Dune is a CLI for the leading blockchain data platform, allowing users to execute DuneSQL queries, discover datasets, and monitor credit usage. It's intended for developers and data analysts working with blockchain data.
$ npx skills add https://github.com/duneanalytics/skills --skill duneThe Dune skill enables AI agents to query blockchain data using DuneSQL through the Dune CLI. It allows developers and data analysts to discover datasets, execute queries, and monitor credit usage programmatically. The skill integrates with AI coding agents like Claude Code and Cursor, automating blockchain data analysis workflows. Users can search for datasets, run complex DuneSQL queries, and track resource consumption without manual platform navigation. This skill bridges AI agents and Dune's blockchain data infrastructure for streamlined data analysis.
Install using the command: `$ npx skills add https://github.com/duneanalytics/skills --skill dune`
Execute DuneSQL queries against on-chain data.
Discover datasets available on Dune.
Monitor credit usage for data queries.
$ npx skills add https://github.com/duneanalytics/skills --skill dunegit clone https://github.com/duneanalytics/skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Using the Dune CLI, execute the following DuneSQL query: `[QUERY]` on the [CHAIN] blockchain. Return the results in a structured format (CSV or JSON) and include execution time and credit usage. If the query fails, provide the error message and suggest optimizations to reduce credit consumption.
# Dune CLI Query Results **Query Executed:** `SELECT COUNT(*) as tx_count FROM ethereum.transactions WHERE block_time > NOW() - INTERVAL '7 days'` **Chain:** Ethereum **Execution Time:** 4.2 seconds **Credit Usage:** 12 credits ### Results: | tx_count | |----------| | 1,247,892 | --- **Note:** Query consumed 12 credits. For large datasets, consider adding `LIMIT` clauses or filtering by recent blocks to optimize performance.
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan