Skip to main content

​
What Are Skills?

Skills are reusable capability modules that agents can discover and run at runtime. Each Skill has a name, description, prompt instructions, and configured automation tools. Instead of wiring every automation into each agent manually, you build Skills once in the Skills Directory; agents then find and use them dynamically based on context.

​
Skills Directory

App admins create and manage Skills under Intelligence → Skills. Per-Skill configuration:
  • Name and Description – How the skill is identified and when it should be used
  • Prompt instructions – Instructions the agent follows when executing the skill
  • Automation tools – One or more automations (e.g., On-Demand) that implement the skill’s behavior
Lifecycle status:
StatusBehavior
DraftNot available to agents; use for work-in-progress
ActiveAvailable to agents when skills are enabled
DisabledTemporarily hidden from agents; can be re-enabled
Only active skills appear when agents search or use skills at runtime. Draft skills never appear in search.

​
Enabling Skills on an Agent

In Agent Configuration, the enabledSkills setting controls whether and how the agent can use Skills.
ModeBehavior
noneAgent has no Skills (default for new agents)
allAgent can discover and use all active Skills in the app
selectedAdmin picks specific skills from a checkbox table
In selected mode, use the checkbox table to choose exactly which Skills the agent can use. This gives fine-grained control when you have many Skills but want each agent to use only a subset.

​
Auto-Injected Tools

When Skills are enabled (any mode other than none), the agent automatically receives tools—no manual tool setup is required: You do not add these tools yourself; they appear whenever enabledSkills is not none.

​
Runtime Behavior

When an agent uses Skills, the flow is:
  1. Search – The agent calls skillSearch to find Skills relevant to the user’s request.
  2. Details – For a chosen Skill, the agent calls getSkillDetails to load name, description, instructions, and automation wiring.
  3. Execute – The agent runs the Skill’s behavior by invoking the underlying automation(s) via the Run Automation tool (e.g., runAutomation).

​
Testing Notes

  • Only active Skills surface at runtime; disabled Skills do not.
  • New agents default to none; enable Skills explicitly if you want the agent to use them.
  • After changing a Skill’s status or an agent’s enabledSkills, allow a moment for the agent to see the updated set.
  • Architecture – Agent platform, tools, and deployment; includes how Skills fit into the agent architecture.
  • Building Agents – Create and configure agents, including tools and channels.