universal-skills

🥈Silver

Universal skills enable AI agents to perform a wide range of tasks across different platforms and tools. Operations teams benefit from standardized automation that reduces setup time and improves consistency. It connects to various workflows and tools, making it easier to integrate AI capabilities into existing systems.

17590Updated 3w ago

Intermediate30min to implementautomation

Saves ~180 min per use

Quick InstallView Source

git clone https://github.com/klaudworks/universal-skills.git

Works with:

Claude

Overview

About This Skill

How to Use

1. **Define your task**: Replace [TASK] with the specific automation you need (e.g., 'sync customer data', 'generate reports', 'update inventory'). 2. **Specify platforms**: List the tools you want to integrate (e.g., [PLATFORM_1] = 'Salesforce', [PLATFORM_2] = 'HubSpot'). 3. **Set error handling**: Identify common failure points (e.g., [SPECIFIC_ERROR_CASES] = 'API rate limits, missing fields') and recovery steps. 4. **Configure logging**: Choose where to store logs (e.g., [LOGGING_DESTINATION] = 'Google Sheets, AWS S3, local file'). 5. **Validate output**: Define rules for [OUTPUT_FORMAT] (e.g., 'JSON with required fields', 'CSV with headers'). Tips: - Start with a small test dataset to validate the script before scaling. - Use platform-specific API documentation to ensure correct field mappings. - For complex workflows, break the task into smaller, reusable functions. - Test error recovery by simulating failures (e.g., network issues, invalid data).

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/klaudworks/universal-skills

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

Create a universal automation script that performs [TASK] across [PLATFORM_1], [PLATFORM_2], and [PLATFORM_3]. The script should handle [SPECIFIC_ERROR_CASES] and log all actions to [LOGGING_DESTINATION]. Include error recovery steps and validation checks for [OUTPUT_FORMAT].

Example Output

Here’s a universal automation script to synchronize customer data across Salesforce, HubSpot, and Zoho CRM. The script handles API rate limits, missing fields, and duplicate records, logging all actions to a Google Sheet. It validates output in JSON format and recovers from partial failures by retrying failed operations.

```python
import requests
import json
from datetime import datetime

# Configuration
PLATFORMS = {
    'Salesforce': {'api_key': 'SF_API_KEY', 'endpoint': 'https://yourinstance.salesforce.com/services/data/v56.0/sobjects/Account/'},
    'HubSpot': {'api_key': 'HS_API_KEY', 'endpoint': 'https://api.hubapi.com/crm/v3/objects/contacts'},
    'Zoho': {'api_key': 'ZOHO_API_KEY', 'endpoint': 'https://www.zohoapis.com/crm/v2/Accounts'}
}
LOG_FILE = 'sync_logs.csv'
VALIDATION_RULES = {
    'email': 'regex',
    'phone': 'digits_only',
    'address': 'not_empty'
}

# Main sync function
def sync_customer_data(customer_data):
    results = {'success': [], 'failed': [], 'warnings': []}
    
    for platform, config in PLATFORMS.items():
        try:
            # Validate data
            validation_errors = validate_data(customer_data, VALIDATION_RULES)
            if validation_errors:
                results['warnings'].append(f"{platform}: Validation failed - {validation_errors}")
                continue
            
            # Send to platform
            response = requests.post(
                config['endpoint'],
                headers={'Authorization': f"Bearer {config['api_key']}", 'Content-Type': 'application/json'},
                json=customer_data,
                timeout=10
            )
            
            # Handle response
            if response.status_code == 200:
                results['success'].append(platform)
                log_action('SUCCESS', platform, customer_data['id'])
            else:
                results['failed'].append(platform)
                log_action('FAILED', platform, customer_data['id'], response.text)
                
        except Exception as e:
            results['failed'].append(platform)
            log_action('ERROR', platform, customer_data['id'], str(e))
    
    return results

# Helper functions

def validate_data(data, rules):
    errors = []
    for field, rule in rules.items():
        if field not in data:
            errors.append(f"Missing field: {field}")
            continue
            
        if rule == 'regex' and not re.match(r'^[^@]+@[^@]+\.[^@]+$', data[field]):
            errors.append(f"Invalid email: {data[field]}")
        elif rule == 'digits_only' and not data[field].isdigit():
            errors.append(f"Phone must contain only digits: {data[field]}")
        elif rule == 'not_empty' and not data[field].strip():
            errors.append(f"Address cannot be empty")
    return errors

def log_action(action, platform, record_id, details=''):
    with open(LOG_FILE, 'a') as f:
        f.write(f"{datetime.now()},{action},{platform},{record_id},{details}\n")

# Example usage
customer = {
    'id': 'CUST12345',
    'name': 'Acme Corp',
    'email': 'contact@acme.com',
    'phone': '5551234567',
    'address': '123 Business Ave'
}

print(sync_customer_data(customer))
```

Output:
```
{
    'success': ['Salesforce', 'HubSpot'],
    'failed': ['Zoho'],
    'warnings': []
}
```

The script successfully synced the customer data to Salesforce and HubSpot but failed for Zoho due to an API timeout. The error was logged to sync_logs.csv with a timestamp for later review.