Skip to main content
Skills are procedural playbooks (SKILL.md files) loaded by the agent to give it reusable, named instructions for a task. The Skills page lets you browse every skill registered in your workspace, upload new ones, and share an existing skill with more brains. Open it from the sidebar. Skills are scoped to brains (datasets) — a skill is attached to one or more brains, and the same skill can be copied into additional brains.

Browse skills

The page is a two-column browser:
  • Brains (left) — every brain that has at least one skill registered. Brains without skills are hidden. Select a brain to see its skills.
  • Skills (right) — the skills registered in the selected brain, grouped by their maintainer.
Use the search box to filter by skill name, maintainer, description, or tag. A green dot marks an active skill; a grey dot marks an inactive one.

Skill detail

Click a skill row to expand it. The detail view shows:
  • Description and metadata — maintainer (linked to its homepage or repository when a URL is provided), version, license, source repository, and the number of brains the skill is attached to.
  • Declared tools — the tools the skill is allowed to invoke.
  • Procedure — the full skill instruction body, fetched on demand when you expand the row.

Add a skill

Click Add skill (enabled once you have at least one brain) to open the upload dialog:
  1. Enter a name for the skill. The name is slugified into the ingestion path (for example, Weather lookup becomes weather-lookup/SKILL.md).
  2. Provide the content — either upload a .md file or paste the skill markdown directly.
  3. Select one or more brains to attach the skill to.
  4. Submit. The result is reported per brain, so you can see which datasets the skill was added to successfully.

Share a skill with more brains

Each skill row has a share control (“Add this skill to more brains”). It opens a dialog listing the brains the skill is not yet attached to. Select one or more destination brains to copy the skill into them; the outcome is reported per brain.
Skills are ingested through the same path as the content_type: "skills" option of the ingestion API — see Data Ingestion.