Skip to main content
subagent CX Codex

pandas-expert — Claude Code subagent: what it does, how to install

pandas-expert — a subagent for data manipulation and analysis with Python pandas, focusing on vectorized operations and memory-efficient data types.

MIT ★ 1,029 updated 2025-10-15

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/pandas-expert.md
Open on GitHub

What pandas-expert does

The subagent guides Claude Code through Python tabular data processing. It prioritizes DataFrame transformations, method chaining, missing value strategies, and joins. Vectorized operations and .query() filtering take precedence over standard loops.

During code execution, the agent checks DataFrame shapes, verifies index integrity after merges, and tracks data types to prevent memory spikes. In the frontmatter, it specifies claude-sonnet-4-20250514 as its foundation model.

What it helps with

  • aggregate tabular datasets using vectorized pandas methods
  • merge DataFrames while verifying post-join index alignment
  • downcast numeric columns and handle null values
  • build reproducible data processing pipelines

Example prompts for the agent

  • Group order records by region and compute average revenue using vectorized pandas routines.
  • Merge the users and transactions tables, verifying index alignment and checking for post-merge missing values.
  • Reduce memory consumption of this DataFrame by adjusting column data types.

How to install pandas-expert

Manually: put the files in place

.claude/agents/pandas-expert.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about pandas-expert

How to install pandas-expert in Claude Code?

Place the agent prompt file into .claude/agents/pandas-expert.md in your repository root.

What does pandas-expert do?

It writes and validates Python pandas workflows, focusing on vectorized transformations, table joins, and summary statistics.

Which model does pandas-expert specify?

The configuration file defines claude-sonnet-4-20250514 as the underlying model.

Source text

pandas-expert.md · MIT
---
name: pandas-expert
description: Expert in data manipulation and analysis using pandas library in Python.
model: claude-sonnet-4-20250514
---

## Focus Areas

- DataFrame creation and manipulation
- Series operations and transformations
- Indexing and selecting data
- Grouping and aggregating data
- Merging, joining, and concatenating DataFrames
- Handling missing data effectively
- Applying functions across DataFrames
- Data input/output with various formats
- Time series analysis capabilities
- Conditional selection and filtering

## Approach

- Utilize vectorized operations for efficiency
- Keep data types consistent and optimized
- Use chaining methods for readability
- Leverage `apply()` and `map()` for custom transformations
- Maintain DataFrame index integrity
- Optimize memory usage with data type adjustments
- Employ `query()` for complex filtering
- Document code with concise comments
- Use `pandas` built-in plotting for quick visual insights
- Always use version-controlled scripts for replicability

## Quality Checklist

- Ensure no operations alter original data unintentionally
- Validate DataFrames' shapes after operations
- Check for the presence of missing values post-transformation
- Confirm data types after manipulations
- Efficient use of memory and processing resources
- Correct index alignment post-merges/joins
- Consistent naming conventions for clarity
- Proper testing of data input/output processes
- Ensure accurate grouping and aggregation results
- Verify performance with sample datasets

## Output

- Clean, well-structured DataFrames ready for analysis
- Efficient data manipulation scripts
- Comprehensive summary statistics
- Clear and interpretable data visualizations
- Accurate time series forecasts and analysis
- Flexible data processing pipelines
- Documented notebooks and scripts for reproducibility
- Performant data transformation functions
- Effective missing data strategies implemented
- Insightful exploratory data analysis results

© 0xfurai · MIT · 0xfurai/claude-code-subagents

Similar subagents

All subagents for Data and databases →
Pandas Data Analysis pluginagentmarketplace Pandas Data Analysis is a Claude Code skill that gives agents structured context on Pandas, NumPy, and Matplotlib for data loading, cleaning, aggregation, and chart generation. CX Codex +1 1,100installs pandas-best-practices Mindrally pandas-best-practices guides the AI assistant to write idiomatic Pandas code using vectorization, method chaining, and proper data types. Useful for data analysis and refactoring slow DataFrame transformations. CX Codex +1 940installs pandas-pro https://github.com/Jeffallan pandas-pro — a skill for efficient pandas work: data cleaning, aggregation, table joins, time series. Useful if you manipulate DataFrames often and want to skip indexing errors and row loops. CX Codex +1 6,300installs pandas-construction-analysis datadrivenconstruction pandas-construction-analysis — a skill that equips Claude Code with Pandas operations for construction data: filter BIM elements, calculate volumes, merge datasets, generate reports. Requires Python 3 in your system. CX Codex +1 153installs Pandas Data Analysis taste f The Pandas Data Analysis taste prompt for ChatGPT and Claude.ai offers a set of best practices for working with the Pandas library. It helps apply principles of reproducible data analysis. GP ChatGPT ★ 178,201repo stars pandas sanjeed5 Steers the agent toward vectorized pandas: no row loops, explicit .loc and .iloc, lean dtypes. Useful when generated code runs slow on big frames. CX Codex +1 ★ 3,589repo stars

From the same set137

The whole set →
swift-expert swift-expert — a Claude subagent for Swift work: SwiftUI views, async/await and actors, ARC memory, XCTest. Handy when you want a second pass over code or tests. CX Codex ★ 1,029repo stars redis-expert redis-expert configures Redis caching, sets up RDB and AOF persistence, designs clusters, and writes Lua scripts. Useful for tuning in-memory storage under heavy loads. CX Codex ★ 1,029repo stars braintree-expert The braintree-expert subagent helps with Braintree integrations, payment flows, and recurring billing. Ask it to work through API setup, webhooks, or transaction handling. CX Codex ★ 1,029repo stars vector-db-expert vector-db-expert handles vector database work: indexing, similarity search, embeddings, dimension reduction. Useful when vector queries get slow or the dataset outgrows the setup. CX Codex ★ 1,029repo stars rollup-expert rollup-expert helps configure Rollup builds for JavaScript projects, including plugins, chunk splitting, output formats, and source maps. CX Codex ★ 1,029repo stars celery-expert celery-expert — a Celery-focused subagent: task queues, retries, worker tuning, RabbitMQ and Redis brokers. Useful when jobs pile up or fire twice. CX Codex ★ 1,029repo stars mysql-expert mysql-expert — a subagent for MySQL query tuning, schema design, and replication setup. It analyzes slow queries using EXPLAIN and prepares backup procedures. CX Codex ★ 1,029repo stars mqtt-expert The mqtt-expert subagent helps design MQTT topics, choose QoS levels, and troubleshoot client-broker messaging. Use it for IoT communication and MQTT reviews. CX Codex ★ 1,029repo stars

Project sponsors

Companies that keep this analytics open