libvector
libvector - Vector similarity search. VectorIndex stores embeddings with metadata and performs cosine similarity search. VectorProcessor handles embedding generation and indexing. Supports filtering by metadata and threshold-based retrieval. Use for semantic search, RAG retrieval, and similarity matching.
npx skills add majiayu000/claude-skill-registry --skill libvector-copilot-ld-copilot-ld-2 --agent copilot
Same command for any agent — swap --agent for claude-code, codex, cursor.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# libvector Skill ## When to Use - Building semantic search functionality - Implementing RAG retrieval pipelines - Finding similar documents by embedding - Filtering vector results by metadata ## Key Concepts **VectorIndex**: Storage-backed index for vectors with cosine similarity search and metadata filtering. **VectorProcessor**: Processes documents into embeddings and indexes them. **calculateDotProduct**: Utility function for computing dot product (cosine similarity for normalized vectors) with loop unrolling for performance. ## Usage Patterns ### Pattern 1: Search by vector ```javascript import { VectorIndex } from "@copilot-ld/libvector/index.js"; const index = new VectorIndex(storage, "content"); const results = await index.search(queryVector, { limit: 10, threshold: 0.7, filter: { type: "document" }, }); ``` ### Pattern 2: Add vectors ```javascript await index.add({ id: "doc-123", vector: embedding, metadata: { type: "document", title: "Example" }, }); ``` ### Pattern 3: Calculate similarity directly ```javascript import { calculateDotProduct } from "@copilot-ld/libvector"; // For normalized vectors, dot product equals cosine similarity const similarity = calculateDotProduc
- When to Use
- Key Concepts
- Usage Patterns
- Pattern 1: Search by vector
- Pattern 2: Add vectors
- Pattern 3: Calculate similarity directly
- Integration
What does the libvector skill do?
libvector - Vector similarity search. VectorIndex stores embeddings with metadata and performs cosine similarity search. VectorProcessor handles embedding generation and indexing. Supports filtering by metadata and threshold-based retrieval. Use for semantic search, RAG retrieval, and similarity matching.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill libvector-copilot-ld-copilot-ld-2 --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.