Are you the author? Sign in to claim
Agent skill that teaches AI agents how to manage Zilliz Cloud vector databases through zilliz-cli
A skill that teaches AI agents how to operate Zilliz Cloud and Milvus vector databases through zilliz-cli. Instead of memorizing CLI commands, just describe what you want:
@codeguilds-knightzilliz/
├── SKILL.md # Main entry — prerequisites, workflows, safety rules
└── references/ # Domain-specific command references (loaded on demand)
├── setup.md # Install, auth, context, config, troubleshooting
├── cluster.md # Cluster create, list, describe, modify, suspend, delete; Vector Lake
├── on-demand-cluster.md # On-demand (Vector Lake) clusters with auto-suspend TTL
├── collection.md # Collection CRUD, aliases, load/release, per-collection metrics
├── external-collection.md # Refresh jobs for Vector Lake-backed external collections
├── vector.md # Search, query, insert, hybrid search, filter syntax
├── index.md # Index types, create/drop
├── database.md # Database CRUD (Dedicated clusters only)
├── partition.md # Partition management
├── user-role.md # RBAC: users, roles, privileges
├── backup.md # Backup/restore, policies
├── import.md # Bulk data import from cloud storage; import stages
├── billing.md # Usage, invoices, payment
├── monitoring.md # Status overview, collection stats, cluster and per-collection time-series metrics
├── project-region.md # Projects, volumes, cloud providers
├── privatelink.md # PrivateLink endpoint services, endpoints, whitelist
└── job.md # Async job tracking
| Area | What You Can Do |
|---|---|
| Clusters | Create, delete, suspend, resume, modify |
| Vector Lake | Create Vector Lake instances; provision, list, describe, and delete on-demand clusters with auto-suspend TTL |
| Collections | Create with custom schema, load, release, rename, drop |
| External Collections | Trigger / describe / list refresh jobs against Vector Lake-backed sources |
| Vectors | Search, query, insert, upsert, delete, hybrid search |
| Indexes | Create (AUTOINDEX), list, describe, drop |
| Databases | Create, list, describe, drop |
| Users & Roles | RBAC setup, privilege management |
| Backups | Create, restore, export, policy management |
| Import | Bulk data import from cloud storage; managed import stages |
| Jobs | Track async operations (backup, restore, migration, import, clone) |
| Partitions | Create, load, release, manage |
| Monitoring | Cluster status, collection stats, load states, cluster and per-collection time-series metrics |
| Billing | Usage, invoices, payment methods |
| Projects | Project and region management |
| PrivateLink | Endpoint services, project endpoints, whitelist management |
claude skill add ./zilliz.skill
Copy the zilliz/ directory into your skill path and ensure SKILL.md is discoverable by your agent.
zilliz-cli (the skill guides installation automatically)Extracted from the zilliz-plugin Claude Code plugin. The reference files correspond directly to the plugin's skills/ directory.
Apache License 2.0
@googleapis✓ OfficialGoogle's universal MCP server supporting PostgreSQL, MySQL, MongoDB, Redis, and 10+ databases
Official MongoDB integration — query collections, run aggregations, inspect schemas
@designcomputerSecure MCP server for MySQL database interaction, queries, and schema management
Run Claude Code as an MCP server so any agent can delegate coding tasks to it