SQL

Writes and runs read-only Redpanda SQL queries on Redpanda Cloud and manages which SQL users can read which topics. Use when a user wants to connect to Redpanda SQL with psql, a PostgreSQL driver, or SQL Studio, query topic-backed tables, create views, export results with COPY TO, grant or revoke access to topics or views, fix a user who lost SQL access, or check how Redpanda SQL differs from PostgreSQL. For enabling SQL, the SQL Manage and SQL Access roles, and the access model, see `/redpanda:sql-admin-api`. For catalogs, mapping topics with CREATE TABLE, and Iceberg-enabled topics, see `/re

9 stars 4 forksDatabases Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add redpanda-data/skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add redpanda-data/skills --skill sql
Manual install
git clone --depth 1 https://github.com/redpanda-data/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/sql ~/.claude/skills/sql

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Redpanda SQL

Redpanda SQL is the analytical SQL engine on Redpanda Cloud. It speaks the PostgreSQL wire
protocol and is read-only: topics are mapped to tables through a catalog, and data arrives by
producing to topics, never by `INSERT` or `COPY FROM`. Host, port, and credentials come from the
**SQL** tab of the cluster's **How to connect** panel; never invent them.

## How to work

**Find the table in its catalog before writing a query.** A topic-backed table is referenced as
`catalog=>table`, almost always `default_redpanda_catalog=>orders`. A bare `orders` or
`catalog.orders` fails, and the unqualified `SHOW TABLES` is an error. A view is the exception:
it lives in a schema, so query it by name with no catalog prefix. Start with:

```sql
SHOW REDPANDA TABLES default_redpanda_catalog;
DESCRIBE TABLE default_redpanda_catalog=>orders;
```

If the topic is not listed, it is not mapped yet; a *SQL: Manage* user maps it
(`/redpanda:sql-federated-queries`). Do not try to create a table with columns or load rows.

**Fix login access in Redpanda Cloud IAM, not with SQL.** When a user cannot connect, check
`SELECT has_database_privilege('<email>', current_database(), 'CONNECT');`. If it is false,
the user has no role with *SQL: Access* or *SQL: Manage*: tell the user to assign one under
**Organization IAM > Roles**. Do not run `GRANT CONNECT`, `CREATE USER`, `DROP USER`, or
`ALTER USER ... SUPERUSER` for an email-named user. The Cloud user sync owns `CONNECT` and
Read the full skill on GitHub

Details

Skill name
sql
Path
skills/sql/SKILL.md
License
Apache-2.0
Repo updated
16 November 2026

FAQ

What does the SQL skill do?

Writes and runs read-only Redpanda SQL queries on Redpanda Cloud and manages which SQL users can read which topics. Use when a user wants to connect to Redpanda SQL with psql, a PostgreSQL driver, or SQL Studio, query topic-backed tables, create views, export results with COPY TO, grant or revoke access to topics or views, fix a user who lost SQL access, or check how Redpanda SQL differs from PostgreSQL. For enabling SQL, the SQL Manage and SQL Access roles, and the access model, see `/redpanda:sql-admin-api`. For catalogs, mapping topics with CREATE TABLE, and Iceberg-enabled topics, see `/re

How do I install the SQL skill?

Claude Code plugin: /plugin marketplace add redpanda-data/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is SQL popular?

It lives in redpanda-data/skills, which has 9 GitHub stars and 4 forks.

Related skills

Adp

9

redpanda-data/skills

Redpanda's Agentic Data Plane: governance infrastructure for building, running, and governing AI agents and MCP servers behind a credential-injecting AI Gateway for LLM providers, operated through the `rpk ai` CLI and the ADP UI at ai.redpanda.com. Use when installing `rpk ai`, signing in to an environment, checking setup with `rpk ai doctor`, managing managed or self-managed AI agents and their triggers with `rpk ai agent` and `rpk ai trigger`, configuring remote or managed MCP servers with `rpk ai mcp-server` (including code mode and user-delegated OAuth), setting up LLM providers and models

AI, LLMs & Agents

Adp Governance

9

redpanda-data/skills

Govern what Agentic Data Plane agents may do, spend, and expose, through the `rpk ai` CLI and the ADP UI at ai.redpanda.com, and look up governance features in the Redpanda docs. Use when writing or debugging a Cedar access policy with `rpk ai policy`, giving a new agent access, capping agent spend with `rpk ai budget`, analyzing cost, attaching a guardrail to a provider, containing or releasing an agent with the kill switch, storing or deleting a credential with `rpk ai secret`, minting an API key, masking MCP tool data with data policies, or setting up inbound or outbound OAuth. For signing

AI, LLMs & Agents

Adp Observability

9

redpanda-data/skills

Read what Agentic Data Plane agents did and why, through traces, conversation transcripts, the audit log, and the monitoring views in the ADP UI at ai.redpanda.com and the `rpk ai` CLI. Use when finding which call made an agent run slow, failed, or expensive with `rpk ai trace`, reading or filtering a conversation with `rpk ai agent transcript`, finding conversations with a failed tool call, investigating a denied or masked call with `rpk ai auditlog`, working out on whose behalf an agent acted, or reading the Agent network or Home views. For budgets, cost, and access policies, see `/redpanda:

DevOps & Cloud

SQL Admin API

9

redpanda-data/skills

Administers Redpanda SQL on a Redpanda Cloud BYOC cluster: enabling, scaling, and disabling the SQL engine through the Cloud Console, the Cloud API, or the Terraform provider, finding connection details, and managing authentication and access. Use when a user wants to turn Redpanda SQL on or off, change its compute size or availability zone, set it up on a BYOVPC cluster, find the SQL endpoint, connect with an OIDC token or a SCRAM password, assign the SQL Manage or SQL Access roles, or understand how grants gate access to topics. For writing queries and GRANT syntax, see `/redpanda:sql`. For

Databases

Connect Cdc Tigerbeetle

9

redpanda-data/skills

Guides setup and operation of the tigerbeetle_cdc input in Redpanda Connect, which streams change data capture from a TigerBeetle financial transactions database into Redpanda or Kafka. Use when configuring tigerbeetle_cdc, connecting to a TigerBeetle cluster, choosing a persistent progress_cache for checkpointing, filtering settled vs pending transfers, routing by ledger, or resolving cgo-build or duplicate-event issues. Unlike the other CDC inputs, tigerbeetle_cdc is a certified community connector and does not require an Enterprise license, though it can still land data on Enterprise destin

Databases

SQL Debugging

9

redpanda-data/skills

Diagnoses Redpanda SQL problems on Redpanda Cloud from the SQL endpoint, and looks up the system tables, error causes, and recovery steps in the Redpanda docs. Use when a Redpanda SQL query is slow, stuck, or canceled for memory, when SHOW NODES reports a degradation error, when a topic-backed table returns decode errors or fewer rows than the topic holds, or when a query over an Iceberg-enabled topic returns stale history or fails to plan. For writing queries, see `/redpanda:sql`. For enabling, scaling, or disabling the SQL engine, see `/redpanda:sql-admin-api`. For catalogs and table mapping

Databases

Browse the most popular Claude skills, all databases skills, or write your own with the skills generator.