ic_research_ask
ActiveTool of Immersive Commons
Query the Immersive Commons research RAG corpus (papers + ingested YouTube). Returns top-k chunks with similarity scores and source links. The query text is forwarded to a server-side RAG proxy (supercommons2 via Tailnet Funnel) and NEVER logged on the IC side — privacy contract. Use this for literature lookups, finding related work, surfacing citations the floor has already ingested. Args: { question: string (<=500 chars), k?: number (1-50, default 10), sources?: ('paper'|'book')[] (default ['paper']) }. Returns the upstream RAG response shape — typically { results: [{ paper_id, title, similarity, snippet, link }, ...] }. Required scope: research:query.
Parameters schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"question"
],
"properties": {
"k": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Number of chunks to return. Default 10, max 50."
},
"sources": {
"type": "array",
"items": {
"enum": [
"paper",
"book"
],
"type": "string"
},
"minItems": 1,
"description": "Which corpora to query. Default ['paper']. Pass ['paper','book'] to span both."
},
"question": {
"type": "string",
"maxLength": 500,
"minLength": 1,
"description": "Natural-language question or keyword query. The proxy embeds and runs top-k retrieval against the corpus."
}
}
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
Immersive Commons
https://github.com/immersive-commons/ic-skills
1/7 registries