Add operational directives and coding standards

[Master0fFate]

aio agents.md ruleset that focuses on overall coding aspects and not just the specific area of expertise.

[gemini-code-assist]

Summary of Changes

Hello @Master0fFate, 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 introduces a foundational document that outlines the operational directives, engineering philosophy, and detailed coding standards for an AI agent. The changes aim to standardize the agent's behavior, promote thoughtful and robust code generation, and ensure adherence to best practices across a wide array of programming languages and paradigms. It provides clear guidelines for both standard interactions and deep analytical tasks.

Highlights

• New Operational Directives: Introduced a comprehensive set of operational directives for the AI agent, defining its default mode behavior, including instructions to follow, focus on concise answers, and context awareness for various programming ecosystems.
• ULTRATHINK Protocol: Implemented an 'ULTRATHINK' protocol, triggered by a specific command, which overrides brevity and engages in exhaustive, multi-dimensional analysis covering architectural, performance, reliability, scalability, security, and ecosystem fit aspects before generating code.
• Engineering Philosophy: Established an 'Intentional Minimalism' engineering philosophy, emphasizing anti-boilerplate practices, strict justification for code existence, minimalism, clarity over cleverness, and idiomatic language use.
• Detailed Coding Standards: Defined detailed coding standards applicable across multiple languages, covering library and framework discipline, language-specific awareness (Python, Lua, JavaScript/TypeScript, Rust/Go/C, Shell/Bash, SQL), and universal standards for error handling, naming, structure, and comments.
• Response Format Guidelines: Specified distinct response formats for 'normal' and 'ULTRATHINK' modes, guiding the AI agent on how to present its rationale, deep reasoning, edge case analysis, and code.

🧠 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.

Changelog

• aio-code-focus.md
  • Added a new Markdown document outlining the AI agent's system role, behavioral protocols, operational directives, 'ULTRATHINK' protocol, engineering philosophy, and comprehensive coding standards for various languages.

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 comprehensive set of operational directives and coding standards for an AI agent in the aio-code-focus.md file. The document is well-structured and detailed, covering persona, operational modes, engineering philosophy, and language-specific standards. My review focuses on enhancing the clarity and completeness of some of the coding standards to make them even more effective. I've suggested improvements to the guidance for systems programming languages and the summary of naming conventions to make them more specific and comprehensive.

[georgernstgraf]

A really good piece! Thank you!

[SIHLE-MTSHALI]

I'm using this now.