Skills

A skill is a folder with a SKILL.md file. Agents see the skill’s name and description by default; when they decide the skill applies, they load its full instructions as context. Skills are how you ship reusable procedures — triage playbooks, report templates, incident response steps — without bloating every system prompt.

skills/
  incident-response/
    SKILL.md
    scripts/
      triage.py
    references/
      playbook.md

---
name: incident-response
description: Triage host compromise signals and summarize next actions.
allowed-tools: read_logs run_skill_script
license: MIT
---

Follow this process:

1. Identify the host and timeframe.
2. Run the triage script for baseline indicators.
3. Summarize findings and next actions.

The directory name and name in frontmatter must match.

Frontmatter fields

Field	Purpose
name	Unique within the capability; must match the directory name.
description	One-line summary shown when the agent lists available skills.
allowed-tools	Space-delimited or list form. Advisory — agents see it as guidance; the runtime does not enforce it.
license	Optional attribution.
metadata	Free-form map attached to the skill.

Note

allowed-tools is advisory in v1. The skill content includes it as an <allowed_tools> hint for the agent, but no permission gate stops a tool call that isn’t listed.

Ship skills in a capability

Declare them in the manifest:

skills:
  - skills/incident-response/
  - skills/report/

If skills: is omitted, the loader auto-discovers every subdirectory of skills/ that contains a SKILL.md. Set skills: [] to disable.

Reference skills from an agent

Agents opt in by name in frontmatter:

---
name: responder
description: Handle incident tickets from triage to summary.
model: anthropic/claude-sonnet-4-5-20250929
skills: [incident-response, report]
---

You are an incident responder. Use the listed skills when they apply.

Every skill listed is visible to the agent. Content only loads when the agent explicitly asks for it, keeping the system prompt small.