CloudflareInstall Basin
Pick your agent. Every command is ready to paste.
npx skills add cloudflare/skills --skill basinThe open skills CLI detects your agents (Claude Code, Cursor, Codex and 70+ more) and installs to the right folder. Add -g to install globally.
01
Install it
Run the command above, or upload the folder in Claude.
02
Ask naturally
Describe the task. Your agent loads basin when the request matches its description.
03
Name it if needed
If it does not trigger, say “use the basin skill”. In Codex, type $basin.
The skill itself
SKILL.md
Cloudflare Basin
Basin ingests and transforms events, manages Apache Iceberg tables in R2, and queries them with distributed SQL. Start with the Basin overview and retrieve the relevant current docs before implementing changes, especially for limits, pricing, permissions, and CLI syntax. While PR #33850 remains open, use the proposed pages in that PR if the new URLs have not been published.
Rebrand
Cloudflare Data Platform is now Basin. Cloudflare Pipelines, R2 Data Catalog, and R2 SQL are now Basin Pipelines, Basin Catalog, and Basin SQL. Existing resources and configurations continue to work. The prior Wrangler command families also continue to work: wrangler pipelines, wrangler r2 bucket catalog, and wrangler r2 sql. Use the new Basin commands and documentation URLs in new guidance. Legacy API identifiers and metrics names may still use the old terms; check the current docs for deprecation details. The migration is documented in cloudflare-docs PR #33850.
Choose the workflow
| Need | Product | Reference | Current docs |
|---|---|---|---|
| Receive events, transform rows, and deliver to R2 | Basin Pipelines | Pipelines guide | Basin Pipelines |
| Manage Iceberg metadata, table maintenance, and engine access | Basin Catalog | Catalog guide | Basin Catalog |
| Query Iceberg tables with analytical SQL | Basin SQL | SQL guide | Basin SQL |
Typical flow: Basin Pipelines → Basin Catalog tables in R2 → Basin SQL or a compatible external engine. Begin with the Basin getting started guide for an end-to-end setup.
The proposed Wrangler command families are wrangler basin pipelines, wrangler basin catalog, and wrangler basin sql. Basin SQL uses WRANGLER_BASIN_SQL_AUTH_TOKEN; its REST query path is /basin-sql/query/{BUCKET}. Check the installed Wrangler version and current reference pages before running commands because the migration is ongoing.
Skill feedback
If the user reports that this skill gave incorrect or outdated guidance, or is missing information, read references/skill-feedback.md.
Tips for Basin
- • Start a fresh session after installing so your agent picks up the new skill.
- • It bundles reference files. The agent reads them only when needed, so they cost no context until then.
- • It is part of a pack with 22 skills. Install only the ones you need with --skill to keep triggers precise.
- • If two skills overlap, mention the one you want by name.
Questions about Basin
What does the Basin skill do?
Build and troubleshoot Cloudflare Basin analytics workflows with Basin Pipelines, Basin Catalog, and Basin SQL. Use for streaming data into R2 Iceberg tables, managing catalogs, or querying those tables; also use for requests using the former Data Platform, Pipelines, R2 Data Catalog, or R2 SQL names.
How do I install Basin?
Run "npx skills add cloudflare/skills --skill basin" in your project. The skills CLI installs it for Claude Code, Cursor, Codex and 70+ other agents. In Claude on the web, upload the skill folder as a ZIP under Customize > Skills.
Does Basin work in Cursor and Codex?
Yes. Basin uses the open SKILL.md format, so it works in Claude Code, Claude, Cursor, OpenAI Codex, Gemini CLI, GitHub Copilot and other agents that support agent skills.
Is Basin free?
Basin is open source on GitHub under the Apache-2.0 license. It is free to install; check the license before commercial use.
Who made Basin?
Basin is published by Cloudflare in the cloudflare/skills repository, together with 21 other skills.
