Open
Conversation
Contributor
📝 WalkthroughWalkthroughA new utility link named "rule-gen" was added to the README.md file, describing an AI-powered tool that generates coding rules from codebases using Google Gemini, supporting multiple output formats without external dependencies. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (2)
README.md (2)
289-289: Consider adding npm package information.The npm package name is "rulegen-ai" while the GitHub repo is "rule-gen". This naming difference might make it harder for users to find and install the package. Consider either mentioning the npm package name in the description or adding a link to the npm package page alongside the GitHub link.
🔗 Suggested improvements
Option 1: Add npm package name to description
-- [rule-gen](https://github.com/nedcodes-ok/rule-gen) - Generate AI coding rules from your actual codebase using Google Gemini. Feeds your source files into Gemini's 1M token context window and produces project-specific .mdc rules. Supports Cursor, Claude Code, Copilot, and Windsurf output formats. Zero dependencies. +- [rule-gen](https://github.com/nedcodes-ok/rule-gen) - Generate AI coding rules from your actual codebase using Google Gemini. Feeds your source files into Gemini's 1M token context window and produces project-specific .mdc rules. Supports Cursor, Claude Code, Copilot, and Windsurf output formats. Zero dependencies. (`npm install -g rulegen-ai`)Option 2: Add npm package link
-- [rule-gen](https://github.com/nedcodes-ok/rule-gen) - Generate AI coding rules from your actual codebase using Google Gemini. Feeds your source files into Gemini's 1M token context window and produces project-specific .mdc rules. Supports Cursor, Claude Code, Copilot, and Windsurf output formats. Zero dependencies. +- [rule-gen](https://github.com/nedcodes-ok/rule-gen) ([npm](https://www.npmjs.com/package/rulegen-ai)) - Generate AI coding rules from your actual codebase using Google Gemini. Feeds your source files into Gemini's 1M token context window and produces project-specific .mdc rules. Supports Cursor, Claude Code, Copilot, and Windsurf output formats. Zero dependencies.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@README.md` at line 289, Update the README list entry that currently references "[rule-gen]" to also surface the npm package name and link: add the npm package name "rulegen-ai" in the description next to "rule-gen" and include a link to its npm page (e.g., https://www.npmjs.com/package/rulegen-ai) so users can find installation info; locate the list item containing the "[rule-gen]" text and append the npm name/link and a short install hint.
289-289: Clarify output format names for accuracy.The description mentions "Claude Code" but based on the PR objectives, the tool generates specific file formats: CLAUDE.md and AGENTS.md (in addition to .mdc for Cursor). Consider being more specific about the actual output file formats to help users understand what the tool produces.
📝 Suggested improvement for clarity
-- [rule-gen](https://github.com/nedcodes-ok/rule-gen) - Generate AI coding rules from your actual codebase using Google Gemini. Feeds your source files into Gemini's 1M token context window and produces project-specific .mdc rules. Supports Cursor, Claude Code, Copilot, and Windsurf output formats. Zero dependencies. +- [rule-gen](https://github.com/nedcodes-ok/rule-gen) - Generate AI coding rules from your actual codebase using Google Gemini. Feeds your source files into Gemini's 1M token context window and produces project-specific rules. Supports multiple output formats: .mdc (Cursor), CLAUDE.md, AGENTS.md, Copilot, and Windsurf. Zero dependencies.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@README.md` at line 289, Update the README description for rule-gen to list the actual output file formats rather than the ambiguous "Claude Code" term: change the sentence that currently mentions "Claude Code" to explicitly state the generated files (.mdc for Cursor, CLAUDE.md, and AGENTS.md) and keep the rest of the sentence about supported output formats (Cursor, Copilot, Windsurf) and zero dependencies intact so users know exactly which files the tool produces.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@README.md`:
- Line 289: Update the README list entry that currently references "[rule-gen]"
to also surface the npm package name and link: add the npm package name
"rulegen-ai" in the description next to "rule-gen" and include a link to its npm
page (e.g., https://www.npmjs.com/package/rulegen-ai) so users can find
installation info; locate the list item containing the "[rule-gen]" text and
append the npm name/link and a short install hint.
- Line 289: Update the README description for rule-gen to list the actual output
file formats rather than the ambiguous "Claude Code" term: change the sentence
that currently mentions "Claude Code" to explicitly state the generated files
(.mdc for Cursor, CLAUDE.md, and AGENTS.md) and keep the rest of the sentence
about supported output formats (Cursor, Copilot, Windsurf) and zero dependencies
intact so users know exactly which files the tool produces.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
rule-gen generates AI coding rules from your actual codebase using Google Gemini's 1M token context window.
Unlike template-based generators that just read package.json, rule-gen sends your source files to Gemini and produces rules based on patterns it finds in your code.
Summary by CodeRabbit