AgentSkillsCN

connector-skill

连接数据源，探索数据模式，编写查询语句，并对数据质量进行画像分析。当用户希望查询数据库、探索数据源、剖析数据表，或深入理解自身的数据架构时，即可使用此技能。该技能兼容多种 SQL 方言、基于 API 的数据源，以及文件型数据源，并内置查询优化与结果校验的常用模式。

SKILL.md
--- frontmatter
name: connector-skill
description: >
  Connect to data sources, explore schemas, write queries, and profile data quality.
  Use when the user wants to query a database, explore a data source, profile tables,
  or understand their data schema. Handles SQL dialects, API-based data sources,
  and file-based data. Includes query optimization and result validation patterns.

Data Connector Skill

Query Patterns

SQL-based Sources

Write dialect-appropriate SQL. Check schema first, validate results after.

API-based Sources

Use MCP tools to query. Handle pagination and rate limits.

File-based Sources

Read CSV/Excel/JSON files and analyze with pandas or similar.

Validation Checklist

  • •Row count sanity
  • •Null check
  • •Value range check
  • •Aggregation logic

Trace Awareness

When previous TRACE.md or FILTER.md files exist for this data source:

  1. •Read the Attention Log — know what schema areas were already explored
  2. •Read the Confidence Map — know where schema understanding is weak
  3. •Read the Surplus Value — know what data patterns emerged last time
  4. •Read the Filter — skip known-noise areas, prioritize signal areas

References

  • •See references/schema-guide.md for schema exploration patterns