Explore, transform, and ship data in pure Python — Jupyter notebooks, pandas and Polars dataframes, Ibis for portable SQL, DuckDB in-process analytics, PandasAI natural-language queries, and Streamlit data apps
8 skills · Works with Claude Code, Codex, Cursor & more
Work effectively in Jupyter notebooks. Structures exploratory analysis, manages kernels and environments, uses magics and widgets, parameterizes runs with papermill, and keeps notebooks clean and reproducible.
mkdir -p ~/.claude/skills/jupyter && curl -fsSL https://raw.githubusercontent.com/TerminalSkills/skills/main/skills/jupyter/SKILL.md -o ~/.claude/skills/jupyter/SKILL.md Write expert pandas for cleaning, reshaping, and analysis. Handles merges, group-bys, pivots, time series, and vectorization, fixes slow or memory-heavy code, and produces tidy, reproducible DataFrames.
mkdir -p ~/.claude/skills/pandas-pro && curl -fsSL https://raw.githubusercontent.com/Jeffallan/claude-skills/HEAD/skills/pandas-pro/SKILL.md -o ~/.claude/skills/pandas-pro/SKILL.md Wrangle data at speed with Polars. Loads, filters, joins, groups, and reshapes large datasets using expressions and lazy frames, and migrates pandas code to faster Polars equivalents.
mkdir -p ~/.claude/skills/polars-dataframes && curl -fsSL https://raw.githubusercontent.com/foryourhealth111-pixel/Vibe-Skills/HEAD/bundled/skills/polars/SKILL.md -o ~/.claude/skills/polars-dataframes/SKILL.md Write analytics once and run it on any backend with Ibis. A pandas-like Python API that compiles to SQL for DuckDB, Postgres, BigQuery, Snowflake, Spark, and more — no rewriting queries per database.
mkdir -p ~/.claude/skills/ibis && curl -fsSL https://raw.githubusercontent.com/TerminalSkills/skills/main/skills/ibis/SKILL.md -o ~/.claude/skills/ibis/SKILL.md Run fast in-process analytics with DuckDB. Queries CSV, Parquet, and JSON directly, converts between formats, joins local files, and writes performant SQL for ad-hoc analysis without a server.
mkdir -p ~/.claude/skills/duckdb-analytics && curl -fsSL https://raw.githubusercontent.com/duckdb/duckdb-skills/HEAD/skills/duckdb-docs/SKILL.md -o ~/.claude/skills/duckdb-analytics/SKILL.md Query dataframes in natural language with PandasAI. Turns plain-English questions into pandas operations and charts, connects an LLM to your data, and adds a conversational layer to analysis workflows.
mkdir -p ~/.claude/skills/pandas-ai && curl -fsSL https://raw.githubusercontent.com/TerminalSkills/skills/main/skills/pandas-ai/SKILL.md -o ~/.claude/skills/pandas-ai/SKILL.md Build interactive data apps in pure Python with Streamlit. Turns scripts into dashboards with widgets, charts, and caching — no frontend code needed for internal tools, ML demos, and analytics apps.
mkdir -p ~/.claude/skills/streamlit && curl -fsSL https://raw.githubusercontent.com/TerminalSkills/skills/main/skills/streamlit/SKILL.md -o ~/.claude/skills/streamlit/SKILL.md Move and process columnar data at speed with Apache Arrow. Uses zero-copy in-memory format, Arrow Flight for fast transport, and interop across pandas, Polars, DuckDB, and Parquet without serialization overhead.
mkdir -p ~/.claude/skills/apache-arrow && curl -fsSL https://raw.githubusercontent.com/TerminalSkills/skills/main/skills/apache-arrow/SKILL.md -o ~/.claude/skills/apache-arrow/SKILL.md Engineer reliable AI agents — build on the Claude Agent SDK, coordinate teams with multi-agent patterns, give them memory, and keep them safe with mechanical guardrails and evaluation
Pick the right framework and ship agents fast — type-safe Python with Pydantic AI, multi-agent orchestration with OpenAI Agents SDK, Agno, and CrewAI, TypeScript graphs with LangGraph.js, and typed workflows with Mastra
Build AI-powered applications with RAG, multi-agent systems, prompt engineering, and MCP integrations