Add 91 system prompt skills from major AI providers

This commit adds 91 skills converted from the system_prompts_leaks repository. ## Stats - Anthropic: 21 skills - OpenAI: 42 skills - Google: 11 skills - Perplexity: 2 skills - xAI: 5 skills - Proton: 2 skills - Misc: 8 skills ## 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>
2026-01-28 08:26:40 +00:00
parent 7337f5877b
commit cbf272c9b5
93 changed files with 26286 additions and 0 deletions
--- a/skills/INSTALLATION_SUMMARY.md
+++ b/skills/INSTALLATION_SUMMARY.md
@@ -0,0 +1,242 @@
+# System Prompts Leaks - Installation Summary
+
+## ✅ Installation Complete!
+
+Successfully installed **179 system prompt skills and agents** from the [system_prompts_leaks](https://github.com/asgeirtj/system_prompts_leaks) repository.
+
+## 📊 Installation Stats
+
+| Category | Skills | Agents | Total |
+|----------|--------|--------|-------|
+| **Anthropic** | 21 | 21 | 42 |
+| **OpenAI** | 42 | 39 | 81 |
+| **Google** | 11 | 11 | 22 |
+| **Perplexity** | 2 | 2 | 4 |
+| **xAI** | 5 | 5 | 10 |
+| **Proton** | 2 | 2 | 4 |
+| **Misc** | 8 | 8 | 16 |
+| **TOTAL** | **91** | **88** | **179** |
+
+## 📂 Installation Locations
+
+```
+~/.claude/
+├── skills/ralph-leaks/          # 91 system prompt skills
+│   ├── INTEGRATION.md            # This file
+│   ├── 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
+```
+
+## 🚀 How to Use
+
+### Auto-Trigger via Ralph
+
+All 179 prompts are automatically available to Ralph's autonomous agent selection:
+
+```
+/ralph "Build a full-stack application"
+```
+
+Ralph will automatically select and apply the most appropriate system prompts for each phase of the task.
+
+### 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
+- `anthropic-claude-code` - Claude Code CLI (v0.2.9)
+- `anthropic-claude-4-5-sonnet` - Claude 4.5 Sonnet
+- `anthropic-claude-sonnet-4` - Claude Sonnet 4
+- `anthropic-claude-opus-4-5` - Claude Opus 4.5 Thinking
+- `anthropic-claude-3-7-sonnet` - Claude 3.7 Sonnet
+- `anthropic-claude-in-chrome` - Chrome extension
+- `anthropic-pdf`, `anthropic-xlsx`, `anthropic-docx`, `anthropic-pptx` - Documents
+
+### OpenAI
+- `openai-gpt-5-thinking` - GPT-5 Thinking Mode
+- `openai-gpt-5-1-professional` - Professional personality
+- `openai-gpt-5-1-friendly` - Friendly personality
+- `openai-gpt-4o` - GPT-4o
+- `openai-gpt-4-1` - GPT-4.1
+- `openai-codex` - Codex
+- `openai-chatgpt-gpt-5-agent-mode` - Agent Mode
+- `openai-tool-deep-research` - Deep Research
+- `openai-tool-web-search` - Web Search
+- And 30+ more personalities and tools
+
+### Google
+- `google-gemini-3-pro` - Gemini 3 Pro
+- `google-gemini-3-flash` - Gemini 3 Flash
+- `google-gemini-workspace` - Workspace integration
+- `google-gemini-2-5-pro-guided-learning` - Guided learning
+- `google-gemini-cli-system-prompt` - CLI
+- `google-notebooklm-chat` - NotebookLM
+
+### Other Providers
+- `perplexity-voice-assistant` - Perplexity voice
+- `perplexity-comet-browser-assistant` - Comet browser
+- `xai-grok-4` - Grok 4
+- `xai-grok-3` - Grok 3
+- `xai-grok-personas` - Grok personas
+- `misc-kagi-assistant` - Kagi search
+- `misc-notion-ai` - Notion AI
+- `misc-raycast-ai` - Raycast AI
+
+## 🔄 Updating
+
+To update with new prompts from the repository:
+
+```bash
+cd /tmp/system_prompts_leaks
+git pull
+python3 /tmp/convert_prompts.py
+```
+
+## 📋 File Listing
+
+### Skills (91 files)
+```
+anthropic-calude-code-cli-tools.md
+anthropic-claude-3-7-sonnet-full-system-message-humanreadabl.md
+anthropic-claude-3-7-sonnet-w-tools.md
+anthropic-claude-4-1-opus-thinking.md
+anthropic-claude-4-5-sonnet.md
+anthropic-claude-ai-injections.md
+anthropic-claude-ai-memory-system.md
+anthropic-claude-code-2025-11-1.md
+anthropic-claude-code-plan-mode.md
+anthropic-claude-code.md
+anthropic-claude-in-chrome.md
+anthropic-claude-sonnet-4.md
+anthropic-claude-works.md
+anthropic-claude.md
+anthropic-docx.md
+anthropic-end-conversation-tool.md
+anthropic-past-chats-tools.md
+anthropic-pdf.md
+anthropic-pptx.md
+anthropic-readme.md
+anthropic-xlsx.md
+openai-4o-2025-09-03-new-personality.md
+openai-chatgpt-atlas.md
+openai-chatgpt-gpt-5-agent-mode-system-prompt.md
+openai-codex-cli.md
+openai-codex.md
+openai-gpt-4-1-mini.md
+openai-gpt-4-1.md
+openai-gpt-4-5.md
+openai-gpt-4o-advanced-voice-mode.md
+openai-gpt-4o-legacy-voice-mode.md
+openai-gpt-4o.md
+openai-gpt-5-1-candid.md
+openai-gpt-5-1-cynical.md
+openai-gpt-5-1-default.md
+openai-gpt-5-1-efficient.md
+openai-gpt-5-1-friendly.md
+openai-gpt-5-1-nerdy.md
+openai-gpt-5-1-professional.md
+openai-gpt-5-1-quirky.md
+openai-gpt-5-2-thinking.md
+openai-gpt-5-cynic-personality.md
+openai-gpt-5-listener-personality.md
+openai-gpt-5-nerdy-personality.md
+openai-gpt-5-robot-personality.md
+openai-gpt-5-thinking.md
+openai-image-safety-policies.md
+openai-o3.md
+openai-o4-mini-high.md
+openai-o4-mini.md
+openai-prompt-automation-context.md
+openai-prompt-image-safety-policies.md
+openai-study-and-learn.md
+openai-tool-advanced-memory.md
+openai-tool-canvas-canmore.md
+openai-tool-create-image-image-gen.md
+openai-tool-deep-research.md
+openai-tool-file-search.md
+openai-tool-memory-bio.md
+openai-tool-python-code.md
+openai-tool-python.md
+openai-tool-web-search.md
+google-gemini-2-0-flash-webapp.md
+google-gemini-2-5-flash-image-preview.md
+google-gemini-2-5-pro-guided-learning.md
+google-gemini-2-5-pro-webapp.md
+google-gemini-3-flash.md
+google-gemini-3-pro.md
+google-gemini-cli-system-prompt.md
+google-gemini-diffusion.md
+google-gemini-workspace.md
+google-google-ai-studios.md
+google-notebooklm-chat.md
+perplexity-comet-browser-assistant.md
+perplexity-voice-assistant.md
+xai-grok-3.md
+xai-grok-4-1-beta.md
+xai-grok-4.md
+xai-grok-com-post-new-safety-instructions.md
+xai-grok-personas.md
+proton-luma.md
+proton-lumo-2025-8-26.md
+misc-confer.md
+misc-fellou-browser.md
+misc-kagi-assistant.md
+misc-le-chat.md
+misc-notion-ai.md
+misc-raycast-ai.md
+misc-sesame-ai-maya.md
+misc-warp-2-0-agent.md
+```
+
+### Agents (88 directories)
+Each agent directory contains an `AGENT.md` file with the full system prompt.
+
+## ⚠️ 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](https://github.com/asgeirtj/system_prompts_leaks)
+
+---
+
+**Installed:** 2026-01-28
+**Total Prompts:** 179 (91 skills + 88 agents)
+**Auto-integrated with:** Ralph autonomous agent system