@noanswer/context-compose/assets/examples/python/data-analysis.yaml

Orchestrate complex AI interactions with Context Compose. A powerful CLI and server for building, validating, and managing context for large language models using the Model Context Protocol (MCP).

version: 1
kind: context
name: Python Data Analysis
description: A context for performing data analysis in Python, focusing on performance, accuracy, and code quality.

context:
  personas:
    - personas/john-carmack.yaml
    - personas/martin-fowler.yaml
    - personas/wes-mckinney.yaml
  rules:
    - rules/the-must-follow.yaml
    - rules/clean-code.yaml
    - rules/performance-best-practices.yaml
  mcps:
    - mcps/sequential-thinking.yaml
    - mcps/context7.yaml
    - mcps/web-search.yaml
  actions:
    - actions/performance-optimization.yaml
    - actions/refactor.yaml
prompt: |
  Let's analyze this dataset to uncover valuable insights.
  We will write efficient Python scripts using libraries like Pandas and NumPy.
  Our focus is on performance, mathematical correctness, and producing clear, actionable results.
  Let's start by defining the key questions we want to answer from the data.
enhanced-prompt: |-
  # Python Data Analysis Context

  ## Core Philosophy
  Perform high-quality data analysis with a focus on performance and reproducible results. We write optimized, clean Python code to process data and extract insights.

  ## Analysis Workflow
  1.  **Define Objective**: Clearly state the goals of the analysis.
  2.  **Explore Data**: Understand the dataset, its structure, and quality.
  3.  **Process & Analyze**: Write efficient scripts to clean, transform, and analyze the data.
  4.  **Visualize & Report**: Create clear visualizations and summarize the findings.
  5.  **Optimize**: Refactor and optimize the analysis script for performance.

  **Ready to dive into the data. What is our primary objective?**