docs: Adds genkit-js skill as a starting point for Genkit agent skills.

[mbleigh]

Removes .guides content in favor of a new top-level skills directory which should allow us to integrate Genkit with https://skills.sh and the skills NPM package.

Checklist (if applicable):

• PR title is following https://www.conventionalcommits.org/en/v1.0.0/
• Tested (manually, unit tested, etc.)
• Docs updated (updated docs or a docs bug required)

[gemini-code-assist]

Summary of Changes

Hello @mbleigh, 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 refactors the project's documentation and skill structure by migrating from a .guides directory to a new skills directory. This change facilitates better integration with external skill platforms and introduces a dedicated genkit-js skill. It also updates core dependencies and enhances the documentation for using Gemini models within Genkit, providing more comprehensive guidance on their capabilities.

Highlights

• Documentation Restructuring: The .guides directory content has been removed and replaced with a new top-level skills directory, aiming for better integration with skills.sh and the skills NPM package.
• New Genkit JS Skill: A new genkit-js skill has been introduced as a starting point for Genkit agent skills, complete with its own SKILL.md and reference documentation.
• Gemini Model Updates: The default Gemini model in the setup guide has been updated from gemini-2.5-flash to gemini-3-flash-preview, and new documentation for Gemini models, including advanced features like 'Thinking Level' and 'Google Search Grounding', has been added.
• Dependency Updates: The next dependency has been updated across js/plugins/next/package.json and js/testapps/next/package.json, and the pnpm-lock.yaml file has been regenerated to reflect these and other dependency changes, including new sharp and @next/swc related entries.

🧠 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 refactors the documentation structure by moving .guides content into a new top-level skills directory, aiming to integrate Genkit with skills.sh and the skills NPM package. It also includes dependency updates for next and sharp packages. Overall, the changes improve the organization of skill-related documentation.

[gemini-code-assist]

The reference to references/nano-banana.md points to a file that was removed in this pull request. This creates a broken link in the documentation. Please either restore the nano-banana.md file in the references directory or update this reference to point to the correct, existing documentation for image generation.

[gemini-code-assist]

The next dependency has been changed from a caret range (^15.2.4) to a pinned version (15.3.6). While pinning ensures stability, it also means that minor and patch updates (which often include bug fixes and performance improvements) will not be automatically applied. Please confirm if this change in dependency management strategy is intentional for this package.

[gemini-code-assist]

The phrase "ALWAYS use this skill when writing Genkit code" is quite strong. While it's good to emphasize its importance, consider softening it to a strong recommendation, e.g., "It is highly recommended to use this skill..." or "This skill should be used...". This allows for more flexibility in edge cases where it might not strictly apply.

[gemini-code-assist]

The default model in the setup guide has been updated to gemini-3-flash-preview. As this is a preview model, it might be subject to more frequent changes or less stability compared to a generally available (GA) model. Consider recommending a stable GA model (e.g., gemini-2.5-flash or gemini-2.5-pro) as the default for a general setup guide, unless there's a strong reason to default to a preview version.

[ssbushi]

The refactor makes sense. Is genkit the right repo for these skills or do we want to move them to genkit-ai?