feat: add react-doctor skill to react category

[runkids]

What

add react-doctor skill

Skill Entry

[
  {
    "name": "react-doctor",
    "description": "Scans your React codebase for security, performance, correctness, and architecture issues. Outputs a 0-100 score with actionable diagnostics.",
    "source": "millionco/react-doctor",
    "skill": "react-doctor",
    "tags": [
      "react",
      "frontend"
    ]
  }
]

Checklist

• Added entry to the correct skills/*.json category file (see CONTRIBUTING.md)
• name is lowercase with hyphens only
• description is a clear one-liner
• source repo is publicly accessible and contains a valid SKILL.md
• No duplicate skill name in the hub
• Tags are 1-3 lowercase words (see CONTRIBUTING.md)

[gemini-code-assist]

Summary of Changes

Hello @runkids, 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 integrates the "react-doctor" skill into the system, expanding the available tools within the React category. This addition provides users with a new capability to analyze and assess the quality, security, and performance of their React projects.

Highlights

• New Skill Added: The "react-doctor" skill has been introduced to the React category. This skill is designed to scan React codebases for security, performance, correctness, and architecture issues, providing a 0-100 score with actionable diagnostics.

🧠 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

• skills/react.json
  • Added a new entry for the "react-doctor" skill, including its name, description, source, and relevant tags.

Activity

• No specific activity (comments, reviews, or progress updates) has been recorded for this pull request yet.

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. ↩

[github-actions]

Skill Audit Results

Audited 1 sources across 1 repos.

Source	Status	Risk
millionco/react-doctor	✅ Passed	LOW (15/100)

All skills passed the security audit.

Audit Details

millionco/react-doctor

Risk: LOW (15/100)

  HIGH: Dynamic code execution (eval/exec) detected (SKILL.md:26)
  "- **Security**: hardcoded secrets in client bundle, eval()"

[gemini-code-assist]

Code Review

This pull request adds the react-doctor skill to the react category. The implementation is straightforward and follows the project's contribution guidelines. I have one suggestion to improve the data by removing a redundant skill property, which I've detailed in a comment.

[gemini-code-assist]

The skill property appears to be redundant here, as its value is the same as name. The project's schema defines skill as an optional field for use in multi-skill repositories. Since this seems to be a single-skill repository, omitting this property would make the entry cleaner and more aligned with the schema's intent. The suggested change removes the skill property and the now-unnecessary trailing comma from the source property.

    "source": "millionco/react-doctor"