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.
Subject-Knowledge-Hub - Skill - OpenSmartRoute
Skillv1.0.0
Subject-Knowledge-Hub
Read [HANDOVER.md](HANDOVER.md) first, then inspect the modules relevant to the task.
Imported from xuantrung-DA/Subject-Knowledge-Hub (AGENTS.md). Install upstream with npx skills add xuantrung-DA/Subject-Knowledge-Hub. Copyright stays with the author.
Working in this repository
Read HANDOVER.md first, then inspect the modules relevant to the task.
Preserve scope/version isolation, durable checkpoints and commit-before-publish.
Run database/recovery tests in an isolated Compose project.
Keep paid calls explicitly opted in and within the user's authorized budget.
Never expose or commit env secrets, session traces, database dumps or user PDFs.
Follow Ruff/Prettier and run checks appropriate to the change.
Update HANDOVER.md when architecture, contracts or operations change.
Preserve historical benchmark artifacts and their measurement limitations.
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}'
Installed into a catalogue, chosen by a router
Install Subject-Knowledge-Hub and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
{
"ocm": "1",
"id": "xuantrung-da-subject-knowledge-hub-subject-knowledge-hub",
"kind": "skill",
"name": "Subject-Knowledge-Hub",
"description": "Read [HANDOVER.md](HANDOVER.md) first, then inspect the modules relevant to the task.",
"publisher": "xuantrung-DA",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Read [HANDOVER.md](HANDOVER.md) first, then inspect the modules relevant to the task."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/xuantrung-DA/Subject-Knowledge-Hub",
"path": "AGENTS.md",
"ref": "fb225e8bbbad532311895c436ee13c2a3cd7cab8",
"url": "https://github.com/xuantrung-DA/Subject-Knowledge-Hub/blob/fb225e8bbbad532311895c436ee13c2a3cd7cab8/AGENTS.md",
"key": "xuantrung-DA/Subject-Knowledge-Hub/AGENTS.md"
}
},
"instructions": "# Working in this repository\n\nRead [HANDOVER.md](HANDOVER.md) first, then inspect the modules relevant to the task.\n\n- Preserve scope/version isolation, durable checkpoints and commit-before-publish.\n- Run database/recovery tests in an isolated Compose project.\n- Keep paid calls explicitly opted in and within the user's authorized budget.\n- Never expose or commit env secrets, session traces, database dumps or user PDFs.\n- Follow Ruff/Prettier and run checks appropriate to the change.\n- Update HANDOVER.md when architecture, contracts or operations change.\n- Preserve historical benchmark artifac",
"cost": {
"context_tokens": 159
}
}
Fetch it by URL: GET /api/v1/registry/xuantrung-da-subject-knowledge-hub-subject-knowledge-hub/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.
