Skill Config
Skill Configuration
Configure skills with parameters, environment variables, and SWAIG field overrides. Understand the parameter schema and discovery options.
Configuration Methods
Parameter Dictionary
Pass configuration when adding a skill:
Parameter Schema
Skills define their parameters via get_parameter_schema():
Parameter Properties
Environment Variables
Skills can read from environment variables:
SWAIG Fields
Override SWAIG function metadata for skill tools:
Available SWAIG fields:
External Skill Directories
Register custom skill directories:
Entry Points
Install skills via pip packages:
Listing Available Skills
Multi-Instance Configuration
Skills supporting multiple instances need unique tool names:
Configuration Validation
Skills validate configuration in setup():

Complete Configuration Example
Configuration Best Practices
Security
- Store API keys in environment variables
- Never commit secrets to version control
- Use hidden: true for sensitive parameters
Organization
- Group related configuration
- Use descriptive tool_name for multi-instance
- Document required configuration
Validation
- Check has_skill() before using conditionally
- Handle ValueError from add_skill()
- Validate parameters early in setup()
Next Steps
You’ve learned the complete skills system. Next, explore advanced topics like contexts, workflows, and state management.