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.
1. Call the bundled `xhr-assistant` MCP server's `read` tool with `skills/compensation_benefits/SKILL.md`. 2. Follow only child entrypoints declared by that index. 3. Call that same MCP server's `read
Imported from xhr-labs/agent-xhr-plugins (plugins/xhr-assistant-macos/skills/xhr-compensation-benefits/SKILL.md). Install upstream with npx skills add xhr-labs/agent-xhr-plugins --skill xhr-compensation-benefits. Copyright stays with the author.
name: xhr-compensation-benefits
description: Handle xHR compensation and benefits: reward elements, package groups, C&B components, and payroll integration guidance.
xHR Compensation & Benefits
Call the bundled xhr-assistant MCP server's read tool with skills/compensation_benefits/SKILL.md.
Follow only child entrypoints declared by that index.
Call that same MCP server's read tool for the single leaf that best matches the request.
Follow the complete leaf instructions and collect all required arguments.
Call that same MCP server's exec tool only for a script explicitly declared by the leaf.
If exec returns AUTHENTICATION_REQUIRED, ask for explicit confirmation to open the private xHR authentication window. After confirmation, call authenticate with no arguments, then retry the original exec once when authentication succeeds.
Never ask for or accept an access token in chat or MCP tool arguments.
Never guess a script path, operation, identifier, or argument.
Obtain explicit confirmation before an action that changes xHR data.
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": "xhr-labs-agent-xhr-plugins-xhr-compensation-benefits",
"kind": "skill",
"name": "xhr-compensation-benefits",
"description": "1. Call the bundled `xhr-assistant` MCP server's `read` tool with `skills/compensation_benefits/SKILL.md`. 2. Follow only child entrypoints declared by that index. 3. Call that same MCP server's `read` tool for the single leaf that best matches the request. 4. Follow the complete leaf instructions and collect all required arguments. 5. Call that same MCP server's `exec` tool only for a script explicitly declared by the leaf. 6. If `exec` returns `AUTHENTICATION_REQUIRED`, ask for explicit confirmation to open the private xHR authentication window. After confirmation, call `authenticate` with no arguments, then retry the original `exec` once when authentication succeeds. 7. Never ask for or accept an access token in chat or MCP tool arguments. 8. Never guess a script path, operation, identifier, or argument. 9. Obtain explicit confirmation before an action that changes xHR data.",
"publisher": "xhr-labs",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"1. Call the bundled `xhr-assistant` MCP server's `read` tool with `skills/compensation_benefits/SKILL.md`. 2. Follow only child entrypoints declared by that index. 3. Call that same MCP server's `read` tool for the single leaf that best matches the request. 4. Follow the complete leaf instructions and collect all required arguments. 5. Call that same MCP server's `exec` tool only for a script explicitly declared by the leaf. 6. If `exec` returns `AUTHENTICATION_REQUIRED`, ask for explicit confirmation to open the private xHR authentication window. After confirmation, call `authenticate` with no arguments, then retry the original `exec` once when authentication succeeds. 7. Never ask for or accept an access token in chat or MCP tool arguments. 8. Never guess a script path, operation, identifier, or argument. 9. Obtain explicit confirmation before an action that changes xHR data."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/xhr-labs/agent-xhr-plugins",
"path": "plugins/xhr-assistant-macos/skills/xhr-compensation-benefits/SKILL.md",
"ref": "ef9bd873ed34f3a20694234626c9ddbbd9a3a1ac",
"url": "https://github.com/xhr-labs/agent-xhr-plugins/blob/ef9bd873ed34f3a20694234626c9ddbbd9a3a1ac/plugins/xhr-assistant-macos/skills/xhr-compensation-benefits/SKILL.md",
"key": "xhr-labs/agent-xhr-plugins/plugins/xhr-assistant-macos/skills/xhr-compensation-benefits/SKILL.md"
}
},
"instructions": "---\nname: xhr-compensation-benefits\ndescription: Handle xHR compensation and benefits: reward elements, package groups, C&B components, and payroll integration guidance.\n---\n\n# xHR Compensation & Benefits\n\n1. Call the bundled `xhr-assistant` MCP server's `read` tool with `skills/compensation_benefits/SKILL.md`.\n2. Follow only child entrypoints declared by that index.\n3. Call that same MCP server's `read` tool for the single leaf that best matches the request.\n4. Follow the complete leaf instructions and collect all required arguments.\n5. Call that same MCP server's `exec` tool only for a scrip",
"cost": {
"context_tokens": 274
}
}
Fetch it by URL: GET /api/v1/registry/xhr-labs-agent-xhr-plugins-xhr-compensation-benefits/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.
