Query Writer
Data and analytics skill, available on Zeplik
Query Writer is a ready-to-run data and analytics skill on Zeplik. Write a SQL query from a plain-English description -- output columns, filters, joins and aggregations in the user's dialect, structured with CTEs and tuned for large tables. Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer. It returns a structured code you can keep and reuse: Language-tagged SQL block -- titled with purpose, complete and runnable, explicit columns and formatted clauses (see artifact-templates/code.md).
The Query Writer skill loads automatically when your request matches it, or you can invoke it directly by typing /write-query in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.
What the Query Writer skill can do
- Translate plain English requests into optimized SQL queries
- Apply dialect-specific syntax for Postgres, Snowflake, BigQuery, Redshift and more
- Discover schema and tables from a connected data warehouse
- Structure queries with readable CTEs and performance best practices
Try these prompts on Zeplik
Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.
How the Query Writer skill works
/write-query - Write Optimized SQL
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Write a SQL query from a natural language description, optimized for the user's dialect. Give them the query. Lead with the SQL in a fenced block, then a short note only on the parts that aren't self-evident. Don't append a standing explanation + performance-notes + modification-suggestions section to every answer — add those only when they actually matter for this query. Match the response to the ask: a simple aggregation is just the query and maybe one line; a gnarly performance-critical query earns the reasoning.
Figure out what they need from the description — output columns, filters, aggregations, joins, ordering, limits. If the dialect isn't known and it changes the syntax, ask (Postgres, Snowflake, BigQuery, Redshift, Databricks, MySQL, SQL Server, DuckDB, SQLite…); remember it for the session. If a warehouse MCP is connected, discover the real tables/columns and partition keys before writing, and offer to run it after.
Write it well by default:
- Structure: CTEs for multi-step logic, one per transformation, named descriptively (
active_users, nott1). - Performance: no
SELECT *in production; filter early; use partition filters; preferEXISTSoverINfor large subqueries; correct JOIN types; avoid correlated subqueries where a JOIN or window function works; watch exploding many-to-many joins. - Readability: explicit columns, each major clause on its own line, meaningful aliases, a comment only where the "why" isn't obvious.
- Dialect: use dialect-appropriate date/string/window syntax and performance features (Snowflake clustering, BigQuery partitioning); see the
sql-queriesskill for the syntax reference.
Tips worth surfacing to the user when relevant: mention the dialect and table names upfront for the right syntax immediately; say whether the query needs to be idempotent or parameterized for recurring date ranges.
How to use the Query Writer skill
Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Query Writer skill right away.
Describe your data and analytics task
Ask in plain language, or type /write-query to invoke the skill directly. Zeplik recognizes the Query Writer skill and applies its method.
Review and refine the result
Zeplik returns a structured code you can edit, download, and reuse. Ask follow-ups to refine it.
Source and credit
- Author
- Anthropic
- License
- Apache-2.0
Adapted from the open-source anthropics/knowledge-work-plugins project and tuned to run natively on Zeplik. View source on GitHub.
Frequently asked questions
- What is the Query Writer skill?
- Query Writer is a ready-to-run data and analytics skill on Zeplik. Write a SQL query from a plain-English description -- output columns, filters, joins and aggregations in the user's dialect, structured with CTEs and tuned for large tables. Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer. It returns a structured code you can keep and reuse: Language-tagged SQL block -- titled with purpose, complete and runnable, explicit columns and formatted clauses (see artifact-templates/code.md).
- How do I use Query Writer on Zeplik?
- Sign in to Zeplik and ask in plain language, or type /write-query in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
- Which AI model does the Query Writer skill use?
- Any model you choose. Zeplik works across every model in one chat, so the Query Writer skill runs on your preferred model for the task.
- Where does the Query Writer skill come from?
- The Query Writer skill is adapted from the open-source anthropics/knowledge-work-plugins project (Apache-2.0) and tuned to run natively on Zeplik. The original source is linked on this page.
- How much does the Query Writer skill cost?
- Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.
Related data and analytics skills
- Backtesting FrameworksBUILD or fix the backtest itself -- harness, point-in-time data plumbing, walk-forward machinery, cost and slippage models, train/test splits. To judge one already run, see backtest-expert.
- Chart & Visualization MakerCreate a publication-quality chart from query results, a DataFrame or a CSV using Python -- picks the right chart type for the data and applies clarity and accuracy best practices.
- ClickHouseClickHouse for high-performance analytics: query optimization, schema design, data engineering patterns
- CocoIndex ETLBuild CocoIndex ETL flows: embed docs to vector DBs, knowledge graphs, search indexes with incremental updates
- Dashboard BuilderBuild a self-contained interactive HTML dashboard -- KPI cards, multiple charts, tables and client-side filters in one browser-openable file, with no server or dependencies.
- Data & ML EngineeringUse when building data pipelines or ML infra -- Airflow DAGs, dbt models, Spark tuning, data quality checks, MLOps pipelines, recommenders. Not for one-off dataset analysis (use analyze-dataset).
More on Zeplik
Try Query Writer on Zeplik
Every model, one chat. Bring the Query Writer skill into your next conversation and let the assistant do the work.