Answers from the documentation; checking which model is on duty
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.
clone_graphy - Skill - OpenSmartRoute
Skillv1.0.0
clone_graphy
This project has a graphify knowledge graph at graphify-out/.
Imported from GG-QandV/clone_graphy (AGENTS.md). Install upstream with npx skills add GG-QandV/clone_graphy. Copyright stays with the author.
graphify
This project has a graphify knowledge graph at graphify-out/.
Rules:
When working on Graphify itself, use the repository's existing Graphify guidance. For codebase questions, prefer scoped graph queries where available; use the report for broad orientation. Do not use the graph as evidence when the task concerns the graph's correctness itself.
If graphify-out/wiki/index.md exists, navigate it instead of reading raw files
After modifying code files in this session, run graphify update . to keep the graph current (AST-only, no API cost)
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 slotcurl-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 clone_graphy 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.
When a provider is down or over quota the request moves on; the trace says it did.
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
gg-qandv-clone-graphy-clone-graphy.ocm.jsonjson
{
"ocm": "1",
"id": "gg-qandv-clone-graphy-clone-graphy",
"kind": "skill",
"name": "clone_graphy",
"description": "This project has a graphify knowledge graph at graphify-out/.",
"publisher": "GG-QandV",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"This project has a graphify knowledge graph at graphify-out/."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/GG-QandV/clone_graphy",
"path": "AGENTS.md",
"ref": "92741d162b2094ffc2fed58cfbd8ee823e9da62c",
"url": "https://github.com/GG-QandV/clone_graphy/blob/92741d162b2094ffc2fed58cfbd8ee823e9da62c/AGENTS.md",
"key": "GG-QandV/clone_graphy/AGENTS.md"
}
},
"instructions": "## graphify\n\nThis project has a graphify knowledge graph at graphify-out/.\n\nRules:\n- When working on Graphify itself, use the repository's existing Graphify guidance. For codebase questions, prefer scoped graph queries where available; use the report for broad orientation. Do not use the graph as evidence when the task concerns the graph's correctness itself.\n- If graphify-out/wiki/index.md exists, navigate it instead of reading raw files\n- After modifying code files in this session, run `graphify update .` to keep the graph current (AST-only, no API cost)",
"cost": {
"context_tokens": 140
}
}
Fetch it by URL: GET /api/v1/registry/gg-qandv-clone-graphy-clone-graphy/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.
