enhance: update pm-dev-frontend-cui skills and fix detect-change-type agent

[cuioss-oliver]

Summary

• pm-dev-frontend-cui skills: Fix ESLint v9→v10 reference, document ESLint v10 breaking changes (eslintrc removed), add Vitest recommendation for new projects, add TypeScript v7.0 ecosystem awareness, document Vite v8 Rolldown bundler
• detect-change-type-agent: Simplify decision tree (check analysis type last, reframe classification as "what is the end result?"), add post-check override in phase-3-outline for compound intent patterns (analyze+fix→enhancement)

Analysis Summary

All pm-dev-frontend-cui skills were analyzed for completeness, consistency, duplication, focus, and currency. The bundle is well-maintained with current version numbers (Node.js v24.14.0, ESLint v10, Jest v30, Vite v8, Prettier v3.8.1). Issues found were minor version references and missing documentation for recent ecosystem shifts.

Test plan

• ./pw verify pm-dev-frontend-cui — 54 tests pass, mypy clean, ruff clean
• Quality gate passes for all changed files

[gemini-code-assist]

Summary of Changes

Hello, 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 refines the automated classification of change types within the plan-marshall agent system, ensuring more precise categorization of user requests. Concurrently, it brings the pm-dev-frontend-cui skill documentation up-to-date with the latest advancements in JavaScript frontend development, providing clearer and more current guidance for project setup and tooling choices.

Highlights

• Enhanced Change Type Detection: The detect-change-type-agent has been updated with a simplified decision tree, a new classification question, and a post-check override mechanism to more accurately classify requests, especially those that combine analysis with action-oriented intents.
• Updated Frontend Development Standards: The pm-dev-frontend-cui skills documentation has been refreshed to reflect current frontend ecosystem trends, including updates for ESLint v10 (flat config), a stronger recommendation for Vitest in new projects, awareness of TypeScript 7.0, and details on Vite v8's new Rolldown bundler.

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.

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 valuable enhancements by updating the frontend development skills documentation and significantly improving the detect-change-type agent's logic for better clarity and robustness. The changes are well-structured and represent a positive step forward. I have identified a couple of minor opportunities for improvement to enhance consistency and classification accuracy, which are detailed in the review comments.