Agent handoff routing

Skill kjuhwa/skills-hub/skills/llm-agents/agent-handoff-routing

Self-correcting knowledge corpus for Claude Code — 9 stable shape clusters, bias-correction pipeline baked into contribution flow. 47 papers, 45 techniques, 1.1k skills.

Install

npx -y skills add kjuhwa/skills-hub --skill agent-handoff-routing

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Route a conversation to a specialist agent via handoff, making that agent own the next turn.

SKILL.md

2.4 KB, 417 tokens by cl100k_base, as published. Nobody here has run it

agent-handoff-routing

List specialist agents in Agent.handoffs. A triage agent inspects the user message and calls transfer_to_<agent_name> to delegate. The specialist becomes the active agent for the remainder of the run.

When to apply

Multi-language support, department routing (billing/support/refunds), or any scenario where the triage agent should not compose the final reply itself.

Core snippet

from agents import Agent, Runner, trace

french_agent = Agent(name="french_agent", instructions="You only speak French")
spanish_agent = Agent(name="spanish_agent", instructions="You only speak Spanish")
english_agent = Agent(name="english_agent", instructions="You only speak English")

triage_agent = Agent(
    name="triage_agent",
    instructions="Handoff to the appropriate agent based on the language of the request.",
    handoffs=[french_agent, spanish_agent, english_agent],
)

async def main():
    with trace("Routing example"):
        result = await Runner.run(triage_agent, "Bonjour, comment vas-tu?")
        print(result.final_output)

With custom handoff description

from agents import handoff

spanish_agent = Agent(
    name="Spanish Assistant",
    instructions="You only speak Spanish and are extremely concise.",
    handoff_description="A Spanish-speaking assistant.",  # Shown to triage LLM
)

triage_agent = Agent(
    name="triage_agent",
    handoffs=[handoff(spanish_agent, tool_name_override="speak_spanish")],
)

Key notes

Handoffs are represented as tools; the tool name defaults to transfer_to_<agent_name>
After handoff, the specialist agent owns the active conversation — no narration from the triage agent
Use handoff_description on the specialist to hint when the model should pick it
For agents-as-tools (specialist helps but triage keeps control), use Agent.as_tool() instead

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.