> ## Documentation Index > Fetch the complete documentation index at: https://docs.kubiya.ai/llms.txt > Use this file to discover all available pages before exploring further. # Capabilities > Manage skills, models, and policies that define agent behavior and compliance Capabilities define what agents can do (skills), which AI models they use, and what security/compliance rules they must follow (policies). These resources work together to control agent behavior and ensure safe, compliant automation. ## Quick Start ```bash theme={null} # List skills kubiya skill list ``` **Output:** ``` 🛠️ Skills (15) NAME TYPE DESCRIPTION kubernetes-cli cli Kubernetes cluster management terraform cli Infrastructure as code aws-sdk sdk AWS cloud operations github-api api GitHub repository management docker-cli cli Container management slack-api api Slack notifications and messaging ``` ```bash theme={null} # Create skill kubiya skill create --file skill.yaml # List models kubiya model list ``` **Output:** ``` 🤖 Available Models (8) NAME PROVIDER CONTEXT DEFAULT gpt-4 openai 8K ✓ gpt-4-32k openai 32K claude-3-opus anthropic 200K claude-3-sonnet anthropic 200K claude-3-haiku anthropic 200K gpt-3.5-turbo openai 4K ``` ```bash theme={null} # Set default model kubiya model set-default gpt-4 # Create policy kubiya policy create --name "Production Policy" --file policy.rego ``` **Output:** ``` 🛠️ Creating policy... ✅ Policy created successfully! ID: abc123def456 Name: Production Policy Status: Enabled ``` ## Skills Agent capabilities including APIs, CLIs, cloud SDKs, and custom functions. Skills replace the V1 concepts of "sources" and "tools" with a unified system. ### List Skills ```bash theme={null} # List all skills kubiya skill list # JSON output kubiya skill list --output json ``` ### Get Skill Details ```bash theme={null} # View skill configuration kubiya skill get ``` ### Create Skill ```bash theme={null} # Create from file kubiya skill create --file skill.yaml ``` ```yaml theme={null} # skill.yaml name: kubernetes description: Kubernetes cluster management type: cli commands: - kubectl - helm ``` **Skill Types:** ```yaml theme={null} name: docker-cli description: Docker container management type: cli commands: - docker - docker-compose ``` ```yaml theme={null} name: github-api description: GitHub API interactions type: api base_url: https://api.github.com authentication: type: token header: Authorization ``` ```yaml theme={null} name: aws-sdk description: AWS SDK operations type: sdk provider: aws services: - s3 - ec2 - lambda ``` ```yaml theme={null} name: custom-validator description: Custom validation logic type: function runtime: python handler: validate_input ``` ### Update Skill ```bash theme={null} # Update skill configuration kubiya skill update --file skill.yaml ``` ### Delete Skill ```bash theme={null} # Delete skill kubiya skill delete ``` ### Validate Skill ```bash theme={null} # Validate skill definition kubiya skill validate skill.yaml ``` ## Models LLM models available to agents for task execution. ### List Models ```bash theme={null} # List all available models kubiya model list # JSON output kubiya model list --output json ``` **Available Models:** | Model | Provider | Use Case | Context Window | | --------------- | --------- | ------------------------ | -------------- | | gpt-4 | OpenAI | Complex tasks, reasoning | 8K tokens | | gpt-4-32k | OpenAI | Long context tasks | 32K tokens | | gpt-3.5-turbo | OpenAI | Fast, efficient tasks | 4K tokens | | claude-3-opus | Anthropic | Advanced reasoning | 200K tokens | | claude-3-sonnet | Anthropic | Balanced performance | 200K tokens | | claude-3-haiku | Anthropic | Fast responses | 200K tokens | ### Get Model Details ```bash theme={null} # View model configuration kubiya model get ``` ### Set Default Model ```bash theme={null} # Set organization default model kubiya model set-default ``` The default model is used when agents don't specify a particular model. You can override this per-agent in the agent configuration. ## Policies Security and compliance policies using Open Policy Agent (OPA). ### List Policies ```bash theme={null} # List all policies kubiya policy list # JSON output kubiya policy list --output json ``` ### Get Policy Details ```bash theme={null} # View policy configuration kubiya policy get ``` ### Create Policy ```bash theme={null} # Create from Rego file kubiya policy create --file policy.rego ``` ```rego theme={null} # policy.rego package kubiya.production # Deny deployments outside business hours deny["Production deployments only allowed during business hours"] { input.environment == "production" not is_business_hours } is_business_hours { hour := time.now_ns() / 1000000000 / 3600 % 24 hour >= 9 hour < 17 } ``` **Common Policy Examples:** ```rego theme={null} package kubiya.environment # Require approval for production deny["Production requires approval"] { input.environment == "production" not input.approved } ``` ```rego theme={null} package kubiya.resources # Limit resource consumption deny["Task exceeds resource limits"] { input.estimated_cost > 100 } ``` ```rego theme={null} package kubiya.skills # Require specific skills deny["Agent missing required skill"] { input.action == "deploy" not has_deployment_skill } has_deployment_skill { input.agent.skills[_] == "kubernetes" } ``` ```rego theme={null} package kubiya.schedule # Maintenance window enforcement deny["Maintenance only allowed on weekends"] { input.action == "maintenance" not is_weekend } is_weekend { day := time.weekday(time.now_ns()) day == "Saturday" } is_weekend { day := time.weekday(time.now_ns()) day == "Sunday" } ``` ### Update Policy ```bash theme={null} # Update policy kubiya policy update --file policy.rego ``` ### Delete Policy ```bash theme={null} # Delete policy kubiya policy delete ``` ### Validate Policy ```bash theme={null} # Validate Rego syntax kubiya policy validate policy.rego ``` ## Best Practices * Organize skills by domain (aws-*, kubernetes-*, github-\*) * Reuse shared skills instead of duplicating * Add clear descriptions and examples to all skills * Version control skill and policy definitions * Test skills and policies before production use * Use GPT-4 for complex reasoning, GPT-3.5 for simple tasks * Monitor model usage and costs per agent * Start with permissive policies, enforce gradually * Document policy intent with clear comments * Only grant skills agents actually need * Rotate credentials regularly ## Command Reference ```bash theme={null} # Skills kubiya skill list kubiya skill get kubiya skill create --file skill.yaml kubiya skill update --file skill.yaml kubiya skill delete kubiya skill validate skill.yaml # Models kubiya model list kubiya model get kubiya model set-default # Policies kubiya policy list kubiya policy get kubiya policy create --file policy.rego kubiya policy update --file policy.rego kubiya policy delete kubiya policy validate policy.rego ``` ## Next Steps Apply capabilities to agents and teams Execute tasks with configured capabilities Configure environments with policies Execute tasks with automatic planning