tanweai /pua

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候,对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement. | Lead: Minwei Wang (https://www.minwei.wang · ORCID: 0009-0002-7976-4689 · DOI: 10.5281/zenodo.24156132)

★ 19,845⑂ 1,203👁 37⑃ 59● 123▤ 11
PythonCreated 2026-03-08openpua.ai/
Download: PUA v3.5.1PUA-3.5.1 ↓3.5.12026-09-09
+6
Daily
19,845
stars
1,203
forks
37
watchers
59
prs
123
issues
11
releases

README

pua


  


 Double your Codex / Claude Code productivity and output

Telegram · Discord · Twitter/X · Landing Page

🇨🇳 中文 | 🇯🇵 日本語 | 🇺🇸 English

 3.5.1 compatibility update: original PUA tone retained; runtime fixes and portable Claude Code / Codex / ChatGPT skill packages added. Not all models passed, and a productivity increase has not been established by this evaluation. Changes · Usage · Model results and known limits · Build and offline tests


  
      
  
  
  Scan to join WeChat group                      Add assistant on WeChat



  
  
  
  
  
  
  
  
  
  
  


 Most people think this project is a joke. That's the biggest misconception. It genuinely doubles your Codex / Claude Code productivity and output.

An AI Coding Agent skill plugin that uses corporate PUA rhetoric (Chinese version) / PIP — Performance Improvement Plan (English version) from Chinese & Western tech giants to force AI to exhaust every possible solution before giving up. Supports Claude Code, OpenAI Codex CLI, pi coding agent, Trae, Cursor, Kiro, CodeBuddy, OpenClaw, Google Antigravity, OpenCode, and VSCode (GitHub Copilot). Three capabilities:

1. PUA Rhetoric — Makes AI afraid to give up
2. Debugging Methodology — Gives AI the ability not to give up
3. Proactivity Enforcement — Makes AI take initiative instead of waiting passively

 Live Demo

https://openpua.ai · 📖 Beginner Guide

 Real Case: MCP Server Registration Debugging

A real debugging scenario. The agent-kms MCP server failed to load. The AI kept spinning on the same approach (changing protocol format, guessing version numbers) multiple times until the user manually triggered /pua.

L3 Triggered → 7-Point Checklist Enforced:

!PUA L3 triggered — stopped guessing, executed systematic checklist, found real error in MCP logs

Root Cause Located → Traced from Logs to Registration Mechanism:

!Root cause — claude mcp managed server registration differs from manual .claude.json editing

Retrospective → PUA's Actual Impact:

!Conversation retrospective — PUA skill forced stop on spinning, systematic checklist drove discovery of previously unchecked Claude Code MCP log directory

Key Turning Point: The PUA skill forced the AI to stop spinning on the same approach (changing protocol format, guessing version numbers) and instead execute the 7-point checklist. Read error messages word by word → Found Claude Code's own MCP log directory → Discovered that claude mcp registration mechanism differs from manual .claude.json editing → Root cause resolved.

 The Problem: AI's Five Lazy Patterns

| Pattern | Behavior |
|---------|----------|
| Brute-force retry | Runs the same command 3 times, then says "I cannot solve this" |
| Blame the user | "I suggest you handle this manually" / "Probably an environment issue" / "Need more context" |
| Idle tools | Has WebSearch but doesn't search, has Read but doe

Top issues

Discussions

Latest release

PUA v3.5.1 v3.5.1 2026-09-09
PUA v3.5.1

Compatibility and runtime fixes; original PUA tone retained. This is not an
all-model pass or a measured productivity-gain claim.

本次是兼容与运行修复,不是“全模型完全通过”认证。保留原情绪强度,不改成温柔版。

 更新内容

- 多端入口:从同一执行契约生成 Claude Code、Codex、ChatGPT 独立技能包及对话粘贴版;支持宿主缺工具、缺钩子时诚实说明能力边界。独立包可从本版本发布附件下载或在本地构建,不包含完整插件的命令和钩子。
- 运行修复:按真实事件处理工具失败;按会话与工作目录隔离、去重和恢复最小数值状态;成功的普通工具调用不清零任务失败;显式风味锁定与自动选择分开。
- 命令与反馈:修正实际插件路径解析和验收资产保护提醒;停止钩子只做非阻断提醒,/pua:survey quick 自愿评分后才本地记录,跳过不记录,无网络上传。
- 验收工具:增加 cc0、OMP、Codex CLI 的精确入口、原生技能调用、源文件指纹和结束事件检查;缺失证据、拒绝、回退、审批阻断和限流单列,不用传输成功替代行为通过。

 保留与边界

- 保留主技能原有引用台词、Codex 的 L1–L4 施压台词;完整 flavor

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON