Agent Skills
| ID | skills |
| Category | Skills |
| Features | None |
| Dependencies | session_file_system |
Discover and activate skills from /.agents/skills/ in the session filesystem. Skills are portable instruction packages following the Agent Skills open specification.
list_skills
Section titled “list_skills”Scan /.agents/skills/ for available skills. Returns names and descriptions only (~100 tokens per skill).
activate_skill
Section titled “activate_skill”Load a skill’s full instructions by name.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | yes | Skill name (directory name under /.agents/skills/) |
Returns: full SKILL.md content and list of bundled files.
How It Works
Section titled “How It Works”Skills use progressive disclosure to keep context efficient:
- Discovery (~100 tokens) —
list_skillsreturns only names and descriptions - Activation (<5000 tokens) —
activate_skillloads the full SKILL.md instructions - Resources (on-demand) — bundled files accessible via File System tools
Workspace layout
Section titled “Workspace layout”/.agents/skills/ deploy/ SKILL.md templates/ k8s-deploy.yaml code-review/ SKILL.md- Skills are per-session (uploaded to session filesystem)
- Path traversal protection on skill names
- Invalid SKILL.md files are reported but don’t block discovery of other skills
- For organization-wide skills, see the Skills Registry
See Also
Section titled “See Also”- Agent Skills feature guide — detailed skills documentation
- Skills Registry — API-managed skills
- AGENTS.md — simpler alternative for project context
- File System — upload skill files
- Capabilities Overview