Milvus Skill — Data skill for Claude Code
Agent skill that teaches LLMs to operate Milvus vector database using pymilvus — connection, collections, vector CRUD, search, hybrid search, full-text search, indexing, RBAC, and common patter.
How to install Milvus Skill
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open zilliztech/milvus-skill and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Milvus Skill does
Agent skill that teaches LLMs to operate Milvus vector database using pymilvus — connection, collections, vector CRUD, search, hybrid search, full-text search, indexing, RBAC, and common patterns like RAG
Alternatives in Data
- Private GPT — Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more 57.5k ★
- Azure Document Intelligence .net — Document text, table, and data extraction 1.8k ★
- Opencode Mem — OpenCode plugin that gives coding agents persistent memory using local vector database 1.5k ★
README
milvus-skill
An agent skill that teaches LLMs how to use [pymilvus](https://github.com/milvus-io/pymilvus) to operate [Milvus](https://milvus.io/) vector database.
What's Included
- SKILL.md — Main skill definition with connection, collection management, vector operations, and index management
- references/ — Detailed reference docs for each feature area:
collection.md— Data types, schema fields, collection operationsvector.md— Insert, search, hybrid search, full-text search, iterators, filtersindex.md— Index types, metric types, create/manage indexespartition.md— Partition CRUDdatabase.md— Database managementuser-role.md— RBAC: users, roles, privilegespatterns.md— Common patterns (RAG, semantic search, hybrid search, full-text search)
Install as Claude Code Skill
claude skill add --url https://github.com/zilliztech/milvus-skillCapabilities
- Connect to Milvus Lite, Standalone, Cluster, or Zilliz Cloud
- Create collections with quick or custom schemas
- Insert, upsert, search, query, get, delete vectors
- Hybrid search with RRF/Weighted reranking
- Full-text search with BM25
- Paginated iteration over large result sets
- Index management (AUTOINDEX, HNSW, IVF_FLAT, etc.)
- Partition, database, and RBAC management
Requirements
- Python 3.8+
pymilvus(pip install pymilvus)
Related Skills
Memory Architecture
Configure, maintain, and troubleshoot the Qdrant vector database layer of Memory OS. Covers collection setup,
Redis Search
Scaffold Redis search adapters (RediSearch full-text, vector, search caching)
Jev Cookbook
Practical, tested recipes for TypeSafe's Jev decision model on OpenRouter: support triage, database indexing,
Docwise Agentic
Full agentic RAG pipeline: adaptive chunking → Qdrant hybrid search (semantic + BM25 + RRF) → LangGraph ReAct
Claudex
by Kunwar Shah - Claudex - A web-based browser for exploring your Claude Code conversation history across proj
Claudoscope
29 Native macOS menu bar app for Claude Code session analytics. Token/cost tracking, full-text search, real-ti
Related Agents
Local Brain Search
Local vector search and connection discovery for the Brain. Use for semantic search, finding connections betwe
Python RAG Backend Engineer
Production-grade Python RAG backend engineer specializing in ChromaDB vector storage, sentence-transformers em
Brain Retrieval Engineer
Retrieval engineer — six retrieval strategies (hybrid, graph-enhanced vector, entity-anchored local, guarded T
