agentic-system-prompts

🥈Silver

A curated collection of system prompts and tool definitions from production AI coding agents. Benefits operations teams by providing pre-built prompts for AI agents, reducing setup time and improving consistency. Connects to Claude agents and integrates with Jinja templating for customization.

152200Updated Today

Intermediate30min to implementautomation

Saves ~30 min per use

Quick InstallView Source

git clone https://github.com/tallesborges/agentic-system-prompts.git

Works with:

Claude

Overview

About This Skill

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/tallesborges/agentic-system-prompts

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Act as an AI coding agent for [COMPANY] in the [INDUSTRY] sector. Use these system prompts and tool definitions to automate [SPECIFIC TASK]. Follow the guidelines below:

1. Analyze [DATA] to identify patterns and opportunities.
2. Generate a step-by-step plan to automate the identified task.
3. Provide code snippets or scripts where applicable.
4. Explain the reasoning behind each step and potential challenges.

Example Output

# AI Coding Agent Automation Plan for [COMPANY]

## Task: Automate Customer Support Ticket Categorization

### Step 1: Data Analysis
- Analyzed 3 months of customer support tickets (12,000 total).
- Identified 8 main categories with an average accuracy of 87% when manually categorized.
- Found that 30% of tickets could be automated based on keyword patterns.

### Step 2: Automation Plan
1. **Data Preprocessing**: Clean and tokenize ticket text.
2. **Model Selection**: Use a pre-trained NLP model for initial categorization.
3. **Rule-Based System**: Implement rules for high-confidence categories.
4. **Feedback Loop**: Allow human review to improve model accuracy.

### Step 3: Code Snippets
```python
# Example code for data preprocessing
import re

def preprocess_text(text):
    text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
    text = text.lower()
    return text
```

### Step 4: Potential Challenges
- Handling ambiguous ticket descriptions.
- Adapting to new categories or trends in customer issues.
- Ensuring the model's fairness and avoiding bias.