Skip to content

/reader-steps

Format the steps only a human can perform.

What it does

A style spec for rendering actions the reader has to do themselves — interactive logins, UI clicks, approvals in other systems — as a bounded task block: numbered with a stable tag, grouped by surface (terminal, browser, phone, physical world), each step titled by its outcome with the literal command underneath and a verification line. Scales down to one line and up to a map with stop points.

When to reach for it

Any handoff containing something an agent cannot do for you.

It's working if

  • Every step ends with something you can check to know it worked.
  • A handoff with one manual action renders as one line, not a full block.
  • You can start any step without scrolling up — the command and the place it runs are both right there.

Install this skill

Then type /reader-steps in your agent.

npx skills@latest add smorinlabs/smorinlabs-harness -s reader-steps

Or install it as the reader-steps plugin.

/plugin install reader-steps@smorinlabs-harness

Where it fits