Skip to content
Get packs

Pandas Pro

Guides the agent to write efficient, validated pandas code for cleaning, merging, grouping and time series

Source Download skill
Repository
Jeffallan/claude-skills
Stars
12,176
Licence
MIT
Files
6 files

What it does

When installed, this skill makes an AI agent behave like an experienced pandas developer when you ask for help with tables of data (DataFrames). It pushes the agent toward fast vectorized code instead of slow row-by-row loops, and toward checking dtypes, missing values and row counts before and after each step. It also loads reference notes on topics like merging, groupby, cleaning and performance when relevant.

Great for

  • Data analysts cleaning or reshaping CSV or spreadsheet-style data in Python
  • Developers writing pandas pipelines who want validation checks and performance patterns built in
  • Anyone doing time series resampling, pivot tables or multi-key joins with pandas

Skip it if

  • Users who need a finished answer rather than code, since the skill's output format is code and it does not run analyses for you on its own; the agent still needs a Python environment with pandas to execute anything
  • Sensitive or regulated datasets, because the agent may write code that loads and transforms personal data without the user checking how it is handled
  • Work that is not pandas-based (for example Polars, Spark or SQL-only workflows)

Try asking

  • “Merge these two customer CSVs on customer_id and date, and tell me how many rows did not match”
  • “Clean this sales DataFrame: fill missing prices by interpolation and convert low-cardinality text columns to categories”
  • “Resample my web session log to daily totals and fill gaps with zero”
  • “Build a pivot table of revenue by region and product line with margins”
Step-by-step guide: how to use Pandas ProInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 6 original files, the MIT licence and an attribution note.

    pandas-pro.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip pandas-pro.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip pandas-pro.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent a sample of your data's columns and dtypes so it can choose the right methods and validation checks
  • Run the generated code on a copy of your data first, since some patterns (such as inplace drops and fillna with mode or median) change values
  • Ask the agent to explain its assumptions about missing values, because the skill's defaults fill gaps and that may not suit your analysis

What's inside

  • references/aggregation-groupby.md
  • references/data-cleaning.md
  • references/dataframe-operations.md
  • references/merging-joining.md
  • references/performance-optimization.md
  • SKILL.md

Redistributed unmodified from Jeffallan/claude-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.