Files
SuperCharged-Claude-Code-Up…/README.md
uroma b98d3716af Add 10% OFF discount link for z.ai coding plan
Added discount offer link in multiple locations:
- README.md: In "What is Z.AI API?" section
- install-claude-code.sh: In hero banner, API key prompt, and manual instructions

Discount link: https://z.ai/subscribe?ic=R0K78RJKNW
2026-01-22 15:49:32 +00:00

456 lines
11 KiB
Markdown

# SuperCharged Claude Code - Ultimate Upgrade
Transform your Claude Code installation into an autonomous development powerhouse with 30+ custom skills, AI agents, and advanced integrations.
![SuperCharge](https://img.shields.io/badge/Claude-Code-Supercharged-blue)
![Skills](https://img.shields.io/badge/Skills-30+-green)
![Agents](https://img.shields.io/badge/Agents-Autonomous-orange)
![Version](https://img.shields.io/badge/Version-1.0.0-purple)
## Features
### 🧠 Cognitive Skills
- **always-use-superpowers** - Automatically applies relevant skills before any action
- **cognitive-core** - Core cognitive processing framework
- **cognitive-context** - Enhanced understanding and analysis
- **cognitive-planner** - Strategic planning capabilities
- **cognitive-safety** - Security and safety validation
### 🎯 Development Tools
- **agent-pipeline-builder** - Build multi-agent pipelines with structured data flow
- **dispatching-parallel-agents** - Execute multiple agents concurrently
- **executing-plans** - Execute implementation plans with review checkpoints
- **finishing-a-development-branch** - Complete and merge development work
- **subagent-driven-development** - Execute plans with independent subagents
### 🤖 Autonomous Agents
- **RalphLoop** - "Tackle Until Solved" autonomous agent for complex tasks
- **test-driven-development** - TDD workflow automation
- **systematic-debugging** - Automated debugging workflow
- **verification-before-completion** - Pre-completion validation
### 🎨 UI/UX Intelligence
- **ui-ux-pro-max** - 50 styles, 21 palettes, 50 font pairings
- Glassmorphism, Claymorphism, Neumorphism, Brutalism
- Responsive design patterns
- Accessibility-first components
### 🌐 Integrations
- **Multi-AI Brainstorming** - Collaborate with multiple AI models
- **Qwen Consultation** - Get second opinions from Qwen models
- **MCP Servers** - Image analysis, web search, GitHub integration
- **Dev-Browser** - Persistent browser automation
### 📝 Commands
- `/ralph` - Autonomous iteration until completion
- `/brainstorm` - Multi-AI brainstorming sessions
- `/write-plan` - Create implementation plans
- `/execute-plan` - Execute written plans
- `/commit` - Smart git commits
## Quick Start
### One-Line Installation
```bash
curl -fsSL https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/raw/main/supercharge.sh | bash
```
### Manual Installation
```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
```
### Installation Options
```bash
# Skip dependency installation
./supercharge.sh --skip-deps
# Development mode (verbose output)
./supercharge.sh --dev-mode
```
## Claude Code Installation (Optional)
If you don't have Claude Code installed yet, the supercharge script will offer to install it for you with **Z.AI API support**.
### What is Z.AI API?
Z.AI provides GLM (General Language Model) models that can be used with Claude Code:
- **glm-4.5-air** - Fast, efficient model (Haiku class)
- **glm-4.7** - Powerful model (Sonnet/Opus class)
> [!TIP]
> **Grab 10% OFF Token for z.ai coding plan**: [https://z.ai/subscribe?ic=R0K78RJKNW](https://z.ai/subscribe?ic=R0K78RJKNW)
### Automated Installation
```bash
# Install Claude Code with Z.AI API
./install-claude-code.sh --auto
# You'll be prompted for your Z.AI API key
# Get your API key from: https://docs.z.ai/devpack/tool/claude
```
### Manual Installation
```bash
# 1. Install Claude Code via npm
npm install -g @anthropic-ai/claude-code
# 2. Configure Z.AI API
# Create or edit ~/.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
```
### Show Manual Instructions Only
```bash
./install-claude-code.sh --manual
```
### Documentation
- **Z.AI Official Docs**: https://docs.z.ai/devpack/tool/claude
- **Claude Code Docs**: https://docs.anthropic.com/en/docs/claude-code/overview
## What Gets Installed
### Directory Structure
```
~/.claude/
├── skills/ # 30+ custom skills
├── agents/ # Agent management system
├── hooks/ # Custom hooks
├── commands/ # Custom commands
├── plugins/ # Plugin references
├── scripts/ # Utility scripts
└── settings.json # Configuration
~/.local/bin/
└── ralphloop # Ralph Orchestrator wrapper
```
### Installed Components
| Component | Description |
|-----------|-------------|
| **Skills** | 30+ custom skills for cognitive enhancement, development, UI/UX |
| **Agents** | Complete agent library with sync capabilities |
| **Hooks** | Session start, prompt submit, auto-trigger hooks |
| **Commands** | Predefined commands for common workflows |
| **Plugins** | MCP servers, LSP integrations, marketplace plugins |
| **Binaries** | RalphLoop wrapper for autonomous agent iteration |
## Usage
### RalphLoop - Autonomous Agent
```bash
# Let Ralph tackle complex problems autonomously
claude
> /ralph "Design a microservices architecture for an e-commerce platform"
# Ralph will iterate until the task is complete
# - Creates task in .ralph/PROMPT.md
# - Iterates continuously until success criteria are met
# - Updates progress in .ralph/state.json
# - Outputs final result to .ralph/iterations/final.md
```
**Configuration:**
```bash
# Set agent (default: claude)
export RALPH_AGENT=claude|gemini|kiro|q|auto
# Max iterations (default: 100)
export RALPH_MAX_ITERATIONS=100
# Max runtime in seconds (default: 14400 = 4 hours)
export RALPH_MAX_RUNTIME=14400
# Verbose output
export RALPH_VERBOSE=true
```
### Multi-AI Brainstorming
```bash
> /brainstorming "Create a viral TikTok marketing strategy"
# Collaborates with multiple AI perspectives:
# - Content strategist
# - SEO expert
# - Social media manager
# - Product manager
# - Developer
# - Designer
```
### Test-Driven Development
```bash
> /test-driven-development "Implement user authentication"
# 1. Write failing tests first
# 2. Implement minimal code to pass
# 3. Refactor while keeping tests green
```
### Systematic Debugging
```bash
> /systematic-debugging "Database connection timing out"
# 1. Gather information about the error
# 2. Form hypotheses about root cause
# 3. Test each hypothesis systematically
# 4. Verify fixes don't break other functionality
```
## Configuration
### Environment Variables
```bash
# Ralph Configuration
export RALPH_AGENT=claude # Agent selection
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
# Superpowers
export AUTO_SUPERPOWERS=true # Auto-inject superpowers context
```
### Settings Files
**~/.claude/settings.json**
```json
{
"customInstructions": "enabled",
"permissions": {
"allowedTools": ["*"],
"allowedPrompts": ["*"]
}
}
```
**~/.claude/hooks.json**
```json
{
"sessionStart": ["session-start-superpowers.sh"],
"userPromptSubmit": ["qwen-consult.sh", "ralph-auto-trigger.sh"]
}
```
## Advanced Features
### Agent Pipeline Builder
Build multi-agent workflows with structured data flow:
```bash
> /agent-pipeline-builder "Create a content generation pipeline"
# Creates: Research -> Draft -> Review -> SEO -> Publish
```
### Parallel Agent Execution
Run multiple independent agents simultaneously:
```bash
> /dispatching-parallel-agents "Test and document in parallel"
# Spawns: test-runner + documentation-writer
```
### Plan Execution
Execute written implementation plans with checkpoints:
```bash
> /execute-plan .claude/plans/feature-xyz.md
# Executes plan with review at each checkpoint
```
## Customization
### Adding Custom Skills
Create a new skill at `~/.claude/skills/your-skill/SKILL.md`:
```markdown
# Your Custom Skill
## When to Use
Use this skill when...
## What It Does
This skill provides...
```
### Adding Custom Hooks
Create hooks at `~/.claude/hooks/`:
**session-start-your-hook.sh**
```bash
#!/bin/bash
# Runs on session start
echo "Custom initialization..."
```
**user-prompt-your-hook.sh**
```bash
#!/bin/bash
# Runs before each user prompt
echo "Processing prompt..."
```
## Troubleshooting
### Ralph Loop Not Working
```bash
# 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
```bash
# Check skills directory
ls -la ~/.claude/skills/
# Verify skill syntax
cat ~/.claude/skills/your-skill/SKILL.md
# Check for errors
claude --debug
```
### Hooks Not Executing
```bash
# Check hooks.json
cat ~/.claude/hooks.json
# Verify hooks are executable
ls -la ~/.claude/hooks/*.sh
# Test hook manually
bash ~/.claude/hooks/session-start-superpowers.sh
```
## Backup and Restore
### Backup Current Setup
```bash
# Export all customizations
~/.claude/agents/export-claude-customizations.sh
```
### Restore from Backup
```bash
# Run installer with backup
./supercharge.sh
# Customizations are automatically backed to:
~/.claude-backup-YYYYMMDD_HHMMSS/
```
## Updates
### Update SuperCharge Package
```bash
cd SuperCharged-Claude-Code-Upgrade
git pull origin main
./supercharge.sh
```
### Update Agents
```bash
~/.claude/scripts/sync-agents.sh
```
## Uninstallation
```bash
# 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
3. Make your changes
4. Submit a pull request
## License
MIT License - See LICENSE file for details
## Credits
- **Ralph Orchestrator** - [mikeyobrien/ralph-orchestrator](https://github.com/mikeyobrien/ralph-orchestrator)
- **Claude Code** - [Anthropic](https://claude.com/claude-code)
- **Community Skills** - Various contributors
## Support
- **Issues**: [GitHub Issues](https://github.com/rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/issues)
- **Discussions**: [GitHub Discussions](https://github.com/rommark.dev/admin/SuperCharged-Claude-Code-Upgrade/discussions)
---
**Made with ❤️ for the Claude Code community**
*SuperCharge your development workflow today!*