Skip to content

Skills

S1 · Philosophy ✓ Stable 2026-04-18

Skills are loaded INTO an agent’s context at invocation time. Unlike agents (which spawn as separate contexts), skills are passive expertise — Claude reads each skill’s description field and decides autonomously when to apply it.

See skills-vs-agents principle for the distinction.

The sidebar autogenerates from this directory. Each page is one skill extracted from its subdirectory’s SKILL.md.

  • Agents — active executors that spawn their own context
  • Kernel index — all seven-artifact kernel targets