feat: prompt user to generate repo-intel in skill

[avifenesh]

Summary

• Pre-check step offers to generate repo-intel for doc-drift detection
• Falls back gracefully when user declines

Test plan

• Skill works when user selects "Skip"

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, add credits to your account and enable them for code reviews in your settings.

[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 enhances the sync-docs skill by integrating a proactive mechanism to ensure the availability of repo-intel data. This data is crucial for effective documentation drift detection, improving the accuracy and utility of the skill. The change provides a user-friendly prompt to generate this intelligence, while also ensuring the skill remains functional even if the user opts out or generation fails.

Highlights

• Pre-check for Repo-Intel: Introduced a new pre-check step in the sync-docs skill that verifies the existence of a repo-intel map before analysis begins.
• User Prompt for Generation: If the repo-intel map is not found, the user is now prompted to generate it, with an explanation of its benefits for doc-drift detection.
• Graceful Fallback: The skill gracefully handles scenarios where the user declines to generate the repo-intel map or if the necessary binary for generation is unavailable, allowing the process to continue without it.

Activity

• No specific activity 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. ↩

[gemini-code-assist]

Code Review

This pull request adds a pre-check to prompt the user for generating repo-intel. The implementation is a good step, but I have a couple of suggestions for improvement. First, the logic for determining the state directory is duplicated and doesn't handle all cases (like the AI_STATE_DIR environment variable); it would be better to use the centralized function for this. Second, the error handling for repo-intel generation is too broad and silent; it should log errors to inform the user if something goes wrong after they've opted in.

[gemini-code-assist]

This implementation for determining the stateDir is a simplified version of the logic in lib/platform/state-dir.js. It is incorrect as it does not respect the AI_STATE_DIR environment variable, which can lead to inconsistent behavior.

To fix this and avoid code duplication, please use the centralized getStateDir function from lib/platform/state-dir.js.

Suggested change

	const stateDir = ['.claude', '.opencode', '.codex']
	.find(d => fs.existsSync(path.join(cwd, d))) || '.claude';
	const stateDir = require('../../lib/platform/state-dir').getStateDir(cwd);

[gemini-code-assist]

The catch block is too broad and silently ignores all errors, including failures in file system operations like mkdirSync or writeFileSync. If generating the repo-intel.json file fails after the user has opted in, they should be notified. The comment is also misleading as this block will catch any error within the try block, not just the binary being unavailable.

Suggested change

	} catch (e) {
	// Binary not available - proceed without
	}
	} catch (e) {
	// The operation to generate repo-intel failed. This can be due to the
	// binary not being available or a file system error. Proceeding without.
	console.error(`Failed to generate repo-intel: ${e.message}`);
	}