Zilliz Skill

Manage Zilliz Cloud vector databases via zilliz-cli. Use when the user wants to: (1) set up zilliz-cli (install, login, configure), (2) manage clusters (crea...

Security Scan

The skill is an instruction-only guide for operating Zilliz Cloud via the official zilliz-cli; its requirements, instructions, and scope are internally consistent with that purpose.

Purpose & Capability

Name and description match the actual content: this is documentation/instructions for using zilliz-cli to manage Zilliz Cloud resources. It does not request unrelated credentials, binaries, or system paths.

Instruction Scope

All runtime actions are shell-based zilliz-cli commands and prerequisite checks (install, auth, context). The skill explicitly forbids running interactive auth commands in non-interactive shells and forbids asking for API keys in chat. Because the skill is written as an agent-executable checklist, it grants broad permission to run CLI commands when the platform executes skills — this is coherent with the purpose but you should be aware it could run pip/zilliz-cli commands if the agent is allowed to execute shell commands.

Install Mechanism

No install spec is embedded in the skill bundle (instruction-only). It recommends using 'python3 -m pip install --upgrade zilliz-cli', a standard package install from PyPI — appropriate and proportionate for a CLI skill.

Credentials

The skill declares no required environment variables or secrets. It documents optional modes (API key via ZILLIZ_API_KEY or interactive OAuth) and explicitly instructs users to perform credential entry in their own terminal, which is proportionate to its functionality.

Persistence & Privilege

The skill is not always-enabled, does not request elevated persistence, and does not attempt to modify other skills or system-wide settings. Autonomous invocation is allowed by default but is typical for skills and not by itself a concern here.

Assessment

This skill is an instruction-only helper for the official zilliz-cli and appears coherent. Before installing/using it: (1) confirm whether your agent platform is permitted to run shell commands — the skill expects to run zilliz and pip commands; (2) never paste API keys or credentials into chat — perform interactive logins (zilliz login/configure) in your own terminal as the skill advises; (3) be comfortable with installing a PyPI package (zilliz-cli) if you follow its install steps; (4) if you want to restrict the agent from running commands on your machine, do not grant shell execution permissions to skills. Overall the bundle matches its stated purpose and has no unexplained requests, so it is coherent to install if you trust the zilliz-cli workflow.

Zilliz Cloud CLI Skill

Operate Zilliz Cloud through zilliz-cli. All operations are executed via shell commands.

Prerequisite Check (always run first)

Before any operation, verify in order:

python3 -m pip show zilliz-cli    # 1. CLI installed? If not: pip install --upgrade zilliz-cli
zilliz auth status                 # 2. Logged in? If not: guide user to login in their terminal
zilliz context current             # 3. Context set? (only for data-plane ops)

CRITICAL: zilliz login, zilliz configure, and zilliz auth switch require interactive input — NEVER run them in a non-interactive shell. Instruct the user to run in their own terminal. NEVER ask for API keys in chat.

Command Pattern

zilliz <resource> <action> --flag <value> [--optional-flag <value>]

All commands support --output json|table|text (default: text). Use --output json for programmatic parsing.

Cluster Type Capabilities

Feature	Free	Serverless	Dedicated
Collection CRUD & Vector ops	Yes	Yes	Yes
Database create/drop	No	No	Yes
User/role management	No	Limited	Yes
Backup management	No	Yes	Yes
Cluster modify (CU/replica)	No	No	Yes

Check cluster type first when a command fails with permission errors.

Reference Files

Each reference covers one resource domain with full command syntax, options, and guidance. Read the relevant reference when handling that domain:

Domain	Reference	When to read
Setup & auth	references/setup.md	Install, login, context, config, troubleshooting
Clusters	references/cluster.md	Create, list, describe, modify, suspend, resume, delete clusters
Collections	references/collection.md	Create, list, describe, drop, rename, load, release, aliases
Vectors	references/vector.md	Search, query, insert, upsert, get, delete, hybrid search, filters
Indexes	references/index.md	Create, list, describe, drop indexes
Databases	references/database.md	Create, list, describe, drop databases
Partitions	references/partition.md	Create, list, load, release, drop partitions
Users & roles	references/user-role.md	RBAC: users, roles, privileges (Dedicated only)
Backups	references/backup.md	Create, restore, export backups; manage backup policies
Import	references/import.md	Bulk data import from cloud storage
Billing	references/billing.md	Usage queries, invoices, payment methods
Monitoring	references/monitoring.md	Cluster status, collection stats, load states
Projects & regions	references/project-region.md	Projects, volumes, cloud providers, regions

Quick-Start Workflow

For new users, guide through setup in order:

1. Install CLI: python3 -m pip install --upgrade zilliz-cli
2. Authenticate: user runs zilliz login in their terminal
3. Verify: zilliz auth status
4. List clusters: zilliz cluster list
5. Set context: zilliz context set --cluster-id <id>
6. Verify: zilliz context current && zilliz collection list

Common Workflows

Create collection and prepare for search:

1. zilliz collection create --name <name> --dimension <dim> — create
2. zilliz index create --collection <name> — index (AUTOINDEX recommended)
3. zilliz collection load --name <name> — load into memory
4. zilliz vector search --collection <name> --data '[[...]]' — search

Status overview (read references/monitoring.md):

1. zilliz context current --output json
2. zilliz cluster describe --cluster-id <id> --output json
3. zilliz database list --output json
4. For each DB: collection list, get-stats, get-load-state, index list
5. Present as formatted table

Async Operations

These return immediately; poll for completion:

Operation	Poll command
cluster create	cluster describe --cluster-id <id> until RUNNING
backup create/export/restore-*	backup describe --cluster-id <id> --backup-id <bid>
import start	import status --job-id <jid> --cluster-id <id>

Safety Rules

• Confirm before destructive ops: drop collection/database, delete cluster/backup, drop user/role
• Sensitive commands in user's terminal: zilliz login, zilliz configure, zilliz billing bind-card
• Never expose credentials in chat or command output