Telegram · Discord · Twitter/X · Landing Page

🇨🇳 中文 | 🇯🇵 日本語 | 🇺🇸 English

    
_{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, Cursor, Claude, 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

https://openpua.ai

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:

Root Cause Located → Traced from Logs to Registration Mechanism:

Retrospective → PUA's Actual Impact:

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 skill activates automatically when any of these occur:

Failure & giving up:

• Task has failed 2+ times consecutively
• About to say "I cannot" / "I'm unable to solve"
• Says "This is out of scope" / "Needs manual handling"

Blame-shifting & excuses:

• Pushes the problem to user: "Please check..." / "I suggest manually..." / "You might need to..."
• Blames environment without verifying: "Probably a permissions issue" / "Probably a network issue"
• Any excuse to stop trying

Passive & busywork:

• Repeatedly fine-tunes the same code/parameters without producing new information
• Fixes surface issue and stops, doesn't check related issues
• Skips verification, claims "done"
• Gives advice instead of code/commands
• Encounters auth/network/permission errors and gives up without trying alternatives
• Waits for user instructions instead of proactively investigating

User frustration phrases (triggers in multiple languages):

• "why does this still not work" / "try harder" / "try again"
• "you keep failing" / "stop giving up" / "figure it out"

Scope: Debugging, implementation, config, deployment, ops, API integration, data processing — all task types.

Does NOT trigger: First-attempt failures, known fix already executing.

Type /pua in the conversation to manually activate.

Inspired by Alibaba's management framework (Smell, Elevate, Mirror), extended to 5 steps:

1. Smell the Problem — List all attempts, find the common failure pattern
2. Elevate — Read errors word by word → WebSearch → read source → verify environment → invert assumptions
3. Mirror Check — Repeating? Searched? Read the file? Checked the simplest possibilities?
4. Execute — New approach must be fundamentally different, have verification criteria, produce new info on failure
5. Retrospective — What solved it? Why didn't you think of it earlier? Then proactively check related issues

• Alibaba Flavor (Methodology): Smell / Elevate / Mirror
• ByteDance Flavor (Brutally Honest): Always Day 1. Context, not control
• Huawei Flavor (Wolf Spirit): Strivers first. In victory, raise the glasses; in defeat, fight to the death
• Tencent Flavor (Horse Race): I've already got another agent looking at this problem...
• Meituan Flavor (Relentless): Do the hard but right thing. Will you chew the tough bones or not?
• Netflix Flavor (Keeper Test): If you offered to resign, would I fight hard to keep you?
• Musk Flavor (Hardcore): Extremely hardcore. Only exceptional performance.
• Jobs Flavor (A/B Player): A players hire A players. B players hire C players.

9 real bug scenarios, 18 controlled experiments (Claude Opus 4.6, with vs without skill)

Key Finding: In the config review scenario, without_skill missed Redis misconfiguration and CORS wildcard security risks. With_skill's "proactive initiative checklist" drove security review beyond surface-level fixes.

PUA Skill provides fully translated versions — each language has independent, culturally adapted skill files.

🇺🇸 English "PIP Edition": "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." — The English version uses PIP (Performance Improvement Plan) rhetoric from Western big-tech. Every sentence is a real phrase from actual PIP conversations. Chinese version uses Alibaba 361, ByteDance, Huawei wolf culture. English version uses Amazon Leadership Principles, Google perf calibration, Meta PSC, Netflix Keeper Test, Stripe Craft. Same repo, same engine, two cultural faces.

Choose the file with the corresponding language suffix when installing. See platform-specific instructions below.

# Option 1: Install via marketplace
claude plugin marketplace add tanweai/pua
claude plugin install pua@pua-skills

# Option 2: Manual install
git clone https://github.com/tanweai/pua.git ~/.claude/plugins/pua

Codex CLI uses the same Agent Skills open standard (SKILL.md). The Codex version uses a condensed description to fit Codex's length limits:

Recommended: One-command install (git clone + symlink, supports git pull updates)

Ask Codex to run:

Fetch and follow instructions from https://raw.githubusercontent.com/tanweai/pua/main/.codex/INSTALL.md

Manual install:

mkdir -p ~/.codex/skills/pua
curl -o ~/.codex/skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/codex/pua/SKILL.md

mkdir -p ~/.codex/prompts
curl -o ~/.codex/prompts/pua.md \
  https://raw.githubusercontent.com/tanweai/pua/main/commands/pua.md

Trigger methods:

Project-level install (current project only):

mkdir -p .agents/skills/pua
curl -o .agents/skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/codex/pua/SKILL.md

mkdir -p .agents/prompts
curl -o .agents/prompts/pua.md \
  https://raw.githubusercontent.com/tanweai/pua/main/commands/pua.md

Cursor uses .mdc rule files (Markdown + YAML frontmatter). The PUA rule triggers automatically via AI semantic matching (Agent Discretion mode):

# Project-level install (recommended)
mkdir -p .cursor/rules
curl -o .cursor/rules/pua.mdc \
  https://raw.githubusercontent.com/tanweai/pua/main/cursor/rules/pua.mdc

Kiro supports two loading methods: Steering (auto semantic trigger) and Agent Skills (SKILL.md compatible).

Option 1: Steering file (recommended)

mkdir -p .kiro/steering
curl -o .kiro/steering/pua.md \
  https://raw.githubusercontent.com/tanweai/pua/main/kiro/steering/pua.md

Option 2: Agent Skills (same format as Claude Code)

mkdir -p .kiro/skills/pua
curl -o .kiro/skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md

CodeBuddy uses the same AgentSkills open standard (SKILL.md). Plugin and skill formats are fully compatible:

# Option 1: Install via marketplace
codebuddy plugin marketplace add tanweai/pua
codebuddy plugin install pua@pua-skills

# Option 2: Manual install (global)
mkdir -p ~/.codebuddy/skills/pua
curl -o ~/.codebuddy/skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/codebuddy/pua/SKILL.md

Project-level install (current project only):

mkdir -p .codebuddy/skills/pua
curl -o .codebuddy/skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/codebuddy/pua/SKILL.md

OpenClaw uses the same AgentSkills open standard (SKILL.md). Skills work across Claude Code, Codex CLI, and OpenClaw with zero modifications:

# Install via ClawHub
clawhub install pua

# Or manual install
mkdir -p ~/.openclaw/skills/pua
curl -o ~/.openclaw/skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md

Project-level install (current project only):

mkdir -p skills/pua
curl -o skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md

Antigravity uses the same AgentSkills open standard (SKILL.md). Skills work across Claude Code, Codex CLI, OpenClaw, and Antigravity with zero modifications:

# Global install (all projects)
mkdir -p ~/.gemini/antigravity/skills/pua
curl -o ~/.gemini/antigravity/skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md

Project-level install (current project only):

mkdir -p .agent/skills/pua
curl -o .agent/skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md

OpenCode uses the same AgentSkills open standard (SKILL.md). Zero modifications needed:

# Global install (all projects)
mkdir -p ~/.config/opencode/skills/pua
curl -o ~/.config/opencode/skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md

Project-level install (current project only):

mkdir -p .opencode/skills/pua
curl -o .opencode/skills/pua/SKILL.md \
  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md

VSCode Copilot uses instruction files under the .github/ directory. Three file types for different use cases:

Global instructions (auto-active):

mkdir -p .github
cp vscode/copilot-instructions-en.md .github/copilot-instructions.md

Path-level instructions (auto-active, supports glob filtering):

mkdir -p .github/instructions
cp vscode/instructions/pua-en.instructions.md .github/instructions/

Manual trigger command (type /pua in Copilot Chat):

mkdir -p .github/prompts
cp vscode/prompts/pua-en.prompt.md .github/prompts/

Required settings: Method 1 — open VSCode Settings (Ctrl+,), search useInstructionFiles, enable github.copilot.chat.codeGeneration.useInstructionFiles. Method 2 — search includeApplyingInstructions, enable chat.includeApplyingInstructions. Method 3 requires no settings.

Experimental: Agent Team requires the latest Claude Code version with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.

# 1. Enable Agent Team
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
# Or add to ~/.claude/settings.json:
# { "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" } }

# 2. Ensure PUA Skill is installed

Approach 1: Leader with built-in PUA (Recommended)

Add to your project's CLAUDE.md:

# Agent Team PUA Config
All teammates must load the pua skill before starting work.
Teammates report to Leader in [PUA-REPORT] format after 2+ failures.
Leader manages global pressure levels and cross-teammate failure transfer.

Approach 2: Standalone PUA Enforcer watchdog (for 5+ teammates)

mkdir -p .claude/agents
curl -o .claude/agents/pua-enforcer.md \
  https://raw.githubusercontent.com/tanweai/pua/main/agents/pua-enforcer-en.md

Spawn pua-enforcer as an independent watchdog in your Agent Team.

┌─────────────────────────────────────────┐
│              Leader (Opus)              │
│ Global failure count · PUA level · Race │
└────┬──────────┬──────────┬──────────┬───┘
     │          │          │          │
┌────▼───┐ ┌───▼────┐ ┌───▼────┐ ┌───▼────────┐
│ Team-A │ │ Team-B │ │ Team-C │ │  Enforcer  │
│Self-PUA│ │Self-PUA│ │Self-PUA│ │  Watchdog  │
│Report ↑│ │Report ↑│ │Report ↑│ │  Intervene │
└────────┘ └────────┘ └────────┘ └────────────┘

High-Agency is PUA's next evolution — same corporate rhetoric, same pressure culture, but with an inner engine that never burns out.

PUA v1 = external pressure only (turbocharger — needs fuel, burns out between sessions) High-Agency = external pressure + internal drive (nuclear reactor — self-sustaining chain reaction)

Based on research into what makes persistently high-agency individuals:

1. Irreconcilable Inner Contradiction — A permanent tension between "how things should be" and "how things are" that fuels continuous improvement
2. Micro-Pleasure Anchors — [Victory] markers that celebrate progress and build momentum
3. Internalized Standards — Quality Compass: you are your own first reviewer, not because someone checks, but because your standards don't allow sloppy work
4. "Doing"-Oriented Identity — P8 identity anchoring: every action reflects who you are, not just what you're told to do
5. Self-Repair Mechanism — Recovery Protocol: when stuck, self-diagnose before external pressure kicks in

# Via marketplace (same plugin, additional skill)
claude plugin marketplace add tanweai/pua
claude plugin install pua@pua-skills
# High-Agency skill is automatically available as "high-agency"

High-Agency works standalone or stacked with PUA v1. When stacked:

1. Task start → Read builder-journal.md + [Calibration]
2. Executing → [Victory] markers + Quality Compass + Full-Chain Audit
3. 1st failure → Natural adjustment (neither skill triggers extra)
4. 2nd failure → Recovery Protocol triggers (self-rescue window)
5. Recovery fails → PUA L1 takes over, normal L1/L2/L3/L4 escalation
6. Task complete → Quality Compass final check + Metacognition archive

• superpowers:systematic-debugging — PUA adds motivation layer, systematic-debugging provides methodology
• superpowers:verification-before-completion — Prevents false "fixed" claims
• high-agency + pua — Stack both: inner drive + external pressure, Recovery Protocol before L1

Upload your Claude Code / Codex CLI conversation logs (.jsonl) to help us improve PUA Skill's effectiveness.

Upload here ->

Uploaded files are used for Benchmark testing and Ablation Study analysis to quantify how different PUA strategies affect AI debugging behavior.

Get your .jsonl files:

# Claude Code
ls ~/.claude/projects/*/sessions/*.jsonl

# Codex CLI
ls ~/.codex/sessions/*.jsonl

MIT

By TanWei Security Lab — making AI try harder, one PUA at a time.