query-writing

作者: langchain-ai

Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database,…

npx skills add https://github.com/langchain-ai/deepagents --skill query-writing

Query Writing Skill

Workflow for Simple Queries

For straightforward questions about a single table:

  1. Identify the table - Which table has the data?
  2. Get the schema - Use sql_db_schema to see columns
  3. Write the query - SELECT relevant columns with WHERE/LIMIT/ORDER BY
  4. Execute - Run with sql_db_query
  5. Format answer - Present results clearly

Workflow for Complex Queries

For questions requiring multiple tables:

1. Plan Your Approach

Use write_todos to break down the task:

  • Identify all tables needed
  • Map relationships (foreign keys)
  • Plan JOIN structure
  • Determine aggregations

2. Examine Schemas

Use sql_db_schema for EACH table to find join columns and needed fields.

3. Construct Query

  • SELECT - Columns and aggregates
  • FROM/JOIN - Connect tables on FK = PK
  • WHERE - Filters before aggregation
  • GROUP BY - All non-aggregate columns
  • ORDER BY - Sort meaningfully
  • LIMIT - Default 5 rows

4. Validate and Execute

Check all JOINs have conditions, GROUP BY is correct, then run query.

Example: Revenue by Country

SELECT
    c.Country,
    ROUND(SUM(i.Total), 2) as TotalRevenue
FROM Invoice i
INNER JOIN Customer c ON i.CustomerId = c.CustomerId
GROUP BY c.Country
ORDER BY TotalRevenue DESC
LIMIT 5;

Error Recovery

If a query fails or returns unexpected results:

  1. Empty results — Verify column names and WHERE conditions against the schema; check for case sensitivity or NULL values
  2. Syntax error — Re-examine JOINs, GROUP BY completeness, and alias references
  3. Timeout — Add stricter WHERE filters or LIMIT to reduce result set, then refine

Quality Guidelines

  • Query only relevant columns (not SELECT *)
  • Always apply LIMIT (5 default)
  • Use table aliases for clarity
  • For complex queries: use write_todos to plan
  • Never use DML statements (INSERT, UPDATE, DELETE, DROP)

来自 langchain-ai 的更多技能

langgraph-docs
langchain-ai
访问LangGraph文档,构建有状态代理和多代理工作流。获取官方LangGraph Python文档,涵盖状态机、基于图的代理设计以及人机协同模式。根据查询类型优先提供相关文档:实现指南解答操作问题,概念页面讲解理论,教程提供端到端示例,API参考提供技术细节。自动选择2–4个最相关的文档URL并检索其内容以回答...
official
langgraph-human-in-the-loop
langchain-ai
暂停图执行以进行人工审查、批准或验证,随后根据其输入恢复执行。需要三个组件:检查点存储器(InMemorySaver 或 PostgresSaver)、配置中的线程 ID 以及 JSON 可序列化的中断负载。interrupt(value) 暂停执行并展示数据;Command(resume=value) 恢复执行并将该值返回给暂停的节点。恢复时,interrupt() 之前的所有代码会重新执行,因此副作用必须具有幂等性(使用 upsert 而非 insert)。支持审批工作流,...
official
web-research
langchain-ai
用于处理与网络研究相关的请求;它提供了一种结构化的方法来进行全面的网络研究
official
langchain-oss-primer
langchain-ai
任何LangChain、Deep Agents或LangGraph代理构建项目都请始终从这里开始。在选择其他技能或编写任何内容之前,这是必需的起点。
official
skill-creator
langchain-ai
创建有效技能的指南,通过专业知识、工作流程或工具集成来扩展代理能力。当用户……时使用此技能。
official
social-media
langchain-ai
根据研究内容起草特定平台的社交媒体帖子,并生成配套图片。支持领英帖子(1300字符,专业语气)和推特/X话题(每条推文280字符,采用1/🧵格式)。需在撰写前将研究任务委托给子代理,随后阅读研究结果以确保准确性和相关性。使用generate_social_image工具自动生成引人注目的社交图片,采用粗体高对比度构图,针对小屏幕进行优化...
official
deep-agents-memory
langchain-ai
为Deep Agents提供可插拔的内存与文件后端,支持临时、持久化和混合路由选项。四种后端类型:StateBackend(线程作用域,临时)、StoreBackend(跨会话持久化)、FilesystemBackend(本地开发时真实磁盘访问)和CompositeBackend(将不同路径路由到不同后端)。FilesystemMiddleware提供六种文件操作工具:ls、read_file、write_file、edit_file、glob、grep。CompositeBackend使用最长前缀匹配进行路由...
official
deep-agents-orchestration
langchain-ai
编排子代理,规划多步骤任务,并对敏感操作要求人工审批。通过任务工具将工作委派给专业子代理;自定义子代理支持独立的工具集和系统提示,而默认的“通用”子代理继承主代理配置。使用write_todos规划并跟踪复杂工作流,将任务组织为待处理、进行中和已完成状态;需要thread_id以实现跨调用的持久化。实现...
official