modelscope-agent icon indicating copy to clipboard operation
modelscope-agent copied to clipboard

Feat: support subfolder for skill_id

Open wangxingjun778 opened this issue 1 week ago • 1 comments

  1. In the form of: owner/skill_name/subfolder, e.g. ms-agent/skill_examples/pdf (refer to: https://modelscope.cn/models/ms-agent/skill_examples)

wangxingjun778 avatar Nov 19 '25 03:11 wangxingjun778

Summary of Changes

Hello @wangxingjun778, I'm Gemini Code Assist[^1]! 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 feature that allows users to specify a subfolder within a skill repository when referencing skill_ids. This enhancement provides greater flexibility and efficiency by enabling the system to download only the necessary sub-parts of a skill, rather than the entire repository. The change involves updating the core skill processing logic to parse the new skill_id format, modifying repository ID validation, and updating relevant documentation and examples to guide users on its adoption.

Highlights

  • Subfolder Support for Skill IDs: The system now recognizes skill_ids in the format owner/skill_name/subfolder, allowing for more granular skill referencing from the ModelScope Hub.
  • Targeted Skill Downloads: When a subfolder is specified in the skill_id, the snapshot_download function is now configured to download only the content within that specific subfolder, improving efficiency and reducing unnecessary data transfer.
  • Documentation Updates: Both English and Chinese documentation, along with the agent_skills example README, have been updated to clearly explain the new skill_id format and its usage.
  • Repository ID Validation Enhancement: The valid_repo_id utility function has been modified to correctly validate the new owner/skill_name/subfolder format, ensuring consistency across the system.
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 :thumbsup: and :thumbsdown: 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.

[^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[bot] avatar Nov 19 '25 03:11 gemini-code-assist[bot]