Kickoff help

Answer the user's question about kickoff, hand them a prompt they can send, and link the file the answer came from. For a help question, don't start the work. The user asked how, and a kickoff run spends real tokens, so let them send the prompt.

A message that asks for work, such as "use kickoff to fix this bug", is not a help question. Read kickoff, do the work under it, and mention once that invoking /kickoff keeps the work in this style.

This file maps questions to the skills and playbooks that hold the answers. Those files own the details. Read the file you route to before you quote it, and trust it when it disagrees with this map. The links here are repo-relative, so give the user the file's public copy: https://github.com/Timmyy3000/skills/blob/main/ followed by its path.

Find out what they need

Infer the need from the message and the conversation. A named situation, such as "which skill reviews a PR?", goes straight to its section. If the need is still unclear, ask one multiple-choice question with these options, then answer only the section they pick: get set up, start a task with /kickoff, pick a skill for a situation, fix a run that went wrong, or make kickoff my own.

Check the state that changes the answer, and mention it only when it does. No kickoff.yaml means /kickoff-setup hasn't run for this user, so every role runs on the parent's model, which is a valid setup. No verify-* skill or other app harness in the project means agents have no scripted way to drive the app; mention /create-verification-skill when the question is about proving a change works.

Get set up

1. Install with npx skills add Timmyy3000/skills plus npx skills add DietrichGebert/ponytail --skill ponytail --skill ponytail-review. The README lists narrower installs.
2. Optionally run /kickoff-setup. It asks for a reasoning budget, maps a model to each role, and writes kickoff.yaml. Skip it and every role runs on the parent's model.
3. Start a real task with /kickoff, a goal, and a check that can pass or fail.