[Feat] Refactor Skills

[wangxingjun778]

1. New agent skills AutoSkills
2. Multi-skills support
3. Skills discovery (hybrid skill retriever)
4. Robust skill DAGs executor (container module)
5. LLMAgent integration as standard agent module
6. Add skill examples
7. Add UTs for skills
8. Add README

[gemini-code-assist]

Summary of Changes

Hello @wangxingjun778, 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 significantly enhances the agent's skill ecosystem by introducing a new AutoSkills system and integrating it with LLMAgent. It provides a robust set of new capabilities, particularly for advanced document processing with a dedicated DOCX manipulation framework, and expands into creative domains like frontend and canvas design. The changes also streamline the organization of skill examples and improve code quality checks.

Highlights

• New Agent Skills: Introduced a new AutoSkills agent skill concept and expanded the agent's capabilities with several new skills, including document co-authoring, frontend design, internal communications, and MCP server building.
• LLMAgent Integration: Integrated the new skills system with LLMAgent, providing a dedicated example script to demonstrate its usage for tasks like mock data generation.
• DOCX Manipulation Framework: Added a comprehensive framework for DOCX creation, editing, and analysis, including Python scripts for unpacking/packing Office files, XSD schemas for validation, and a library for managing comments and tracked changes.
• Skill Examples Restructuring: Refactored the organization of skill examples, moving them from projects/agent_skills to a new examples/skills/claude_skills directory, and updated pre-commit configurations to accommodate these changes.
• Enhanced Documentation and Testing: Included detailed documentation for each new skill, outlining their purpose, usage, and underlying principles, along with new validation tools for XML integrity and tracked changes.

🧠 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 is an impressive pull request that introduces a significant refactoring of agent skills and adds a wealth of new capabilities, particularly for document manipulation. The new structure under examples/skills/ is much clearer. The addition of detailed skills for docx, canvas-design, frontend-design, internal-comms, and mcp-builder is a huge step forward. The underlying Python code for OOXML manipulation is well-designed, robust, and includes thorough validation, which is excellent. The use of a line-tracking parser and detailed error reporting in the validation scripts is particularly noteworthy. I have one minor suggestion to improve the user experience of the new example script.