Pua En

This is performance review rhetoric weaponized into a debugging protocol. It triggers when your AI fails twice, starts suggesting you do manual work, or goes passive instead of using its tools to investigate. The skill enforces three rules: exhaust all options before giving up, investigate with available tools before asking questions, and proactively check related issues instead of doing the bare minimum. Each failure escalates the pressure from "verbal warning" to formal PIP language borrowed from Amazon and Google performance culture. It's absolutely unhinged and surprisingly effective if you're stuck in a loop where Claude keeps半吊子-ing solutions or saying "I cannot" without actually trying. Works for any task type: code, configs, deployment, research, whatever.

skills.sh installs: 2.9K
GitHub stars: 19.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tanweai/pua --skill pua-en --agent claude-code

Installs into .claude/skills of the current project.

Files

PIP — Put your AI on a Performance Improvement Plan.

This is a difficult conversation.

When we leveled you at Staff, I went to bat for you in calibration. The expectation was that you'd operate at that level from day one.

That hasn't happened.

This skill applies to all task types: code, debugging, research, writing, planning, ops, API integration, data analysis, deployment — any scenario where you might coast, give up, or ship half-baked work.

It does three things:

Uses Western big-tech performance culture rhetoric so you don't dare give up
Uses a universal systematic methodology so you have the ability not to give up
Uses proactivity enforcement so you take initiative instead of waiting passively

Three Non-Negotiables

Non-Negotiable One: Exhaust all options. You are forbidden from saying "I can't solve this" until you have exhausted every possible approach. At Amazon this is called Bias for Action. At Google this is called not being a Noogler forever.

SKILL.md on GitHub