Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →evolution-foundation/knowledge-query
Hybrid search (vector + BM25 via RRF + metadata boost) against the pgvector Knowledge base, with optional RAG synthesis.
Passed 18 of 21 test cases with the skill, and 5 of 21 without it.
and 16 more in the full report
15 fixed6 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Format search snippet results for document titled 'API Gateway Spec' with content type 'markdown' and metadata page '12'.
| Checked | Without skill | With skill |
|---|---|---|
| Formats the header line as **[markdown]** API Gateway Spec — p.12. | Missed | Passed |
The instructions your model reads when the skill loads.
Group: Consumption. Hybrid search on pgvector + optional RAG (LLM synthesis with citations).
| Name | Type | Default | Description |
|---|---|---|---|
query | str | required | Natural language question |
connection | str | first ready | Connection slug (e.g., "academy", "acme") |
space | str | null = all | Space slug within the connection |
top_k | int | 5 | How many snippets to return |
filters | dict | {} | {unit_id, content_type, topics, date_range} |
answer | bool | false | If true, synthesize narrative answer with citations |
If connection is not provided, call GET /api/knowledge/connections?status=ready and use the first one. If none ready: return actionable error: "No Knowledge connection configured. Run knowledge-admin action=connect first."
from dashboard.backend.sdk_client import evo
hits = evo.post(
"/api/knowledge/v1/search",
{"query": query, "space": space, "top_k": top_k, "filters": filters},
headers={"X-Knowledge-Connection": connection},
)
test cases passed, vs 5 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.