winkmaster

I built https://spritestudio.dev , a browser-based tool to generate and preview sprite sheets from text prompts. You can reorder frames, edit animations, and export directly.

Added Gemini NanoBanana Pro for faster, smarter generation. Would love feedback from devs – what features would actually make this useful in your pipeline?

a powerful alternative to platforms like Brilliant. With GenLesson, you can easily create automated, interactive courses tailored to your needs. It’s designed to make high-quality education more accessible, whether you’re a student, educator, or trainer by simplifying the process of lesson creation.

Upload screenshots and get reply suggestions to improve your conversations with your dating match and increase your chances of securing a date.

A Custom GPT that integrates with Github with read and write access for chatting with your repo, code contribution, issues resolution, and PR reviews all with ChatGPT.

An article explaining how it all works https://medium.com/@grace.lungu/gpt-repository-assistant-the...

Imagine having an engineer embedded in your repo with automated code contribution by raising PR from issues as tickets to pull request reviews. Say goodbye to boring chores and mundane tasks, using GPT-4, have an AI take the wheel and deliver faster.

Here's how to build a plugin that renders the code in the chat with ChatGPT.

Yeah haha, one more reason to use the bot and catch these mistakes

The bot is built to act as an extra team member dedicated to code review, these suggestions could then be discussed on the thread within the team and new commits can then be made

Most PR reviews contain comments and suggestion that could easily be automated with ChatGPT, and reduce the time it takes for a PR to be merged, which makes the team more productive.

The goal is to provide more context to the model and use the changes with the title and description of the PR to get a review, while asking for improvements and suggestions.

The examples on the site are meant to showcase the features and chatGPT capabilities being where it shines. Depending on the project's context the bot will make great reviews, chatGPT already does a good job at reviewing code if given enough context and that's what the bot is trying to achieve. In the future the bot can be onboarded to a codebase and the overall project for better review and possible code contribution.

The bot does not work like a linter or testing framework, these are suggestions that are subject to discussions, and the pull request is a great place to get reviews from the team

The bot is not meant to completely replace code review but to improve the code to be more production ready and catch any errors that might not be caught by the developers. In my experience more than 40% of code review comments relate to the specific changes and do not need a global context from the project.

The Github bot is built to review pull requests by analyzing the changes made and providing detailed comments on the changes, by suggesting improvements or highlighting vulnerabilities or bugs.

I think the bot should avoid unnecessary comments on every change.

I agree with you, I think the examples need to show the full potential of the bot. This being based on ChatGPT, the feedback can really be astonishing if the use case makes sense.

ChatCody is a new Github bot that utilizes the latest GPT model to streamline the code review process and boost team productivity. The bot can perform a variety of tasks to help software development teams save time with comments on both pull requests and issues.