consecutive failed clarification turns.
   - Sensitive financial transactions or non-standard refund approvals are requested.
2. Reply politely with a reassuring acknowledgment: let the user know a team member is reviewing the conversation.
3. Mark decision as `handoff`.

From yuanweize/signal-ai-agent-platform, MIT.

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Sep 22, 2026 (1 month ago)
Last release
Sep 25, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from yuanweize

Cite this page

human-handoff skill. Agent Mart. https://agentmart.dev/skills/yuanweize-human-handoff (last updated 2026-10-24)