Skip to main content
A skill is a reusable, named set of instructions that Swan can follow — a written-down way of doing something, so you (or anyone in your org) don’t have to re-explain it every time. Skills show up in the dashboard under Skills (agent.getswan.com/skills), and Swan can also load and follow one during a conversation or a trigger run.

Three kinds of skills

  • Personal skills — visible only to you. When you create a skill (agent.getswan.com/skills/new) and mark it personal, it lives in your own space (shown in the UI as your personal skills workspace, filterable with ?scope=personal) and can only be used in your own conversations and personal triggers.
  • Org skills — shared across the whole organization. Any org member can see and use them; they’re the default kind unless you mark a skill personal (filterable with ?scope=org).
  • System skills — provided by Swan itself, shared across every organization. They’re read-only: you can’t edit or delete them, but Swan can load and follow them. System skills aren’t shown in the Skills page — they work in the background rather than as something you browse. New orgs also ship with a small set of default org skills (for example, a company-qualification skill) that you can see and edit like any other org skill.

Nesting

A skill can have sub-skills nested under it — useful for breaking a large playbook into sections (an overview skill with detailed sub-skills for specific scenarios). Sub-skills aren’t loaded automatically with the parent; Swan fetches them by name or ID when the parent skill’s instructions call for it.

Editing and permissions

Editing skills — creating, updating, or deleting any skill (personal or org) — is restricted to Admins by default. Members can view org and personal skills but can’t create or modify them unless an Admin grants that permission (see roles and permissions). Marking a skill “personal” controls who can see and use it, not who can edit it. Every edit to a skill’s instructions is versioned with a change summary, and past versions can be reviewed and restored from the skill’s page in the UI (https://agent.getswan.com/skills/{skillId}).

Skill vs. trigger vs. memory

These three get confused because they all shape agent behavior, but they answer different questions:
  • A skill is a reusable how-to — instructions for performing a task, invoked by name.
  • A trigger is an automation — a source (a schedule, a webhook, a CRM event) plus instructions plus toolkits, running unattended. A trigger’s instructions can reference a skill to reuse existing know-how instead of repeating it.
  • Memory is freeform facts, not instructions — notes Swan should remember, not steps it should follow.
If you find yourself repeating the same instructions across multiple triggers or conversations, that’s the signal to turn them into a skill instead. Swan applies the same principle itself: when it gets something working that took figuring out — like a direct API integration — it documents the working recipe as an org skill so later runs and teammates reuse it.

Common questions

Can I turn a personal skill into an org skill, or vice versa? Skill visibility is set when it’s created. Ask an Admin to recreate the content under the scope you need if you want to change it. Can members create their own personal skills? By default, creating and editing any skill — personal or org — requires Admin permissions. Ask your Admin to make the skill for you, or to grant your role skill-management permission. Are system skills something I need to manage? No — they’re maintained by Swan and applied automatically where relevant. You can’t edit or delete them. Can I reorder skills in the sidebar? No — skills are listed in creation order (newest first); there’s no manual sort or drag-and-drop ordering. How is a template different from a skill? A template is a ready-made play you install to create your own trigger or skill. Once installed, it becomes a normal org or personal skill/trigger that you can edit like any other. Does a skill know how well it’s performing? No — a skill can’t see its own usage or performance metrics while running. That data, where available, lives in analytics.