Claude-skill-registry agentuity-cli-cloud-vector-search

Search for vectors using semantic similarity. Requires authentication. Use for Agentuity cloud platform operations

install

source · Clone the upstream repo

git clone https://github.com/majiayu000/claude-skill-registry

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/agentuity-cli-cloud-vector-search" ~/.claude/skills/majiayu000-claude-skill-registry-agentuity-cli-cloud-vector-search && rm -rf "$T"

manifest: skills/data/agentuity-cli-cloud-vector-search/SKILL.md

Cloud Vector Search

Search for vectors using semantic similarity

Prerequisites

Authenticated with
```
agentuity auth login
```
Project context required (run from project directory or use
```
--project-id
```
)

Usage

agentuity cloud vector search <namespace> <query> [options]

Arguments

Argument	Type	Required	Description
`<namespace>`	string	Yes	-
`<query>`	string	Yes	-

Options

Option	Type	Required	Default	Description
`--limit`	number	Yes	-	maximum number of results to return (default: 10)
`--similarity`	number	Yes	-	minimum similarity threshold (0.0-1.0)
`--metadata`	string	Yes	-	filter by metadata (format: key=value or key1=value1,key2=value2)

Examples

Search for similar products:

bunx @agentuity/cli vector search products "comfortable office chair"

Search knowledge base:

bunx @agentuity/cli vector list knowledge-base "machine learning"

Limit results:

bunx @agentuity/cli vector search docs "API documentation" --limit 5

Set minimum similarity:

bunx @agentuity/cli vector search products "ergonomic" --similarity 0.8

Filter by metadata:

bunx @agentuity/cli vector ls embeddings "neural networks" --metadata category=ai

Output

Returns JSON object:

{
  "namespace": "string",
  "query": "string",
  "results": "array",
  "count": "number"
}

Field	Type	Description
`namespace`	string	Namespace name
`query`	string	Search query used
`results`	array	Search results
`count`	number	Number of results found