Buckets:

download
raw
3.41 kB
#!/usr/bin/env python3
"""
R CLI - Workflow Automation Example
Shows how to chain multiple skills together for complex tasks.
"""
from r_cli.core.agent import Agent
def analyze_csv_and_report(csv_path: str, output_pdf: str):
"""
Workflow: Analyze CSV data and generate a PDF report.
1. Run SQL queries on the CSV
2. Generate summary statistics
3. Create a PDF report
"""
agent = Agent()
agent.load_skills()
# Step 1: Get basic stats
print("Step 1: Analyzing data...")
stats = agent.run_skill_directly(
"sql",
query="SELECT COUNT(*) as total_rows FROM data",
csv=csv_path,
)
# Step 2: Get column info
columns = agent.run_skill_directly(
"sql",
query="SELECT * FROM data LIMIT 1",
csv=csv_path,
)
# Step 3: Generate report content
report_content = f"""# Data Analysis Report
## Overview
- **File**: {csv_path}
- **Statistics**: {stats}
## Sample Data
```
{columns}
```
## Generated by R CLI
This report was automatically generated using the SQL and PDF skills.
"""
# Step 4: Create PDF
print("Step 2: Generating PDF report...")
result = agent.run_skill_directly(
"pdf",
content=report_content,
output=output_pdf,
title="Data Analysis Report",
)
print(f"Report saved to: {output_pdf}")
return result
def backup_and_archive(source_dir: str, backup_name: str):
"""
Workflow: Create a backup archive with git info.
1. Get git status
2. Create archive
3. Log the backup
"""
agent = Agent()
agent.load_skills()
# Step 1: Get git info
print("Getting git status...")
git_info = agent.run_skill_directly(
"git",
action="status",
path=source_dir,
)
# Step 2: Create archive
print("Creating archive...")
archive_result = agent.run_skill_directly(
"archive",
action="create",
source=source_dir,
output=f"{backup_name}.zip",
format="zip",
)
# Step 3: Get timestamp
timestamp = agent.run_skill_directly(
"datetime",
action="now",
format="%Y-%m-%d %H:%M:%S",
)
print(f"Backup created: {backup_name}.zip at {timestamp}")
print(f"Git status: {git_info[:100]}...")
return archive_result
def scrape_and_summarize(url: str):
"""
Workflow: Scrape a webpage and create a summary.
1. Fetch webpage content
2. Extract text
3. Save to markdown
"""
agent = Agent()
agent.load_skills()
# Step 1: Fetch page
print(f"Fetching {url}...")
content = agent.run_skill_directly(
"web",
action="fetch",
url=url,
)
# Step 2: Save as markdown
print("Saving content...")
result = agent.run_skill_directly(
"fs",
action="write",
path="scraped_content.md",
content=f"# Scraped from {url}\n\n{content[:2000]}...",
)
print("Content saved to scraped_content.md")
return result
if __name__ == "__main__":
print("R CLI Workflow Examples")
print("=" * 40)
print("\nAvailable workflows:")
print("1. analyze_csv_and_report(csv_path, output_pdf)")
print("2. backup_and_archive(source_dir, backup_name)")
print("3. scrape_and_summarize(url)")
print("\nExample:")
print(' analyze_csv_and_report("data.csv", "report.pdf")')

Xet Storage Details

Size:
3.41 kB
·
Xet hash:
ad01f7ef1da092f355cd072846a567aa5f7cf2d4ec0b3afde7d156bbeb10c481

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.