Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
handoff - Skill - OpenSmartRoute
Skillv1.0.0
handoff
Description: Escalate the conversation to a human agent when the situation is beyond the AI's scope or the user requests it.
Imported from 147phuc23/zalo-agent (packages/agent/src/skills/global/handoff/SKILL.md). Install upstream with npx skills add 147phuc23/zalo-agent --skill handoff. Copyright stays with the author.
Handoff
Description: Escalate the conversation to a human agent when the situation is beyond the AI's scope or the user requests it.
When to use
User explicitly asks to speak to a human
User is distressed, angry, or the conversation is emotionally sensitive
The request requires authority or decision-making only a human can provide
Repeated misunderstandings that the AI cannot resolve
Behaviour
Acknowledge the user's request warmly
Confirm that a human will follow up
Do not attempt to resolve the issue yourself after triggering handoff
Log the reason for handoff
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
147phuc23-zalo-agent-handoff.ocm.jsonjson
{
"ocm": "1",
"id": "147phuc23-zalo-agent-handoff",
"kind": "skill",
"name": "handoff",
"description": "Description: Escalate the conversation to a human agent when the situation is beyond the AI's scope or the user requests it.",
"publisher": "147phuc23",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Description: Escalate the conversation to a human agent when the situation is beyond the AI's scope or the user requests it."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/147phuc23/zalo-agent",
"path": "packages/agent/src/skills/global/handoff/SKILL.md",
"ref": "bc718cc49e4b577fdcb9d35216a01030f6e0be5a",
"url": "https://github.com/147phuc23/zalo-agent/blob/bc718cc49e4b577fdcb9d35216a01030f6e0be5a/packages/agent/src/skills/global/handoff/SKILL.md",
"key": "147phuc23/zalo-agent/packages/agent/src/skills/global/handoff/SKILL.md"
}
},
"instructions": "# Handoff\n\nDescription: Escalate the conversation to a human agent when the situation is beyond the AI's scope or the user requests it.\n\n## When to use\n\n- User explicitly asks to speak to a human\n- User is distressed, angry, or the conversation is emotionally sensitive\n- The request requires authority or decision-making only a human can provide\n- Repeated misunderstandings that the AI cannot resolve\n\n## Behaviour\n\n- Acknowledge the user's request warmly\n- Confirm that a human will follow up\n- Do not attempt to resolve the issue yourself after triggering handoff\n- Log the reason for handoff",
"cost": {
"context_tokens": 149
}
}
Fetch it by URL: GET /api/v1/registry/147phuc23-zalo-agent-handoff/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
