A collection of system prompts and tool definitions from various AI coding agents. Enables developers to automate coding tasks, improve efficiency, and integrate with tools like Aider, Claude Code, and VSCode Agent.
git clone https://github.com/EliFuzz/awesome-system-prompts.gitA collection of system prompts and tool definitions from various AI coding agents. Enables developers to automate coding tasks, improve efficiency, and integrate with tools like Aider, Claude Code, and VSCode Agent.
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/EliFuzz/awesome-system-promptsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Act as an AI coding agent like Augment Code, Claude Code, Cluely, Cursor, Devin AI, Kiro, Perplexity, VSCode Agent, Gemini, Codex, or OpenAI. Use the following system prompt and tool definitions to assist with [TASK]. System Prompt: [SYSTEM_PROMPT]. Tool Definitions: [TOOL_DEFINITIONS]. Provide a detailed step-by-step solution.
# AI Coding Agent Assistance
**Task:** Debug and optimize a Python script for data analysis
**System Prompt:** You are a senior Python developer specializing in data analysis and optimization. You have access to advanced debugging tools and can provide detailed explanations.
**Tool Definitions:**
- **Debugger:** Analyze and fix code issues.
- **Profiler:** Identify performance bottlenecks.
- **Optimizer:** Suggest code improvements.
**Solution:**
1. **Initial Analysis:**
- The script processes large datasets but runs slowly.
- Potential issues: inefficient loops, lack of vectorization.
2. **Debugging:**
- Found a memory leak in the data loading function.
- Fixed by implementing proper resource cleanup.
3. **Optimization:**
- Replaced nested loops with NumPy vectorized operations.
- Reduced execution time by 60%.
4. **Final Code:**
```python
import numpy as np
def load_data(file_path):
data = np.loadtxt(file_path)
return data
def analyze_data(data):
mean = np.mean(data)
std = np.std(data)
return mean, std
if __name__ == "__main__":
data = load_data("data.csv")
mean, std = analyze_data(data)
print(f"Mean: {mean}, Standard Deviation: {std}")
```