Generate validated analytics SQL with SQLCoder
Use SQLCoder when an analytics agent needs to turn natural-language questions plus schema context into SQL drafts that can be reviewed, validated, and run inside a controlled data workflow.
npx skills add agentskillexchange/skills --skill generate-validated-analytics-sql-with-sqlcoder
Tool: SQLCoder. This skill is for analytics agents that need a repeatable text-to-SQL step grounded in known schema metadata, not a generic chat prompt that guesses at database structure. SQLCoder provides model weights, installation paths, a CLI launch flow, and sample inference code for converting natural-language questions into SQL queries.
What this skill actually does
When to use it: invoke this when an agent must answer business or product analytics questions by drafting SQL against a known warehouse or database schema, then validating the query before execution. It is useful when the operator wants local or self-hosted SQL generation, reproducible model behavior, and reviewable SQL artifacts before results are returned to a user.
Scope boundary: this is not a general database client, BI dashboard, SQL formatter, or broad LLM framework listing. The boundary is narrow: connect schema context, generate candidate SQL with SQLCoder, validate or edit the query, then run it through the agent’s approved database access path.