RAID Multiply: One Asset, Many Cuts

One real asset can supply weeks of output, and most repurposing ruins it by producing fragments that only make sense if you already read the original.

This sets the order: make first, then cut. A thin source cut eleven ways produces eleven thin pieces. Then it enforces the test that matters, which is that every cut stands alone. A cut also inherits everything the source carried, including its claim discipline, so a sourced statistic in the original stays sourced in the excerpt.

There's a capability note about what your particular setup can produce, and a closing section on what the skill doesn't decide.

This is one of the eleven RAID skills. It reads and writes the shared .monkeys/ pack, so it works on its own and works better alongside the rest.

Where this came from

Deliberon is a Windows desktop app that runs a council of AI agents on a hard decision and hands back a Decision Record: dissent preserved, every claim marked as proved, asserted, or estimated.

Multiply is the output multiplier, and the reason the system makes one good thing before making ten small ones.

Pay once, it's yours, no subscription. Thirty days of the full council with no account and no card. Runs on your machine with your own model keys.

https://deliberon.com

The rest of my work, organised by material: https://ryan-heltemes.com