feat: Add advanced data analysis pipeline recipe (#4990)

[ARYPROGRAMMER]

Summary

Advanced recipe that orchestrates data validation, cleaning, statistical analysis, and visualization through 4 specialized sub-recipes. Features 3 extensions, conditional logic, OS-compatible path handling, and comprehensive error recovery. Optimized for token reduction and faster execution.

Extensions usage:

1. Developer (Builtin)

• Type: builtin
• Name: developer
• Timeout: 600s (main), 300s (validator, analyzer, cleaner, generator)
• Purpose: File operations, data processing, script execution, running Python code
• Used in: All 5 recipes (main + all 4 sub-recipes)

2. Memory (Builtin)

• Type: builtin
• Name: memory
• Timeout: 300s
• Purpose: Storing analysis context and intermediate results across stages, passing validation results between sub-recipes
• Used in: Main recipe only

3. Filesystem (Stdio MCP Server)

• Type: stdio
• Name: filesystem
• Command: npx -y @modelcontextprotocol/server-filesystem
• Args: {{ output_dir }}
• Timeout: 300s
• Purpose: Enhanced filesystem operations for managing analysis outputs in the specified directory
• Used in: Main recipe only

Type of Change

• Feature
• Bug fix
• Refactor / Code quality
• Performance improvement
• Documentation
• Tests
• Security fix
• Build / Release
• Other (specify below)

Testing

Local Testing: Validated with CSV data - successfully executed validation and cleaning stages with sub-recipe orchestration working correctly.

Test Command:

goose run --recipe documentation/src/pages/recipes/data/recipes/data-analysis-pipeline.yaml \
  --params data_file=test_data.csv \
  --params analysis_type=quick \
  --params include_visualizations=false

Results:

• Recipe validation passed (all 5 YAML files)
• Sub-recipe orchestration working
• Parameter passing verified
• File generation confirmed (analyze_csv.py created)
• OS compatibility tested on Windows

Related Issues

Fixes #4990

Screenshots/Demos (for UX changes)

Before: N/A - New recipe submission

After: N/A - New recipe submission

Email: [email protected]

[github-actions]

❌ Recipe Validation Failed

Please fix the validation errors and push your changes:

✅ data-analysis-pipeline.yaml: VALID\n❌ chart-generator.yaml: INVALID\n\n✗ Unnecessary parameter definitions: analysis_results. Error: Unnecessary parameter definitions: analysis_results.\n\n❌ data-cleaner.yaml: INVALID\n\n✗ Unnecessary parameter definitions: validation_results. Error: Unnecessary parameter definitions: validation_results.\n\n✅ data-validator.yaml: VALID\n✅ statistical-analyzer.yaml: VALID\n

📚 Check our Recipe Guide for help with the correct format.

[github-actions]

🔍 Recipe Security Scan Results

❓ Status: UNKNOWN - Could not determine scan results

📊 Scan Summary:

• Total recipes scanned: 5

📋 Individual Recipe Results:
✅ Recipe 1: APPROVED (LOW risk)
✅ Recipe 2: APPROVED (LOW risk)
✅ Recipe 3: APPROVED (LOW risk)
✅ Recipe 4: APPROVED (LOW risk)
❓ Recipe 5: UNKNOWN (UNKNOWN risk)

🔗 View detailed scan results in the workflow artifacts.

[github-actions]

✅ Recipe Validation Passed

Your recipe(s) are valid and ready for review!

🔍 Next Steps:

1. Our team will review your recipe
2. If approved, we'll run a security scan
3. Once merged, you'll receive $10 in OpenRouter credits (if email provided)

Thanks for contributing to the goose Recipe Cookbook! 🎉

[github-actions]

🔍 Recipe Security Scan Results

✅ Status: APPROVED - All recipes passed security scan

📊 Scan Summary:

• Total recipes scanned: 5

📋 Individual Recipe Results:
✅ Recipe 1: APPROVED (LOW risk)
✅ Recipe 2: APPROVED (LOW risk)
✅ Recipe 3: APPROVED (LOW risk)
✅ Recipe 4: APPROVED (LOW risk)
✅ Recipe 5: APPROVED (LOW risk)

🔗 View detailed scan results in the workflow artifacts.

[ARYPROGRAMMER]

ready for immediate review and merging

[blackgirlbytes]

can you add a screenshot of a chart that this generated?

[ARYPROGRAMMER]

data was :

OrderID,Product,Quantity,Price,Customer,Date
1,Laptop,1,1200,Alice,2023-01-01
2,Mouse,2,25,Bob,2023-01-02
3,Keyboard,1,75,Alice,2023-01-01
4,Monitor,1,300,Charlie,2023-01-03
5,Mouse,2,25,Bob,2023-01-02
6,Webcam,1,50,,2023-01-04
7,Headphones,1,100,David,

output was:

analysis_report.md:

Data Analysis Report## Dataset: sample_sales_data.csv- Rows: 7- Columns: 6## Generated Charts- ✅ chart_1_bar.png: OrderID by Product- ✅ chart_2_line.png: Trends for OrderID, Quantity- ✅ chart_3_histogram.png: Distribution of OrderIDKey Statistics- Average OrderID: 4.00

Note: It took me a while to get the output to due multiple steps in this pipeline also i used bit more token consumption. Also installing pandas and data libraries will take some time. The agent currently handles that good.

can you add a screenshot of a chart that this generated?

[ARYPROGRAMMER]

also at all times: sorry to disturb you on weekend

[blackgirlbytes]

Interesting use case! thank you for your contribution.

[blackgirlbytes]

no worries. not bothering us at all. I was just explaining our slow response times. @ARYPROGRAMMER . We will be back to being active very soon!

[github-actions]

✅ $10 OpenRouter API key sent to [email protected]. Thanks for your contribution to the goose cookbook!