Skip to content

Agent Skills

Agent Skills are portable instruction packages following the Agent Skills open specification. They keep the agent’s context efficient through progressive disclosure: the agent sees only short names and descriptions until it activates a skill, at which point the full instructions and bundled resources load.

Overview video

Three-stage disclosure

  1. Discovery (~100 tokens per skill) — names and descriptions appear in the system prompt under <available_skills>.
  2. Activation (under 5,000 tokens) — full SKILL.md instructions load when the agent calls activate_skill.
  3. Resources — bundled files mount at /skills/{name}/ and are read with the normal filesystem tools.

This keeps thousands of skills available to an agent without burning context on the ones it doesn’t need.

Two ways to use skills

SourceWhere they liveWhen to use
Workspace skills/.agents/skills/ in the session VFSProject-specific skills; per-session experimentation
Registry skillsOrganization-wide via the Skills RegistryShared across agents; managed via API

The built-in skills capability handles workspace discovery. Registry skills appear in the capability system as virtual capabilities (skill:{uuid}).

Do something

See also