Pandas
Pandas is a Python library for loading, cleaning, transforming, and analyzing tabular data. It provides DataFrames for structured data manipulation, supports CSV, Excel, SQL, JSON, and Parquet formats, and offers powerful groupby aggregation, merge/join operations, time series resampling, and method chaining for buildi
Overview
Pandas is a foundational Python library integrated into AI agent workflows via the TerminalSkills/skills repository. This skill enables agents like Claude, Gemini, and Codex to perform structured data manipulation using DataFrames. It supports various file formats including CSV, Excel, SQL, and Parquet. Users can leverage the skill for complex data cleaning, merging datasets, and performing groupby aggregations. By utilizing method chaining and time series resampling, the skill facilitates sophisticated data analysis directly within agent environments. The TerminalSkills/skills repository, which currently holds 72 stars, provides the documentation and framework for implementing these Pandas-based operations. This integration allows for seamless transformation of tabular data into actionable insights during automated coding or analysis sessions.
Use Cases
Install Notes
# Review source first
open https://github.com/TerminalSkills/skills/blob/main/skills/pandas/SKILL.mdCopy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.
Security Notes
Users should ensure that any data files processed by the Pandas skill are from trusted sources to prevent injection or unauthorized data access. As this skill operates within AI agent environments like Claude or Codex, standard Python execution security protocols apply when handling external file formats such as Parquet or SQL databases.
Related Skills
Electron
vercel-labs/agent-browser
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "au
CodeQL
trailofbits/skills
Scans a codebase for security vulnerabilities using CodeQL's interprocedural data flow and taint tracking analysis. Triggers on "run codeql", "codeql scan", "codeql analysis", "build codeql database", or "find vulnerabilities with codeql". Supports "run all" (security-and-quality + security-experimental suites) and "im
Deep Agents Orchestration
langchain-ai/langchain-skills
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
LangChain Fundamentals
langchain-ai/langchain-skills
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
LangGraph Fundamentals
langchain-ai/langchain-skills
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
Ecosystem Primer
langchain-ai/langchain-skills
INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting point for up to date info on framework selection (LangChain vs LangGraph vs Deep Agents vs hybrid composition), agent patterns, install, environment setup, and whic