Agent-skill-creator is a meta-skill that enables Claude Code to autonomously build complete agents using Claude Skills. It automates the creation of intelligent agents for operations teams, reducing manual workflows and improving efficiency. The skill connects to Python-based workflows and supports Claude agents.
git clone https://github.com/FrancyJGLisboa/agent-skill-creator.gitAgent-skill-creator is a meta-skill that enables Claude Code to autonomously build complete agents using Claude Skills. It automates the creation of intelligent agents for operations teams, reducing manual workflows and improving efficiency. The skill connects to Python-based workflows and supports Claude agents.
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/FrancyJGLisboa/agent-skill-creatorCopy 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.
Create a complete agent with the following specifications: [AGENT_NAME], [PURPOSE], [SKILLS_REQUIRED]. The agent should be able to [TASKS]. Provide the full code and instructions for implementation.
# Agent: Market Research Analyst
## Purpose
This agent is designed to assist marketing teams in gathering and analyzing market research data to inform strategic decisions.
## Skills Required
- Data Collection
- Data Analysis
- Report Generation
- Presentation Creation
## Tasks
1. Gather market research data from specified sources.
2. Analyze the data to identify trends and insights.
3. Generate a comprehensive report summarizing the findings.
4. Create a presentation to visually represent the data and insights.
## Implementation
```python
# Import necessary libraries
import requests
import pandas as pd
import matplotlib.pyplot as plt
# Define the agent class
class MarketResearchAgent:
def __init__(self, data_sources, analysis_parameters):
self.data_sources = data_sources
self.analysis_parameters = analysis_parameters
def collect_data(self):
# Code to collect data from specified sources
data = []
for source in self.data_sources:
response = requests.get(source)
data.append(response.json())
return data
def analyze_data(self, data):
# Code to analyze the collected data
df = pd.DataFrame(data)
# Perform analysis based on parameters
trends = df.groupby('category').mean()
return trends
def generate_report(self, trends):
# Code to generate a report
report = f"Market Research Report\n\nTrends:\n{trends.to_string()}"
return report
def create_presentation(self, report):
# Code to create a presentation
plt.figure(figsize=(10, 6))
plt.plot(trends)
plt.title('Market Trends')
plt.xlabel('Categories')
plt.ylabel('Values')
plt.savefig('market_trends.png')
return 'market_trends.png'
# Example usage
if __name__ == "__main__":
data_sources = ["https://api.example.com/data1", "https://api.example.com/data2"]
analysis_parameters = {"group_by": "category", "metrics": ["mean", "median"]}
agent = MarketResearchAgent(data_sources, analysis_parameters)
data = agent.collect_data()
trends = agent.analyze_data(data)
report = agent.generate_report(trends)
presentation = agent.create_presentation(report)
print(report)
```AI assistant built for thoughtful, nuanced conversation
IronCalc is a spreadsheet engine and ecosystem
Service Management That Turns Chaos Into Control
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan