Description

bro is a one-line Claude Code skill: it makes Claude restate its last message in plain language, no jargon. When Claude answers with a wall of dense AI text, run /bro and it says the same thing like a human would.

Code Byte

---
name: bro
description: Restate the last message in plain human language, with no jargon.
disable-model-invocation: true
---

Restate your last message. Stop using jargon and speak coherently. State it more simply and concisely, like one human talking to another.

disable-model-invocation: true means Claude never triggers it on its own; it fires only when you type /bro.

Setup:

# Create the skill directory in your global (user-level) Claude config
mkdir -p ~/.claude/skills/bro

# Create the skill file and paste the Code Byte content above.
# The file must be named SKILL.md (singular); Claude Code won't find SKILLS.md.
nano ~/.claude/skills/bro/SKILL.md

Anything under ~/.claude/skills/ is global; it loads in every project. Drop it in a repo’s .claude/skills/ instead to scope it to that repo.

Example usage:

Claude says this:

The refactor decouples the persistence layer via a repository abstraction, enabling dependency inversion so the domain module no longer transitively imports the ORM.

You run /bro, and it says:

I split the database code out behind a small wrapper, so the main logic no longer touches the database library directly.

Same point, minus the jargon.