vector-search
Implement vector search for knowledge retrieval. Use when adding RAG, semantic search, knowledge base features, or context building for the agent.
npx skills add majiayu000/claude-skill-registry --skill vector-search --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Vector Search (Upstash Vector) Context strategy is **retrieval-first**. The agent uses hybrid search (dense + sparse) to find relevant context. ## Upstash Vector Setup ```typescript import { Index } from '@upstash/vector' const index = new Index({ url: process.env.UPSTASH_VECTOR_URL, token: process.env.UPSTASH_VECTOR_TOKEN, }) ``` ## Document Types Single index with type filters: ```typescript interface VectorDocument { id: string data: string // The text content (PII-redacted) metadata: { type: 'conversation' | 'knowledge' | 'response' appId: string // Conversation metadata category?: MessageCategory resolution?: 'refund' | 'transfer' | 'info' | 'escalated' customerSentiment?: 'positive' | 'neutral' | 'negative' touchCount?: number resolvedAt?: string // Knowledge metadata source?: 'docs' | 'faq' | 'policy' | 'canned-response' title?: string lastUpdated?: string // Response metadata trustScore?: number usageCount?: number conversationId?: string } } ``` ## PII Redaction (Required) Always redact PII before embedding: ```typescript function redactPII(text: string, knownNames: string[] = []): string { let redacted = text // Email .replace(/[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]
- Upstash Vector Setup
- Document Types
- PII Redaction (Required)
- Upsert Pattern
- Agent Context Building
- Optional: Cohere Rerank
- File Locations
- Reference Docs
What does the vector-search skill do?
Implement vector search for knowledge retrieval. Use when adding RAG, semantic search, knowledge base features, or context building for the agent.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill vector-search --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.