Skip to main content
Skills Dashboard Skills are the building blocks of agent capabilities in Kubiya. They define what actions your agents can perform—from reading files and executing shell commands to managing Docker containers and orchestrating multi-agent workflows.

Built-in Skills

Ready-to-use capabilities for common operations

Security First

Variants for different permission levels

Fully Extensible

Create custom Skills for your needs

​
Why Skills Matter

Skills define what agents can do with precise control over permissions. An agent with “Shell - Safe Commands” can only run approved diagnostic commands, while “Shell - Full Access” enables any command execution.
Built-in security variants follow the principle of least privilege. Start with read-only or safe variants, then expand permissions only as needed. Sandboxed environments provide additional isolation.
Create custom Skills to integrate with proprietary APIs, services, and tools. Skills make your organization’s unique capabilities available to agents.

​
Get Started

1

Choose a Skill Type

Select from built-in Skills or create a custom one:
  • File System - Read, write, and manage files
  • Shell - Execute commands with configurable restrictions
  • Python - Run Python code with import controls
  • Docker - Manage containers, images, and networks
  • Agent Communication - Enable multi-agent orchestration
  • And more…

View All Built-in Skills

Explore the complete reference with use cases and configuration options
2

Select a Variant

Pick a pre-configured security level:
Minimal permissions for monitoring and observation
  • No write or destructive actions
  • Perfect for audit and compliance
  • Example: Read-only file access for log monitoring

Learn About Variants

Understand how to choose the right variant for your use case
3

Create & Assign

Create a Skill instance and attach it to agents or teams:
# Create a skill with a specific variant
kubiya skill create \
  --name "Production Shell" \
  --type shell \
  --variant safe_commands \
  --enabled

# Assign to an agent
kubiya skill associate agent <agent-id> <skill-id>

CLI Reference

Complete command documentation

View Examples

Real-world configurations

​
Explore Skills

Skills Overview

Comprehensive guide to understanding and managing SkillsLearn about the Skills lifecycle, UI workflow, best practices, and troubleshooting

Built-in Skills Reference

Complete catalog of all built-in SkillsFile System, Shell, Python, Docker, Workflows, Agent Communication, and more

Skill Variants Guide

Master security variants and skill instancesLearn how to create properly configured instances following least privilege

Custom Skills

Extend Kubiya with custom capabilitiesStep-by-step guide to creating Skills with .kubiya/skills directory

CLI Reference

Command-line tools for Skills managementCreate, list, update, delete, and associate Skills programmatically

Real-World Examples

Practical configurations and patternsProduction deployments, monitoring agents, sandbox environments, and more

​
Common Use Cases

Production Deployment

Skills: Shell (Safe Commands), File System (Full Access), Docker (Full Control)Enable controlled deployments with restricted command execution

Monitoring & Observability

Skills: File System (Read Only), Shell (Read Only), Data VisualizationObserve systems without risk of accidental changes

Development Sandbox

Skills: File System (Sandboxed), Shell (Full Access), Python (Full Access)Give developers freedom to experiment in isolated environments

Multi-Agent Orchestration

Skills: Agent Communication (Limited), Workflow ExecutorCoordinate complex workflows across specialist agents

Custom Integrations

Skills: Custom Skills (Slack, GitHub, JIRA, etc.)Connect agents to your organization’s tools and APIs

Audit & Compliance

Skills: All Skills (Read Only variants)Ensure agents can observe but never modify critical systems

​
Best Practices

Security First: Always start with the most restrictive variant that meets your needs. You can upgrade permissions later if required.

Principle of Least Privilege

Only grant the minimum permissions required for the task

Use Pre-configured Variants

Leverage built-in templates instead of custom configurations

Test in Development First

Validate Skill configurations before deploying to production

Document Custom Skills

Include clear descriptions and usage instructions

Overview

Built-in Skills

Variants

Custom Skills

CLI

Examples

Agents

Teams