About k2
A documentation-focused skill for Cloudflare K2, a durable log that separates event producers from consumers. It directs agents to current documentation before advising on setup, APIs, limits, or pricing.
Key features
- 01Finds task-specific K2 documentation
- 02Prioritizes current docs over prior knowledge
- 03Flags unpublished pricing or availability details
- 04Points to Basin and Queues for related tasks
Use cases
- 01Looking up current stream setup steps
- 02Checking record delivery, retries, or retention
- 03Answering capacity or pricing questions
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/k2in Claude Code to confirm it loaded.
Details
From the project READMECloudflare K2
K2 is a durable log for decoupling event producers and consumers. Start with the K2 overview, then retrieve the relevant current documentation before giving setup instructions, code, limits, availability, permissions, or API details. The docs are the source of truth over this skill. While cloudflare-docs PR #33858 remains open, use its proposed pages if the public URLs have not been published.
Documentation
| Task | Docs | Check for |
|---|---|---|
| Create a stream and try K2 | Get started | Prerequisites, setup sequence, current API examples |
| Understand streams and subscriptions | Concepts | Record model and delivery behavior |
| Configure a stream | Configuration | Inputs, authentication, CORS, retention |
| Produce from HTTP or a Worker | Produce records | Request and binding syntax, encoding, errors, retries |
| Consume through subscriptions | Consume records | Leases, acknowledgements, retries, errors |
| Size a stream or consumer | Limits | Current quotas and size limits |
Retrieve the matching pages above for each task and use their current examples. For capacity or cost questions, check current limits and any published pricing before quoting values. State when a requested pricing or availability detail is not yet published.
For SQL transformation and delivery to R2 Iceberg tables, use the basin skill. For task processing, consult Queues.