Skills define what an agent can do at runtime. While knowledge gives the agent information to reference, skills allow it to take actions — such as calling APIs, executing code, querying databases, interacting with external systems, or invoking other agents.
This flow allows you to attach new capabilities to an agent directly from the Builder Canvas through the Add Skill to Agent workflow.
Different skill types are designed for different runtime actions. Before adding a skill, identify the type of capability your agent needs.
Call external APIs or services
API Call
Execute backend business logic
Python Code or JavaScript Code
Query structured databases using natural language
Structured Data Query
Connect to external MCP tools or systems
MCP Server
Reuse another agent as part of a workflow
Agents
Use internally created reusable capabilities
Custom Skills
If you are unsure where to begin, start with the Skill Library tab.
From the Builder Canvas, click + Add Skill in the Skills section below the agent node.
This opens the Add Skill to Agent dialog.
The dialog is organized into multiple tabs to help you discover skills from different sources.
All
Displays all available skills across sources
Skill Library
Platform-provided skills maintained by Uptiq
Custom Skills
Skills created within your workspace
Uptiq MCP Marketplace
Curated MCP-based integrations and tools
Agents
Existing agents that can be reused as sub-agents
MCP Marketplace
External third-party MCP integrations
Switching tabs automatically filters the available skill list.
Use the Search Skills field to quickly filter skills by name or capability.
Search results are scoped to the currently selected tab.
Click a skill to open its configuration form.
Each skill card includes:
Skill name
Capability summary
Skill type
Author or provider attribution
The configuration experience varies depending on the selected skill type.
Configure the selected skill based on its runtime requirements.
Examples:
API Call
Endpoint, headers, authentication, request body
Python / JavaScript
Runtime logic and execution code
Structured Data Query
Database connection and schema mapping
MCP Server
Server URL, credentials, tool access
Agent
Agent selection and invocation configuration
Secrets and variables can be referenced dynamically using:
$secret.{name}
$agent.{name}
This enables reusable and secure runtime configuration.
Once saved, the skill becomes available to the agent during runtime execution.
The agent planner can now decide when to invoke the skill based on the incoming user request and the agent instructions.
The Builder Canvas and Manage Agent views are also updated to reflect the newly attached capability.
Possible causes:
The agent instructions do not describe when the skill should be used
The skill description is too generic or unclear
Another skill is being prioritized by the planner
Improving the skill description and refining agent instructions usually resolves this.
Check:
Authentication and credentials
Endpoint configuration
MCP server availability
Runtime syntax or dependency errors
Use Monitoring and execution traces to inspect failures in detail.
Try switching to the All tab to search across every source.
If the capability does not exist yet, create it through Custom Skills or connect it via MCP integrations.
Skills are the operational layer of the agent runtime.
Without skills, agents can only generate responses. With skills, agents can execute workflows, retrieve live data, interact with systems, automate tasks, and orchestrate multi-step business actions.
The most effective agents combine:
Strong knowledge sources
Well-defined instructions
Carefully selected runtime skills
This combination enables agents to move beyond conversational responses into real operational execution.
Last updated
