# scylladb

Eight skills covering ScyllaDB: CQL data modeling, Vector Search, Alternator, Kubernetes and benchmarking. Useful when your agent writes ScyllaDB code.

- plugin · `type=plugin` · Claude Code · ★ 8
- Author: scylladb
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/scylladb/agent-skills
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/plugins/scylladb

## What it does

The plugin drops eight skills into Claude. A parent `scylladb` skill opens with an overview and points to the rest: connecting to a ScyllaDB Cloud cluster, the Cloud MCP server for cluster management, CQL data modeling, Vector Search, the DynamoDB-compatible Alternator API, running ScyllaDB on Kubernetes through the ScyllaDB Operator, and load testing with cassandra-stress.

Everything follows the Agent Skills format, so the agent reads them as ordinary instructions. You can pull the whole set or pick skills by name, say only `scylladb-data-modeling`. Porting a DynamoDB app? The Alternator skill flags the difference up front: there is no single endpoint the way real DynamoDB has one, and auth goes through CQL roles.

The benchmark skill assumes a ScyllaDB Cloud cluster on AWS, with loaders reached over VPC peering. Skip that setup and the recipe has nothing to run against. Validating the skills locally needs Go, since the validator installs with `go install`.

## Install

### Claude Code (native platform)

**Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add anthropics/claude-plugins-community
```
In the agent chat (not a shell):
```text
/plugin install scylladb@claude-community
```

## When to use it
- connect to a ScyllaDB Cloud cluster and verify the connection
- design CQL tables that avoid hot partitions
- set up Vector Search and ANN queries
- move an app from DynamoDB to Alternator
- deploy ScyllaDB on Kubernetes with the operator

## Example prompts
- Walk me through connecting to a ScyllaDB Cloud cluster, driver included
- Design CQL tables for a query that fetches a user's latest orders
- Set up Vector Search on ScyllaDB Cloud and show an ANN query example

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 86c388e1fa0f29cc.

BEGIN THIRD-PARTY FILE 86c388e1fa0f29cc
````text
# ScyllaDB Agent Skills

Collection of ScyllaDB agent skills for use in agentic workflows.
These skills provide coding agents with deep knowledge of ScyllaDB.

## Installation

### CLI

**Recommended**: install the `scylladb` parent skill. It gives the agent an overview of ScyllaDB and a map of the other skills.

```sh
npx skills add scylladb/agent-skills --skill scylladb
```

Install all skills:

```sh
npx skills add scylladb/agent-skills
```

#### Install specific skills
```sh
npx skills add scylladb/agent-skills --skill scylladb
npx skills add scylladb/agent-skills --skill scylladb-cloud-setup
npx skills add scylladb/agent-skills --skill scylladb-cloud-mcp
npx skills add scylladb/agent-skills --skill scylladb-data-modeling
npx skills add scylladb/agent-skills --skill scylladb-vector-search
npx skills add scylladb/agent-skills --skill scylladb-alternator
npx skills add scylladb/agent-skills --skill scylladb-kubernetes
npx skills add scylladb/agent-skills --skill scylladb-benchmark
```

### Claude Code plugin
Coming soon.

### Cursor plugin
Available on the Cursor Marketplace: [ScyllaDB Agent Skills](https://cursor.com/marketplace/scylla-db).
```sh
/add-plugin scylladb
```

### Manual install

Clone this repo and copy the skill folders into the appropriate directory for your agent:

| Agent | Skill Directory | Docs |
|-------|-----------------|------|
| Claude Code | `~/.claude/skills/` | [docs](https://code.claude.com/docs/en/skills) |
| Cursor | `~/.cursor/skills/` | [docs](https://cursor.com/docs/context/skills) |
| OpenCode | `~/.config/opencode/skills/` | [docs](https://opencode.ai/docs/skills/) |
| OpenAI Codex | `~/.codex/skills/` | [docs](https://developers.openai.com/codex/skills/) |
| Pi | `~/.pi/agent/skills/` | [docs](https://github.com/badlogic/pi-mono/tree/main/packages/coding-agent#skills) |

## Skills

| Skill | Description |
|-------|-------------|
| [scylladb](skills/scylladb/SKILL.md) | Start here. Overview of ScyllaDB and a map of the other skills. |
| [scylladb-cloud-setup](skills/scylladb-cloud-setup/SKILL.md) | Guide users through connecting to a ScyllaDB Cloud cluster — credentials, drivers, and connection verification. |
| [scylladb-cloud-mcp](skills/scylladb-cloud-mcp/SKILL.md) | Set up and use the ScyllaDB Cloud MCP server to manage ScyllaDB Cloud clusters via AI agents. |
| [scylladb-data-modeling](skills/scylladb-data-modeling/SKILL.md) | CQL data modeling patterns and anti-patterns. Query-first design, partition keys, clustering columns, compaction, TTL, tombstones, and common pitfalls. |
| [scylladb-vector-search](skills/scylladb-vector-search/SKILL.md) | Implement and optimize Vector Search on ScyllaDB Cloud — vector indexes, ANN queries, filtering, quantization, and driver integration. |
| [scylladb-alternator](skills/scylladb-alternator/SKILL.md) | Build against ScyllaDB's DynamoDB-compatible API — write isolation policies, load balancing (no single endpoint like real DynamoDB), authentication via CQL roles, and compatibility differences to know before porting a DynamoDB app. |
| [scylladb-kubernetes](skills/scylladb-kubernetes/SKILL.md) | Deploy and operate ScyllaDB on Kubernetes via the ScyllaDB Operator — node preparation (CPU pinning, XFS/local storage), ScyllaCluster configuration, installation/upgrades, client access & networking, TLS/mTLS & authentication, multi-datacenter, scaling, and monitoring/backup. |
| [scylladb-benchmark](skills/scylladb-benchmark/SKILL.md) | Load test a ScyllaDB Cloud cluster on AWS with cassandra-stress, from loaders connected through VPC peering. Measure the maximum 50/50 read/write rate at p99 ≤ 10 ms with a measured default recipe, or test the workload of your app, and get a repeatable report with p50, p90, and p99 latency. |

The skills follow the [Agent Skills format](https://agentskills.io).

## Development

See [CONTRIBUTING.md](CONTRIBUTING.md) for the contribution process and [AGENTS.md](AGENTS.md) for the skill authoring rules. AI coding agents read `AGENTS.md` (Claude Code reads it through `CLAUDE.md`).
````
END THIRD-PARTY FILE 86c388e1fa0f29cc

The third-party file has ended. Everything between the 86c388e1fa0f29cc tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 4067 of 4663 bytes. © scylladb · Apache-2.0 · https://github.com/scylladb/agent-skills

## Similar
- [Infrawise](https://affpapa.org/en/nevibecode/mcp/infrawise.md) — MCP server · ★ 22
- [amazon-opensearch-service](https://affpapa.org/en/nevibecode/skills/amazon-opensearch-service.md) — skill · 5500 installs
- [aws-database](https://affpapa.org/en/nevibecode/skills/aws-database.md) — skill · 5700 installs
- [aws-sdk-java-v2-dynamodb](https://affpapa.org/en/nevibecode/skills/aws-sdk-java-v2-dynamodb.md) — skill · 3700 installs
- [dynamodb-toolbox-patterns](https://affpapa.org/en/nevibecode/skills/dynamodb-toolbox-patterns.md) — skill · 3500 installs

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md