Adding a script to count tokens used by a skill

[joehan]

Description

Useful little utility to check whether a skill is the appropriate token length.

To use it, npm i in the skill-token-counter directory, set the GEMINI_API_KEY env var, and then npm run count ../../skills/firestore-basics

Scenarios Tested

[gemini-code-assist]

Summary of Changes

Hello @joehan, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request delivers a valuable new developer tool: a TypeScript-based script for precisely measuring the token length of skill definitions. By analyzing SKILL.md content and associated reference files using the Gemini API, it helps authors ensure their skills remain within token limits, streamlining the development and deployment of AI-powered features.

Highlights

• New Token Counting Utility: Introduces a new TypeScript script (skill-token-counter) to calculate the token usage of a skill definition.
• Comprehensive Token Analysis: The script counts tokens for both the frontmatter and body of SKILL.md, as well as any markdown files found in the references subdirectory within a given skill directory.
• Gemini API Integration: Utilizes the @google/genai library to interact with the Gemini API for accurate token counting, requiring an API key (GEMINI_API_KEY or GOOGLE_API_KEY).
• Easy Execution: Provides clear instructions for installation (npm i) and execution (npm run count <path-to-skill-dir>), emphasizing the need for an API key.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a useful utility script for counting tokens in a skill definition. The script is well-structured, but it contains a critical bug in how it interacts with the Google GenAI SDK, which will prevent it from running correctly. I've provided a comment with a suggested fix for the client initialization and token counting logic. I've also suggested a performance improvement to process reference files in parallel, which will make the script faster when dealing with multiple files. The package and TypeScript configurations are well-defined.