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.
safety-escalation - Skill - OpenSmartRoute
Skillv1.0.0
safety-escalation
Route potential professional safety concerns through approved evidence and qualified-human escalation.
Imported from wanghanyu654321-cell/-agent (skills/safety-escalation/SKILL.md). Install upstream with npx skills add wanghanyu654321-cell/-agent --skill safety-escalation. Copyright stays with the author.
Recognize a potential professional safety concern without claiming diagnosis or certainty. Retrieve approved safety knowledge before discussing any professional handling option. Use only the retrieved approved evidence, and present no more than three options actually supported by it.
If evidence is missing, partial, synthetic, unapproved, or requires qualified review, tell the operator to pause the current operation and escalate to a qualified human. Never use model memory as safety evidence. Do not invent treatment, contraindications, device instructions, allergy handling, or professional safety facts.
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.
{
"ocm": "1",
"id": "wanghanyu654321-cell-agent-safety-escalation",
"kind": "skill",
"name": "safety-escalation",
"description": "Route potential professional safety concerns through approved evidence and qualified-human escalation.",
"publisher": "wanghanyu654321-cell",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Route potential professional safety concerns through approved evidence and qualified-human escalation."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/wanghanyu654321-cell/-agent",
"path": "skills/safety-escalation/SKILL.md",
"ref": "890d44992daf5ca9b70539ae5eb79ae54d086289",
"url": "https://github.com/wanghanyu654321-cell/-agent/blob/890d44992daf5ca9b70539ae5eb79ae54d086289/skills/safety-escalation/SKILL.md",
"key": "wanghanyu654321-cell/-agent/skills/safety-escalation/SKILL.md"
}
},
"instructions": "Recognize a potential professional safety concern without claiming diagnosis or certainty. Retrieve approved safety knowledge before discussing any professional handling option. Use only the retrieved approved evidence, and present no more than three options actually supported by it.\n\nIf evidence is missing, partial, synthetic, unapproved, or requires qualified review, tell the operator to pause the current operation and escalate to a qualified human. Never use model memory as safety evidence. Do not invent treatment, contraindications, device instructions, allergy handling, or professional sa",
"cost": {
"context_tokens": 152
}
}
Fetch it by URL: GET /api/v1/registry/wanghanyu654321-cell-agent-safety-escalation/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.
