HO13 — Interactive Data App

Hands-on portfolio project · Week 5 · Peer-reviewed · module M14. Part of the ForgeMind AI — AI Productivity Essentials course.

Goal

Done when: A small data-driven tool/app built with Claude Code

What to ship

Full source + README on what it does + how to run it.

Pick a problem statement

Choose one of these real use-cases — or bring your own (get it approved first):

1. Your Downloads folder is a graveyard of mystery files and you waste minutes hunting for things. Build a command-line tool with Claude Code that sorts and renames a messy folder by rules (by type, date or name pattern). Success: you point it at a folder, run one command, and it tidies everything, documented in a README with how to run it.

2. You inherit messy CSV exports with duplicates and inconsistent columns. Build a CLI tool with Claude Code that takes a CSV, dedupes rows, reformats the columns, and exports a clean file. Success: running one command on a real messy CSV produces a tidy output file, with the README explaining the input and how to run it.

3. You regularly have to resize a batch of images or convert a folder of files and doing it one by one is painful. Build a CLI batch processor with Claude Code that resizes images or converts files across a whole folder in one run. Success: one command processes the folder, with a README covering the input and usage.

4. Every week you hand-write a summary from the same kind of CSV. Build a CLI report generator with Claude Code that reads a CSV and writes a formatted summary (totals, top items, a short narrative). Success: running one command on the CSV produces a ready-to-share report, documented with what it takes in and how to run it.

5. You repeatedly grab the same data from a website or API and paste it somewhere. Build a fetch-and-save CLI script with Claude Code that pulls data from a source and stores it to a file on disk. Success: one command fetches the latest data and saves it locally, with a README explaining the source and how to run it.

Use it with your Claude.ai subscription

You don't need an API key, a credit card, or the terminal. Everything here runs on your normal Claude.ai subscription (Pro or Team) using Cowork — the workspace where you drag in files and Claude works on them for you.

This is the reference branch. Each samples/sample-01 … sample-05 folder has a finished README with:

1. A ready-made Cowork prompt you can copy, paste, and use immediately. No API key needed.
2. Sample files in sample_data/ to try it on.
3. A worked main.py reference script under Optional — automate it with code (advanced), for anyone who later wants to run it on their own computer. That path is never required.

Open the landing page (index.html) to browse all five samples.

How to use this repo

1. Click Use this template to create your own copy.
2. Pick one sample, follow its README with Cowork, then adapt the prompt to your own use case.
3. Replace this section of the README with: what you built, the problem it solves, and how you used it.

---

HO13 · Peer-reviewed · ForgeMind AI Course · module M14 (Week 5)

💡 Use your Claude.ai Pro plan wisely

The Pro plan has a usage limit that resets every few hours. A few habits make it stretch — and keep a mistake from burning your whole session:

• Use the example prompt in each sample's README — it's already written and tested. Don't reinvent it.
• One clear prompt beats lots of vague back-and-forth. Say what you want, with an example, in a single message.
• Start a new chat when you switch tasks. Long chats re-read every earlier message and use up your limit faster.
• Don't paste big files over and over. Paste once, then refer back to it.
• If something works, keep it. Tweak it rather than regenerate from scratch.
• Using Claude Code or Cowork? This repo's CLAUDE.md makes Claude follow these same rules automatically, and SKILL.md is a reusable "token-wise" skill.

If you do hit the limit, it resets after a few hours — nothing you've saved is lost.

Run it locally

This is a command-line tool — it runs in your terminal, not on the GitHub Pages page (Pages is static and can't run a CLI). To run it on your own machine:

# clone your copy of this repo, then from a sample folder:
pip install -r requirements.txt
python main.py <your-folder-or-file>

Each samples/sample-0X/ folder has its own README with the exact run command and sample input files to try it on.

Deploying to a server

You don't have to host this anywhere to pass — it runs locally. If you later want it running on a public server, the course covers that once: See the Week-6 deploy walkthrough.