Weaviate Agent Skills
Official Weaviate skills: vector database search, data import and ready-made RAG app blueprints for Claude Code and Cursor
- 104 ★ on the repository
- Last commit
- BSD-3-Clause
Extended access
Why this level
- The scripts create collections and import data into your Weaviate cluster using an API key
- The API key and cluster address live in environment variables that any script the agent runs can read
- The app blueprints pull third-party Python packages whose security the authors do not verify
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/weaviate-agent-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The scripts create collections and import data into your Weaviate cluster using an API key
- The API key and cluster address live in environment variables that any script the agent runs can read
- The app blueprints pull third-party Python packages whose security the authors do not verify
This is third-party code. Review the repository files before installing.
What it does
Weaviate Agent Skills is a package from Weaviate itself that teaches an agent to work with this vector database. The `weaviate` skill can create collections, inspect schema and metadata, search by keyword, by meaning and in hybrid mode, fetch objects by filters, import data from PDF, CSV, JSON and JSONL, and put questions to the Query Agent, which answers with source citations. In Claude Code the set arrives as a plugin with the commands `/weaviate:quickstart`, `/weaviate:ask`, `/weaviate:query`, `/weaviate:search`, `/weaviate:collections`, `/weaviate:explore` and `/weaviate:fetch`. The first command walks you through setting environment variables and loading your own or sample data. The second skill, `weaviate-cookbooks`, holds blueprints for whole applications: multimodal PDF ingestion, basic, advanced and agentic RAG, a chatbot on the Query Agent, a data explorer and an optional frontend. Underneath sit Python scripts that the agent runs through uv or pip.
Who it is for. Developers building search and RAG on Weaviate who want the agent to write queries, create collections and load data into their cluster.
Good fit when
- The Weaviate cluster already has collections and you want to ask them questions in plain words
- You have to choose between keyword, semantic and hybrid search and compare results on your own data
- A folder of PDFs or tables should become a collection that the agent then searches
- A RAG app is being built from scratch and a proven blueprint beats a blank page
- A new team member connects to Weaviate Cloud for the first time and needs a guided start
Not a fit when
- The data lives in another vector database: the skills only work with Weaviate
- You have no cluster or API key and do not want to run a database locally: the scripts expect `WEAVIATE_URL` and `WEAVIATE_API_KEY`
- The production app code has to manage without Python 3.11 and uv, because the scripts are built on them
- The agent must not get write access to the cluster: the set can create collections and import data
Example request
List the collections in my Weaviate and find three passages about HNSW indexes in the Documentation collection using hybrid searchLimitations
You need Python 3.11 or newer, uv or pip and a Weaviate cluster, for example a free one in Weaviate Cloud. The address and key go in as environment variables `WEAVIATE_URL` and `WEAVIATE_API_KEY`, external embedding providers add their own keys; the full list is in `skills/weaviate/references/environment_requirements.md`. The authors warn that the scripts and blueprints rely on third-party packages whose security they do not vouch for, and advise scanning dependencies before running.
How to disable. Disable the plugin through `/plugin` in Claude Code or remove the skills with your skills manager. Collections and data in your Weaviate cluster stay: delete them in the Weaviate console.
FAQ
How do I install Weaviate Agent Skills in Claude Code?
Run `/plugin marketplace add weaviate/agent-skills`, then `/plugin install weaviate@weaviate-plugins`. For Cursor and other agents use `npx skills add weaviate/agent-skills`. After installing, run `/weaviate:quickstart`: it asks for the address and key and offers to load sample data.
What is needed for the skills to work?
A Weaviate cluster, the variables `WEAVIATE_URL` and `WEAVIATE_API_KEY`, Python 3.11 or newer and uv or pip. A free cluster is created in Weaviate Cloud. Semantic search needs an embedding provider configured on the cluster, and its key is also passed as an environment variable.
How does the weaviate skill differ from weaviate-cookbooks?
`weaviate` performs actions on the database: queries, schemas, import. `weaviate-cookbooks` describes how to build a whole application: RAG, a chatbot, a data explorer. The first is for daily work, the second for starting a new project.
Can the set touch the database without my confirmation?
The agent runs the scripts itself, so it depends on your permission settings. Reading is safer than writing: creating collections and importing change the cluster data, so keep a confirmation prompt for them in Claude Code or Cursor.
Which commands does the plugin add to Claude Code?
The commands `/weaviate:quickstart`, `/weaviate:ask`, `/weaviate:query`, `/weaviate:search`, `/weaviate:collections`, `/weaviate:explore` and `/weaviate:fetch`. For example, `/weaviate:search query "best laptops" collection "Products" type "hybrid" alpha "0.7"` runs a hybrid search with a weight of 0.7.
Discussion
No questions or reviews yet.
Related
SkillsAround 200 skills for Claude Code on bioinformatics, chemistry and biostatistics, from RNA-seq analysis to molecular docking
The Zvec skill guides an agent through the embedded vector database: collection schema, hybrid search, RAG and multimodal queries
Nine Pinecone skills: the agent creates a vector index, loads data, searches it and builds an assistant for documents
A local MCP server that turns a folder of documents into a knowledge base with hybrid search for Claude Code and Cursor
AntV Chart Visualization Skills
chart-visualization-skills
Data visualization skills from AntV: choosing a chart type and building it. The repository accepts only AI code. The antv CLI
VisActor Skills: charts, dashboards and posters
VisActor Skills
Nine VisActor skills: business charts, data stories, map dashboards and posters, all assembled by your agent
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Weaviate Agent Skills (this card) | yes | 104 | ||
| Qdrant Skills | no | 267 | skills for a different vector database, Qdrant | |
| Qdrant MCP Server | yes | key is optional | 1,563 | an official MCP semantic-memory server on Qdrant, without RAG app blueprints |
README in short
The README gives three install routes, a quickstart, cloud cluster and environment variable setup, a list of what the two skills can do and examples of plugin commands with parameters. The security section flags third-party packages, and the end collects links to Weaviate docs and ebooks.
README badge
Original SKILL.md
--- name: weaviate description: Search, query, and manage Weaviate vector database collections. Use for semantic search, hybrid search, keyword search, natural language queries with AI-generated answers, collection management, data exploration, filtered fetching, data imports from PDF/CSV/JSON/JSONL files, create example data and collection creation. --- # Weaviate Database Operations This skill provides comprehensive access to Weaviate vector databases including search operations, natural language queries, schema inspection, data exploration, filtered fetching, collection creation, and data imports. ### Weaviate Cloud Instance If the user does not have an instance yet, direct them to the cloud console to register and create a free sandbox. Create a Weaviate instance via [Weaviate Cloud](https://console.weaviate.cloud/signin?utm_source=github&utm_campaign=agent_skills). ## Environment Variables **Required:** - `WEAVIATE_URL` - Your Weaviate Cloud cluster URL - `WEAVIATE_API_KEY` - Your Weaviate API key **External Provider Keys (auto-detected):** Set only the keys your collections use, refer to [Environment Requirements](references/environment_requirements.md) for more information. ## Running Scripts Commands start from `SKILL_DIR`, the absolute path of the folder that contains this `SKILL.md`. Replace it before running, and run the command from the user's project so file arguments such as `data.csv` resolve against the project: ```bash uv run /path/to/skills/weaviate/scripts/list_collections.py ``` ## Script Index ### Search & Query - [Query Agent - Ask Mode](references/ask.md): Use when the user wants a **direct answer** to a question based on collection data. The Query Agent synthesizes information from one or more collections and returns a structured response with source citations (collection name and object ID). - [Query Agent - Search Mode](references/query_search.md): Use when the user wants to **explore or browse raw objects** across one or more collections. Unlike ask mode, this returns the actual data objects rather than a synthesized answer. - [Hybrid Search](references/hybrid_search.md): **Default choice for most searches.** Provides a good balance of semantic understanding and exact keyword matching. Use this when you are unsure which search type to pick. - [Semantic Search](references/semantic_search.md): Use for finding **conceptually similar content** regardless of exact wording. Best when the intent matters more than specific keywords. - [Keyword Search](references/keyword_search.md): Use for finding **exact terms, IDs, SKUs, or specific text patterns**. Best when precise keyword matching is needed rather than semantic similarity. ### Collection Management - [List Collections](references/list_collections.md): Use to **discover what collections exist** in the Weaviate instance. This should typically be the first step before performing any search or data operation. - [Get Collection Details](references/get_collection.md): Use to **understand a collection's schema** — its properties, data types, vectorizer configuration, replication factor, and multi-tenancy status. Helpful before running searches or imports.