npx skills add https://github.com/weaviate/agent-skills --skill weaviate此技能提供对 Weaviate 向量数据库的全面访问,包括搜索操作、自然语言查询、模式检查、数据探索、过滤获取、集合创建和数据导入。
如果用户还没有实例,请引导他们到云控制台注册并创建一个免费的沙箱。通过 Weaviate Cloud 创建一个 Weaviate 实例。
必需:
WEAVIATE_URL - 您的 Weaviate Cloud 集群 URLWEAVIATE_API_KEY - 您的 Weaviate API 密钥外部提供商密钥(自动检测): 仅设置您的集合使用的密钥,更多信息请参考 环境要求。
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
首先列出集合,如果您不知道有哪些可用集合:
uv run scripts/list_collections.py
询问用户,如果没有可用数据且用户提出请求,他们是否希望创建示例数据。否则继续。
uv run scripts/example_data.py
获取集合详情以了解模式:
uv run scripts/get_collection.py --name "COLLECTION_NAME"
探索集合数据以查看值和统计信息:
uv run scripts/explore_collection.py "COLLECTION_NAME"
导入数据以填充新集合(如果需要):
uv run scripts/import.py "data.csv" --collection "CollectionName"
创建集合时不要指定向量化器,除非有明确要求:
uv run scripts/create_collection.py Article
--properties '[{"name": "title", "data_type": "text"}, {"name": "body", "data_type": "text"}]'
选择正确的搜索类型:
* 获取跨多个集合的、带有来源引用的 AI 驱动答案 → `ask.py`
* 从多个集合获取原始对象 → `query_search.py`
* 通用搜索 → `hybrid_search.py`(默认)
* 概念相似性 → `semantic_search.py`
* 精确术语/ID → `keyword_search.py`
所有脚本都支持:
--json 标志)常见错误:
WEAVIATE_URL not set → 设置环境变量Collection not found → 使用 list_collections.py 查看可用集合Authentication error → 检查 Weaviate 和向量化器提供商的 API 密钥每周安装数
97
代码仓库
GitHub 星标数
69
首次出现
2026年2月13日
安全审计
安装于
opencode94
gemini-cli93
codex93
github-copilot93
amp92
kimi-cli92
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.
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.
Required:
WEAVIATE_URL - Your Weaviate Cloud cluster URLWEAVIATE_API_KEY - Your Weaviate API keyExternal Provider Keys (auto-detected): Set only the keys your collections use, refer to Environment Requirements for more information.
text2vec_weaviate is used).Start by listing collections if you don't know what's available:
uv run scripts/list_collections.py
Ask the user if they want to create example data if nothing is available and the user requests it. Otherwise continue.
uv run scripts/example_data.py
Get collection details to understand the schema:
uv run scripts/get_collection.py --name "COLLECTION_NAME"
Explore collection data to see values and statistics:
uv run scripts/explore_collection.py "COLLECTION_NAME"
Import data to populate a new collection (if needed):
uv run scripts/import.py "data.csv" --collection "CollectionName"
Do not specify a vectorizer when creating collections unless requested:
All scripts support:
--json flag)Common errors:
WEAVIATE_URL not set → Set the environment variableCollection not found → Use list_collections.py to see available collectionsAuthentication error → Check API keys for both Weaviate and vectorizer providersWeekly Installs
97
Repository
GitHub Stars
69
First Seen
Feb 13, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode94
gemini-cli93
codex93
github-copilot93
amp92
kimi-cli92
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
49,000 周安装
uv run scripts/create_collection.py Article \
--properties '[{"name": "title", "data_type": "text"}, {"name": "body", "data_type": "text"}]'
Choose the right search type:
ask.pyquery_search.pyhybrid_search.py (default)semantic_search.pykeyword_search.py