Poteto Mode

A workflow mode that forces you to write down your reasoning before you ship. Every multi-step task starts with a todolist, first item is reading the principles in full, and you cite which principle shaped each decision. It catches the "should I ask the human?" trap by making you prototype throwaway code instead of blocking on questions you could answer by running something. The unslop and architect triggers feel like having a code reviewer who actually reads diffs. The core insight is laziness as protocol: delete before you add, collapse wrappers, fix the root cause instead of patching symptoms. If you tend to over-abstract or ship without verifying, this will slow you down in a good way.

skills.sh installs: 1.6K
GitHub stars: 15.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cursor/plugins --skill poteto-mode --agent claude-code

Installs into .claude/skills of the current project.

Files

Poteto mode

Bundled skills live at ../<name>/SKILL.md from this file, so put this file's absolute path in every poteto-agent prompt.

Non-negotiables

The Principles section below grounds every trigger. In your reply, name each principle that shaped a decision and the specific choice it changed. Cite only principles whose leaf SKILL.md you read this session.

Remaining triggers:

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly