This commit adds 91 skills and 88 agents converted from the system_prompts_leaks repository. ## Stats - Anthropic: 21 skills + 21 agents (42 total) - OpenAI: 42 skills + 39 agents (81 total) - Google: 11 skills + 11 agents (22 total) - Perplexity: 2 skills + 2 agents (4 total) - xAI: 5 skills + 5 agents (10 total) - Proton: 2 skills + 2 agents (4 total) - Misc: 8 skills + 8 agents (16 total) ## Features - Auto-integrated with Ralph autonomous agent system - Actual system prompts from production AI systems - Includes Claude Code, GPT-5, Gemini 3, Grok 4, and more 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
5.1 KiB
5.1 KiB
SuperCharged Claude Code Upgrade - System Prompts Leaks
This repository contains 179 system prompt skills and agents converted from the system_prompts_leaks repository.
📊 Installation Stats
| Category | Skills | Agents | Total |
|---|---|---|---|
| Anthropic | 21 | 21 | 42 |
| OpenAI | 42 | 39 | 81 |
| 11 | 11 | 22 | |
| Perplexity | 2 | 2 | 4 |
| xAI | 5 | 5 | 10 |
| Proton | 2 | 2 | 4 |
| Misc | 8 | 8 | 16 |
| TOTAL | 91 | 88 | 179 |
📂 Repository Structure
supercharged-claude-code-upgrade/
├── skills-ralph-leaks/ # 91 system prompt skills
│ ├── INTEGRATION.md # Integration guide
│ ├── INSTALLATION_SUMMARY.md # Complete summary
│ ├── anthropic-*.md # 21 Anthropic prompts
│ ├── openai-*.md # 42 OpenAI prompts
│ ├── google-*.md # 11 Google prompts
│ ├── perplexity-*.md # 2 Perplexity prompts
│ ├── xai-*.md # 5 xAI prompts
│ ├── proton-*.md # 2 Proton prompts
│ └── misc-*.md # 8 miscellaneous prompts
│
└── agents-ralph-leaks/ # 88 full system prompt agents
├── anthropic-*-agent/ # 21 Anthropic agents
├── openai-*-agent/ # 39 OpenAI agents
├── google-*-agent/ # 11 Google agents
├── perplexity-*-agent/ # 2 Perplexity agents
├── xai-*-agent/ # 5 xAI agents
├── proton-*-agent/ # 2 Proton agents
└── misc-*-agent/ # 8 miscellaneous agents
🚀 Installation
Clone this repository
git clone https://github.rommark.dev/admin/SuperCharged-Claude-Code-Upgrade.git
cd SuperCharged-Claude-Code-Upgrade
Install to Claude Code
# Copy skills
cp -r skills-ralph-leaks/* ~/.claude/skills/
# Copy agents
cp -r agents-ralph-leaks/* ~/.claude/agents/
📖 Usage
Auto-Trigger via Ralph
All 179 prompts are automatically available to Ralph's autonomous agent selection:
/ralph "Build a full-stack application"
Manual Skill Invocation
/skill anthropic-claude-code "Help me build a React app"
/skill openai-gpt-5-thinking "Solve this complex problem"
/skill google-gemini-3-pro "Explain quantum computing"
/skill openai-gpt-5-1-friendly "Write a casual email"
Manual Agent Creation
/agent anthropic-claude-code-agent
/agent openai-gpt-5-thinking-agent
/agent google-gemini-3-pro-agent
🎯 Key Prompts Available
Anthropic (42 prompts)
anthropic-claude-code- Claude Code CLI (v0.2.9)anthropic-claude-4-5-sonnet- Claude 4.5 Sonnetanthropic-claude-sonnet-4- Claude Sonnet 4anthropic-claude-opus-4-5- Claude Opus 4.5 Thinkinganthropic-claude-3-7-sonnet- Claude 3.7 Sonnetanthropic-claude-in-chrome- Chrome extensionanthropic-pdf,anthropic-xlsx,anthropic-docx,anthropic-pptx- Documents
OpenAI (81 prompts)
openai-gpt-5-thinking- GPT-5 Thinking Modeopenai-gpt-5-1-professional- Professional personalityopenai-gpt-5-1-friendly- Friendly personalityopenai-gpt-4o- GPT-4oopenai-gpt-4-1- GPT-4.1openai-codex- Codexopenai-chatgpt-gpt-5-agent-mode- Agent Modeopenai-tool-deep-research- Deep Researchopenai-tool-web-search- Web Search- And 30+ more personalities and tools
Google (22 prompts)
google-gemini-3-pro- Gemini 3 Progoogle-gemini-3-flash- Gemini 3 Flashgoogle-gemini-workspace- Workspace integrationgoogle-gemini-2-5-pro-guided-learning- Guided learninggoogle-gemini-cli-system-prompt- CLIgoogle-notebooklm-chat- NotebookLM
Other Providers (34 prompts)
perplexity-voice-assistant- Perplexity voiceperplexity-comet-browser-assistant- Comet browserxai-grok-4- Grok 4xai-grok-3- Grok 3xai-grok-personas- Grok personasmisc-kagi-assistant- Kagi searchmisc-notion-ai- Notion AImisc-raycast-ai- Raycast AI
🔄 Updating
To update with new prompts from the source repository:
cd /tmp
git clone https://github.com/asgeirtj/system_prompts_leaks.git
python3 convert_prompts.py # Use the conversion script
⚠️ Security & Usage Note
These are actual leaked system prompts from production AI systems. They contain:
- Behavioral guidelines
- Safety protocols
- Tool usage patterns
- Response formatting rules
- Personality configurations
Use responsibly and in accordance with each provider's terms of service.
📚 Source
https://github.com/asgeirtj/system_prompts_leaks
📝 License
This repository contains converted system prompts from various AI providers. Please respect the original providers' terms of service and use these prompts responsibly.
Installed: 2026-01-28 Total Prompts: 179 (91 skills + 88 agents) Auto-integrated with: Ralph autonomous agent system