From Track Workout to Ridgelines with Gemini CLI
Through a process of debugging and exploration with Gemini CLI, I turned a binary data file into a visualization that truly tells the story of my workout.
The Gemini CLI is a command-line tool for querying and editing codebases of any size. It can use tools like your shell, filesystem, Google Search, and has the ability to fetch websites and connect to MCP servers.
Here's how to install the tool (the free tier is very generous):
npm install -g @google/gemini-cli
gemini
Through a process of debugging and exploration with Gemini CLI, I turned a binary data file into a visualization that truly tells the story of my workout.
I wrote a language-agnostic script that creates a list of functions and classes in a codebase, improving Gemini CLI's ability to perform exploratory tasks and recognize existing code when implementing new functionality.
Teach Gemini CLI to write executable, single-file Python scripts with an inline dependency block, a technique that lets you run scripts without having to run pip install
first.
I started with a binary .FIT
file from my sports watch and used
Gemini CLI to parse it, explore the data, and generate insightful plots about my run.
Use npx to run the nightly and keep your stable gemini
version intact while letting you test the latest features.
Here are three useful keyboard shortcuts for the Gemini CLI that I have found to be particularly helpful.
This week, I used the Gemini CLI to generate scripts, and write code. Here are six practical tips that go beyond basic code generation.
A look under the hood of the Gemini CLI to understand how it learns about a codebase, from the initial snapshot to on-demand learning with tools.