feat: add proactive skill & tool suggestions to claude plugin

[mKeRix]

This change will utilize a UserPromptSubmit hook to proactively inject context referencing potentially relevant skills and tools as determined by the Haiku model. This should increase the auto-activation rate of these tools & decrease the time the (often more expensive) main session spends searching around.

[gemini-code-assist]

Summary of Changes

Hello @mKeRix, 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 significant enhancement to the Claude plugin by implementing an intelligent context injection system. Instead of a generic, static message, the system now dynamically analyzes user prompts using the Claude Agent SDK and the Haiku model to suggest relevant skills and tools. This change is designed to make the interaction more intuitive and efficient, ensuring that users receive tailored assistance and that the AI agent can more quickly identify and utilize appropriate functionalities.

Highlights

• Intelligent Context Injection: Replaces static context injection with a dynamic, LLM-powered system that suggests relevant skills and tools based on user prompts.
• UserPromptSubmit Hook: A new hook is utilized to proactively inject context, allowing for real-time, context-aware suggestions during user interaction.
• Claude Agent SDK Integration: The system leverages the Claude Agent SDK, specifically the Haiku model, for efficient and cost-effective evaluation and selection of suggestions.
• Improved User Experience: The goal is to increase the auto-activation rate of tools and decrease the time the main session spends searching, leading to a more fluid and helpful user experience.

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 significant and well-designed feature to provide intelligent, proactive suggestions for skills and tools. The use of a UserPromptSubmit hook powered by the Claude Agent SDK is a great approach to make the tool more context-aware and improve the user experience. The implementation is thorough, including new CLI commands, agent wrappers, utility functions for skill discovery, and comprehensive tests. The design and specification documents are also a valuable addition, clearly outlining the architecture and decisions made. My review includes a few suggestions for improving debuggability and maintainability. Overall, this is an excellent contribution.

[codecov-commenter]

Codecov Report

❌ Patch coverage is 62.01550% with 147 lines in your changes missing coverage. Please review.
✅ Project coverage is 54.50%. Comparing base (8a375b5) to head (e50e889).
⚠️ Report is 2 commits behind head on main.
✅ All tests successful. No failed tests found.

Files with missing lines	Patch %	Lines
src/utils/skill-discovery.ts	62.98%	67 Missing ⚠️
...rc/cli/commands/context/claude-usage-suggestion.ts	53.84%	42 Missing ⚠️
src/agent/suggestion.ts	63.10%	38 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main       #6      +/-   ##
==========================================
+ Coverage   53.36%   54.50%   +1.13%     
==========================================
  Files          33       37       +4     
  Lines        2361     2743     +382     
  Branches      156      195      +39     
==========================================
+ Hits         1260     1495     +235     
- Misses       1101     1248     +147     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[github-actions]

🎉 This PR is included in version 1.1.0 🎉

The release is available on:

• JSR.io
• GitHub release

Your semantic-release bot 📦🚀