Agentic Product Lifecycle

mxa-orchestrate

Runs the other skills on a schedule or a trigger, on whatever agent runtime a team uses, and keeps the rule that agents propose and people decide.

  • Triggers a run, claims an item, routes it to the right skill and stops at the human gate.
  • Treats the scheduling engine as something to plug in rather than something we build.
  • Keeps the tracker as the one source of truth, so the loop and the people read the same list.
  • Runs the other skills without their having to remember anything between runs.

What is inside

Instructions. Nothing here runs on its own: the judgement is the skill.

Evals
3

Works with

The outside tools and connectors this skill drives.

  • Claude Code Routines or GitHub Actions· our default
  • Vercel eve
  • Linear agents

The first is what we reach for on our own projects. A project that already uses one of the others keeps it, and the skill works with that instead.

Install it

npx skills add madebymany/madebyagents --skill mxa-orchestrate
Read the skill itself