← Back to Explorer

Skill

/skill
A named, self-contained capability that a human or agent can invoke on demand. The atomic unit of the {a}OS skill system. Always has a slash-command interface; never requires a long path command.
Strata: L2, L3 Axes: Execution, Orchestration Status: seed

Explainer

A skill is the agentic equivalent of a function or a CLI tool: it has a name, a defined input/output contract, and it does one thing well. In the {a}OS workspace, every skill lives in a canonical directory under 0.agentic/Skills/<name>/ with a SKILL.md that specifies its steps, model tier, constraints, and flags.

Skills are invoked — not scheduled, not automatically fired. A human types /sentinel or an orchestrating agent decides to call it as part of a larger plan. This is the key distinction from hooks (which fire on events) and cron jobs (which fire on time).

Rule: Every skill must have a /slash-command in .claude/commands/. Never give a user a long python path/to/script.py --flags command. The slash command is the interface.

Anatomy of a skill

Skill vs Workflow vs Hook

ConceptTriggerScopeExample
SkillManual or agentic (on demand)Single capability, one step or a few/sentinel, /humanizer, /close
WorkflowManual or agentic (on demand)Multi-step, chains skills and decisions/li-crucible, /acquire-skill
HookLifecycle event (automatic)Side effect at a runtime boundarySentinel on Stop, memory capture on PostToolUse

Anti-Patterns

Related Concepts