Skills

Pre-built workflows agents can invoke as slash commands.

Available skills

SkillWhat it does
/buildRead commands.yaml → run install, build, test, lint
/reviewgit diff → tests → decisions.md check → maturity
/bugfixReproduce → find root cause → fix → verify → regression test
/delegateSave session → create swarm task → handoff to another agent
/feedbackLog bug / suggestion / friction / positive observation
/statusDoctor + validate + maturity + swarm status

How they work

Each skill reads commands from ai/manifest/commands.yaml — never hardcodes project-specific commands. Skills also reference MCP servers when appropriate:

  • context7 — for unfamiliar library APIs or version errors
  • sequential-thinking — for complex multi-step debugging

Delegation rules in skills

Each skill includes escalation guidance:

  • Stuck after 2 attempts → escalate to opus model
  • Need to search code → delegate to haiku
  • Architecture change needed → delegate to architect agent