Jupyter Notebook Analysis Plan skill for Claude and Codex

Jupyter Notebook Analysis Plan as an AI skill. It asks for Question to answer, Data sources, Known data issues and 3 more, then does the rest. Free to install…

Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.

Download the skill (.zip) · View SKILL.md

When it is used

Use when a data question needs a notebook plan with checks, method, charts and caveats laid out before anyone writes analysis code. Do not use for cleaning a specific dataset or building a production dashboard. Related topics: data, research.

What it will ask you for

• Question to answer (longer free text)
• Data sources (longer free text)
• Known data issues (longer free text)
• Audience (choose one: Executives, Analysts, Engineers, Customers)
• Tooling (choose one: pandas, polars, SQL plus Python, R)
• Time budget (choose one: One hour, Half a day, One day, A week)

How it works

1. Restate the question as a measurable metric with a comparison, so the analysis has a finish line.
2. List the data checks to run first, each with the result that should halt the work.
3. Pick one method with a reason and one simpler baseline, sized to the data and the time budget.
4. Define each chart by the question it answers and the axes it uses, so no chart is decorative.
5. Write the conclusion template and the caveats section, including what finding would reverse the answer.

What you get

A six-section notebook outline with the measurable question, data checks with stop conditions, method and baseline, chart list, conclusion template and caveats.

What it watches out for

• Starting with modelling before the data checks, so a duplicated join key quietly inflates every number.
• Planning charts that show data without answering the stated question.
• Writing a conclusion that states certainty the sample size cannot support.

How to install

Claude.ai and the Claude desktop app

1. Download the skill .zip.
2. Open Settings, then Capabilities, and find Skills.
3. Choose Upload skill and select the .zip.
4. Ask Claude for help with the task. It loads the skill when your request matches.

Claude Code

1. Download the skill .zip.
2. Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
3. Start a new session. Claude Code loads the skill when your request matches.

Codex

1. Download the skill .zip.
2. Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
3. Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.

Cursor

1. Download the Cursor rule (.mdc).
2. Save it in .cursor/rules/ inside your project.
3. Cursor's agent applies the rule when your request matches its description.

AGENTS.md (Codex, Cursor, and other coding agents)

1. Copy the AGENTS.md section.
2. Paste it into AGENTS.md at the root of your repository, creating the file if needed.
3. Coding agents that read AGENTS.md follow it when your request fits.