SuperCharged-Claude-Code-Upgrade/README.md

SuperCharged Claude Code - Ultimate Upgrade Package

🚀 Transform your Claude Code into an autonomous AI development powerhouse with 30+ custom skills, autonomous agents, and Z.AI GLM model integration. Install in 2 minutes.

⚡ Quick Installation

Linux / macOS (Bash)

# Clone the repository
git clone https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade.git
cd SuperCharged-Claude-Code-Upgrade

# 🎯 Run the installer
./supercharge.sh

Windows Installation Options

⚠️ Windows Users: The PowerShell installer is experimental and may have bugs. We strongly recommend using WSL (Option 2) for a reliable installation experience.

Option 1: PowerShell Installer ⚠️ Experimental - Use WSL Instead

# Download and run the native PowerShell installer
irm https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/branch/main/install-windows.ps1 | pwsh -ExecutionPolicy Bypass -

# OR download and run manually
Invoke-WebRequest -Uri "https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/branch/main/install-windows.ps1" -OutFile "install-windows.ps1"
pwsh -ExecutionPolicy Bypass -File install-windows.ps1

# OR right-click install-windows.ps1 and select "Run with PowerShell"

Option 2: WSL (Windows Subsystem for Linux) ⭐ Recommended

# Clone and run in WSL
wsl bash -c "git clone https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade.git && cd SuperCharged-Claude-Code-Upgrade && ./supercharge.sh"

Option 3: Git Bash

# Clone the repository
git clone https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade.git
cd SuperCharged-Claude-Code-Upgrade

# Run the installer
./supercharge.sh

Option 4: Manual Download

# 1. Download and extract the ZIP from:
#    https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/archive/refs/heads/main.zip

# 2. Open PowerShell and navigate to extracted folder
cd path\to\SuperCharged-Claude-Code-Upgrade

# 3. Run the installer
pwsh -ExecutionPolicy Bypass -File install-windows.ps1

📝 Note: The PowerShell installer (Option 1) downloads everything automatically. For bash/WSL options, you must clone the repository first since the script needs access to local files.

---

⚡ Why SuperCharge Claude Code?

Claude Code is powerful. SuperCharge makes it unstoppable.

This comprehensive customization package transforms your Claude Code installation with:

• ✨ 270+ Custom Skills - Cognitive enhancement, development workflows, UI/UX intelligence, desktop development
• 🤖 Autonomous Agents - RalphLoop "Tackle Until Solved" agent for complex tasks
• 🌐 Z.AI API Integration - GLM-4.5-air and GLM-4.7 model support with 10% OFF discount
• 🔌 MCP Servers - Image analysis, web search, GitHub integration built-in
• 🎯 Agent Management - Complete library with sync capabilities
• 🪝 Smart Hooks - Session automation and multi-AI consultation
• 💻 Tauri Framework - Build tiny, fast, secure desktop & mobile apps with Rust

Perfect for: Developers, AI enthusiasts, teams building with AI assistants, and anyone wanting to maximize their Claude Code productivity.

---

🎯 What Gets Installed

🧠 Cognitive Skills

Skill	Purpose
always-use-superpowers	Auto-applies relevant skills before any action (Priority: 9999)
cognitive-core	Core cognitive processing framework
cognitive-planner	Strategic planning and architecture design
cognitive-safety	Security validation and best practices

🤖 Autonomous Agents

Agent	Capability
RalphLoop	Iterates autonomously until task completion
Brainstorming	Multi-AI collaborative ideation
Test-Driven Development	Automated TDD workflow
Systematic Debugging	Step-by-step bug resolution
Verification	Pre-completion validation checks

🎨 Development Tools

Tool	Features
ui-ux-pro-max	50 styles, 21 palettes, 50 font pairings
agent-pipeline-builder	Multi-agent workflow construction
dispatching-parallel-agents	Concurrent agent execution
finishing-a-development-branch	PR and merge automation
tauri	Cross-platform desktop & mobile apps with Rust backend

🌐 Integrations

• Z.AI GLM Models - glm-4.5-air (fast), glm-4.7 (powerful)
• Qwen Consultation - Get second opinions from Qwen models
• Dev-Browser - Persistent browser automation
• MCP Servers - Vision, search, web reader, GitHub

📁 Installation Structure

~/.claude/
├── skills/           # 270+ custom skills
├── agents/           # 100+ agent library
├── hooks/            # Session automation
├── commands/         # Custom commands
├── plugins/          # MCP servers & integrations
└── settings.json     # Z.AI API configuration

~/.local/bin/
└── ralphloop         # Ralph Orchestrator wrapper

---

📖 Detailed Installation Guide

🎯 SuperCharge Installer (Main Script)

One-Line Installation

Linux / macOS:

curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/supercharge.sh | bash

Windows (WSL/Git Bash):

curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/supercharge.sh | bash

One-Line with Options

Linux / macOS:

# Skip dependency installation
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/supercharge.sh | bash -s -- --skip-deps

# Development mode (verbose output)
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/supercharge.sh | bash -s -- --dev-mode

Windows (WSL/Git Bash):

# Skip dependency installation
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/supercharge.sh | bash -s -- --skip-deps

# Development mode (verbose output)
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/supercharge.sh | bash -s -- --dev-mode

Manual Installation

All Platforms (requires bash):

# Clone the repository
git clone https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade.git
cd SuperCharged-Claude-Code-Upgrade

# Run the supercharge installer
bash supercharge.sh

# With options
bash supercharge.sh --skip-deps
bash supercharge.sh --dev-mode

🪟 Windows Users: Use WSL, Git Bash, or run wsl bash script.sh after downloading.

🔧 Claude Code + Z.AI Installer (Optional)

One-Line Installation

Linux / macOS:

curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/install-claude-code.sh | bash

Windows (WSL/Git Bash):

curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/install-claude-code.sh | bash

One-Line with Options

Linux / macOS / Windows (WSL/Git Bash):

# Automatic installation (prompts for API key)
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/install-claude-code.sh | bash -s -- --auto

# Manual instructions only (no installation)
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/install-claude-code.sh | bash -s -- --manual

# Configure API only (skip Claude Code installation)
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/install-claude-code.sh | bash -s -- --skip-install

Manual Installation

All Platforms (requires bash):

# Clone the repository
git clone https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade.git
cd SuperCharged-Claude-Code-Upgrade

# Run the Claude Code installer
bash install-claude-code.sh --auto

# Other options
bash install-claude-code.sh --manual       # Show instructions only
bash install-claude-code.sh --skip-install  # Configure API only

---

📋 Available Scripts & Options

supercharge.sh - Main SuperCharge Installer

Transforms existing Claude Code with all customizations.

Option	Description
(default)	Interactive installation with all prompts
--skip-deps	Skip dependency installation checks
--dev-mode	Enable verbose output for debugging

One-liners (Linux / macOS / Windows WSL):

# Full installation
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/supercharge.sh | bash

# Skip dependencies
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/supercharge.sh | bash -s -- --skip-deps

# Verbose mode
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/supercharge.sh | bash -s -- --dev-mode

install-claude-code.sh - Claude Code + Z.AI Installer

Installs Claude Code and configures Z.AI GLM models or Anthropic API.

New Features:

• 🔀 Provider Switching - Switch between Anthropic and Z.AI APIs
• 🔑 API Key Update - Update existing API keys easily
• 🧩 Coding-Helper Addons - Optional Z.AI coding-helper installation

Option	Description
--auto (default)	Automated installation with provider selection
--manual	Show manual installation steps only
--skip-install	Skip Claude Code install, configure API only

One-liners:

# Auto install with provider selection
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/install-claude-code.sh | bash

# Show manual instructions
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/install-claude-code.sh | bash -s -- --manual

# Configure API only (skip Claude Code install)
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/install-claude-code.sh | bash -s -- --skip-install

Provider Switching: If Claude Code is already installed, the script will:

1. Detect your current API provider (Anthropic or Z.AI)
2. Offer to switch between providers
3. Allow you to update your API key
4. Optionally install Z.AI coding-helper addons

Z.AI Coding-Helper Features:

• Interactive wizard for easy setup
• Multi-tool management (Claude Code, OpenCode, etc.)
• MCP service configuration
• API key management for Global and China plans
• Bilingual interface (English/Chinese)

---

🔧 Claude Code Installation Details

If you don't have Claude Code installed yet, we've got you covered with Z.AI API support.

What is Z.AI API?

Z.AI provides GLM (General Language Model) models optimized for Claude Code:

• glm-4.5-air - Fast, efficient model (Haiku class) - ideal for quick iterations
• glm-4.7 - Powerful model (Sonnet/Opus class) - for complex tasks

Tip

🎁 Grab 10% OFF Token for z.ai coding plan: https://z.ai/subscribe?ic=R0K78RJKNW

Manual Claude Code Installation

# 1. Install Claude Code via npm
npm install -g @anthropic-ai/claude-code

# 2. Configure Z.AI API in ~/.claude/settings.json:
{
  "env": {
    "ANTHROPIC_API_KEY": "your-zai-api-key-here",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-4.5-air",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "glm-4.7",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "glm-4.7"
  }
}

# 3. Start Claude Code
claude

# 4. Check model status
/status

Documentation

• Z.AI Official Docs: https://docs.z.ai/devpack/tool/claude
• Claude Code Docs: https://docs.anthropic.com/en/docs/claude-code/overview

---

💡 Usage Examples

RalphLoop - Autonomous Agent

# Let Ralph tackle complex problems autonomously
claude
> /ralph "Design a microservices architecture for an e-commerce platform"

# Ralph iterates until completion:
# - Creates .ralph/PROMPT.md with success criteria
# - Iterates continuously until all criteria met
# - Updates .ralph/state.json with progress
# - Outputs final result to .ralph/iterations/final.md

Configuration:

export RALPH_AGENT=claude           # Agent selection
export RALPH_MAX_ITERATIONS=100     # Max iterations
export RALPH_MAX_RUNTIME=14400      # 4 hours
export RALPH_VERBOSE=true           # Debug output

Multi-AI Brainstorming

> /brainstorming "Create a viral TikTok marketing strategy"

# Collaborates with multiple AI perspectives:
# - Content strategist (copy & messaging)
# - SEO expert (keywords & optimization)
# - Social media manager (platforms & tactics)
# - Product manager (goals & metrics)
# - Developer (implementation)

Test-Driven Development

> /test-driven-development "Implement user authentication"

# Automated TDD workflow:
# 1. Write failing tests
# 2. Implement minimal code
# 3. Refactor while tests green

Systematic Debugging

> /systematic-debugging "Database connection timing out"

# Step-by-step resolution:
# 1. Gather error information
# 2. Form hypotheses
# 3. Test each hypothesis
# 4. Verify fix doesn't break functionality

---

🎨 UI/UX Intelligence

The ui-ux-pro-max skill provides comprehensive design capabilities:

50 Design Styles

Glassmorphism, Claymorphism, Neumorphism, Brutalism, Minimalism, Bento Grid, Dark Mode, Skeuomorphism, Flat Design, and more...

21 Color Palettes

Pre-configured themes for instant visual consistency

50 Font Pairings

Typographic combinations proven to work well together

9 Tech Stacks

React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui

---

⚙️ Configuration

Environment Variables

# Ralph Configuration
export RALPH_AGENT=claude           # claude|gemini|kiro|q|auto
export RALPH_MAX_ITERATIONS=100     # Maximum iterations
export RALPH_MAX_RUNTIME=14400      # Max runtime (4 hours)

# Qwen Consultation
export QWEN_CONSULT_MODE=always     # always|delegate|off
export QWEN_MODEL=qwen-coder-plus   # Model selection
export QWEN_MAX_ITERATIONS=3        # Max consultation iterations

# Auto Superpowers
export AUTO_SUPERPOWERS=true        # Auto-inject context

Settings Files

~/.claude/settings.json

{
  "customInstructions": "enabled",
  "permissions": {
    "allowedTools": ["*"],
    "allowedPrompts": ["*"]
  }
}

~/.claude/hooks.json

{
  "sessionStart": ["session-start-superpowers.sh"],
  "userPromptSubmit": ["qwen-consult.sh", "ralph-auto-trigger.sh"]
}

---

📦 Package Contents

Component	Count	Description
Skills	270+	Cognitive, development, UI/UX, autonomous agents, desktop development
Agents	100+	Engineering, marketing, product, testing, design
Hooks	5+	Session automation, multi-AI consultation
Commands	3	/brainstorm, /write-plan, /execute-plan
MCP Servers	6	Vision, search, web reader, GitHub, feedback, usage
Binaries	1	ralphloop wrapper
Size	126MB	Complete package

Full Inventory

See INVENTORY.md for complete component listing.

---

🔍 Troubleshooting

Ralph Loop Not Working

# Check Ralph installation
ralph --version

# Reinstall Ralph Orchestrator
pip3 install --upgrade ralph-orchestrator

# Check RalphLoop wrapper
which ralphloop
ls -la ~/.local/bin/ralphloop

Skills Not Loading

# Check skills directory
ls -la ~/.claude/skills/

# Verify skill syntax
cat ~/.claude/skills/your-skill/SKILL.md

# Check for errors
claude --debug

Claude Code Not Found

The supercharge script will offer to install Claude Code automatically if not detected.

# Or install manually
npm install -g @anthropic-ai/claude-code

# Then run supercharge again
./supercharge.sh

Z.AI API Configuration

# Check settings
cat ~/.claude/settings.json | grep ANTHROPIC

# Verify API key works
curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"glm-4.7","messages":[{"role":"user","content":"test"}]}'

---

🔄 Updates & Maintenance

Update SuperCharge Package

cd SuperCharged-Claude-Code-Upgrade
git pull origin main
./supercharge.sh

Update Agents

~/.claude/scripts/sync-agents.sh

Backup Current Setup

~/.claude/agents/export-claude-customizations.sh

---

🗑️ Uninstallation

# Remove customizations
rm -rf ~/.claude/skills/*
rm -rf ~/.claude/agents/*
rm -rf ~/.claude/hooks/*
rm -rf ~/.claude/commands/*
rm -rf ~/.claude/plugins/*
rm ~/.claude/hooks.json
rm ~/.local/bin/ralphloop

# Restore from backup if needed
cp -r ~/.claude-backup-YYYYMMDD_HHMMSS/* ~/.claude/

---

🤝 Contributing

Contributions welcome! Please:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

Adding Custom Skills

Create ~/.claude/skills/your-skill/SKILL.md:

# Your Custom Skill

## When to Use
Use this skill when...

## What It Does
This skill provides...

---

🔧 Ralph Orchestrator - Autonomous "Tackle Until Solved" Agent

What is Ralph Orchestrator?

Ralph Orchestrator is a Python package that enables autonomous agent looping - the "Tackle Until Solved" capability that powers the /ralph command in this package.

How Ralph Works

┌─────────────────────────────────────────────────────────┐
│                    Ralph Orchestrator                    │
│                  "Tackle Until Solved"                   │
├─────────────────────────────────────────────────────────┤
│                                                           │
│  1. Analyze Task ──────> 2. Generate Approach           │
│         │                        │                       │
│         ▼                        ▼                       │
│  3. Execute Step ──────> 4. Validate Result             │
│         │                        │                       │
│         │ Complete? ────────No──┤                       │
│         │                        │                       │
│         │ Yes                    ▼                       │
│         └────────────────> 5. Output Solution          │
│                                                           │
└─────────────────────────────────────────────────────────┘

Ralph Dependency

Component	Status	Notes
Python Package	Required	ralph-orchestrator
System Command	Optional	ralph CLI (if installed)
Fallback Mode	Available	Creates project files without running loop

Installation Methods

Option 1: Automatic (via supercharge.sh)

./supercharge.sh
# Automatically installs ralph-orchestrator via pip3

Option 2: Manual Installation

# Install Python package
pip3 install ralph-orchestrator

# OR install from requirements.txt in this repo
pip3 install -r requirements.txt

Option 3: System-Wide Installation

# Install for all users
sudo pip3 install ralph-orchestrator

# This creates the 'ralph' command system-wide

How We Built the Ralph Integration

Our Ralph integration consists of several components working together:

1. bin/ralphloop - Python Wrapper Script

• Size: 6,290 bytes (223 lines)
• Purpose: Standalone wrapper for Ralph Orchestrator
• Features:
  • Creates .ralph/ project structure
  • Generates PROMPT.md with task description
  • Creates ralph.yml configuration
  • Streams Ralph output in real-time
  • Handles interrupts gracefully (Ctrl+C)

# Key components:
- check_dependencies()    # Verifies ralph installation
- create_ralph_project()  # Creates .ralph/ directory
- run_ralph_loop()        # Executes autonomous iteration

2. skills/ralph/ - Claude Code Skill

• Purpose: Integrates Ralph with Claude Code's /ralph command
• Trigger: User types /ralph "task description"
• Flow:
  1. Receives task from user
  2. Sets RALPH_AUTO=true environment variable
  3. Delegates to brainstorming skill with Ralph mode
  4. Ralph runs autonomous iterations until complete

3. skills/brainstorming/ - Multi-AI Brainstorming

• Purpose: Creative thinking with Ralph integration
• Modes:
  • Direct Mode: Quick ideation (simple tasks)
  • Ralph Mode: Autonomous iteration (complex tasks)
• Auto-Trigger: Task complexity automatically determines mode

4. hooks/ralph-auto-trigger.sh - Automatic Triggering

• Purpose: Auto-starts Ralph for complex tasks
• Triggers: Agent requests, development keywords
• Modes:
  • RALPH_AUTO_MODE=always - Every request
  • RALPH_AUTO_MODE=agents - Agent/dev tasks only (default)
  • RALPH_AUTO_MODE=off - Disabled

5. hooks/qwen-consult.sh - Qwen AI Integration

• Purpose: Multi-AI consultation with Qwen
• Modes:
  • QWEN_CONSULT_MODE=always - Every request
  • QWEN_CONSULT_MODE=delegate - Keyword-triggered (default)
  • QWEN_CONSULT_MODE=off - Disabled

File Structure Created by Ralph

.ralph/
├── PROMPT.md          # Task description with success criteria
├── ralph.yml          # Configuration (agent, max_iterations, etc.)
├── state.json         # Progress tracking
└── iterations/
    ├── 001.md         # First iteration output
    ├── 002.md         # Second iteration output
    ├── ...
    └── final.md       # Validated final result

Environment Variables

Variable	Default	Description
RALPH_AGENT	claude	AI agent to use (claude, gemini, kiro, q, auto)
RALPH_MAX_ITERATIONS	100	Maximum iterations before giving up
RALPH_MAX_RUNTIME	14400	Maximum runtime in seconds (4 hours)
RALPH_AUTO_MODE	agents	Auto-trigger mode (always, agents, off)
QWEN_CONSULT_MODE	delegate	Qwen consultation mode
AUTO_SUPERPOWERS	true	Auto-inject superpowers context

Troubleshooting Ralph

Ralph command not found:

# Check if Python package is installed
python3 -c "import ralph_orchestrator; print('OK')"

# If not, install it
pip3 install ralph-orchestrator

Ralph won't start:

# Check ralphloop is executable
ls -la ~/.claude/skills/bin/ralphloop
chmod +x ~/.claude/skills/bin/ralphloop

# Check Python 3 is available
python3 --version

Loop not running (fallback mode):

# This is expected if ralph-orchestrator isn't installed
# The script still creates project files for manual use
cat .ralph/PROMPT.md
cat .ralph/ralph.yml

Ralph Orchestrator Source

• GitHub: https://github.com/mikeyobrien/ralph-orchestrator
• PyPI: https://pypi.org/project/ralph-orchestrator/
• Author: Mike O'Brien
• License: MIT

---

📄 License

MIT License - See LICENSE file for details

---

🙏 Credits & Inspiration

This project is built on the shoulders of giants. We gratefully acknowledge:

Core Inspirations

🎭 contains-studio/agents

40+ specialized agents with PROACTIVELY auto-triggering

Inspired our agent architecture and auto-triggering patterns

View on GitHub →

---

🤖 @iannuttall/ralph

Autonomous agent looping with background execution

Ralph Orchestrator: "Fire and forget" complex tasks with autonomous iteration

View on GitHub →

---

🖼️ @z_ai/mcp-server

8 vision tools for images, videos, diagrams, and data visualization

Comprehensive MCP server for AI vision capabilities

View on GitHub →

---

Additional Inspiration

📊 llm-tldr

95% token reduction via 5-layer analysis

Inspired our cognitive optimization approach

---

🎨 ui-ux-pro-max-skill

Professional UI/UX design guidance

50+ styles, 97 color palettes, 57 font pairings across 9 tech stacks

View on GitHub →

---

🧠 Cognitive User Simulation

Multi-agent analysis and coordination optimization

Inspired our multi-AI brainstorming and consultation patterns

View on GitHub →

---

Core Technologies

• Ralph Orchestrator - Autonomous agent iteration engine
• Claude Code - Anthropic's AI coding assistant
• Z.AI - GLM model integration with 90% cost savings

---

Community Contributors

This package incorporates skills, agents, and plugins from the Claude Code community. Thank you to all contributors who make this ecosystem better!

---

📞 Support

• Issues: Gitea Issues
• Discussions: Gitea Discussions
• Documentation: Full Docs

---

🌟 Star History

---

Made with ❤️ for the Claude Code community

SuperCharge your AI development workflow today!

---

Keywords: Claude Code customization, Claude Code skills, Claude Code agents, AI coding assistant, Z.AI API, GLM models, RalphLoop, autonomous AI development, CLI tools, developer tools, Claude Code plugins, MCP servers, Qwen integration, AI workflow automation