Figure It Out

When you're staring down a codebase-wide migration or a complex multi-part change that doesn't fit any narrower playbook, this skill builds you a custom workflow before touching code. It forces you to define done as a falsifiable predicate, scope the work, pick a rigor level, then decompose into independently landable units with verification harnesses built first. The hypothesis loop runs per unit with real artifact inspection, not self-reports, and everything logs to a TSV audit trail via show-me-your-work so you can review decisions after stepping away. It's opinionated about rigor scaling to blast radius and treats the workflow design itself as the first deliverable. Best for ambitious changes where the cost of building the wrong thing justifies the ceremony.

skills.sh installs: 4.7K
GitHub stars: 15.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cursor/plugins --skill figure-it-out --agent claude-code

Installs into .claude/skills of the current project.

Files

Figure it out

When the task matches no playbook, design one. The deliverable before any code is the workflow itself: a sequence of phases that scales rigor to the task, runs the scientific method, and leaves a decision trail a human can audit after stepping away.

Start

Open a todolist whose first item is to read the Principles section of the poteto-mode skill. Then add the phases below as todos.

Phase A: Frame

Ground first, then commit. Don't start the run until you can state:

The definition of done as a falsifiable predicate (the prove-it-works principle skill).
Scope, quantified: rough units and effort, plus the blockers grounding surfaced.
The rigor level, biased high. One-way doors and high blast radius get more. Reversible low-stakes steps get less. Rigor is gates and artifacts, not "try harder".

Present the framing and tradeoffs before committing to a long run. Reversible work proceeds (the never-block-on-the-human principle skill), but a multi-hour run earns one checkpoint.