正在加载视频...

视频加载失败

How to make Claude Code 10x better: Connect it with a tool that reviews your code and generates prompts for Claude to fix any issues with it automatically. Here is what this looks like:

99,207 次观看 • 1 年前 •via X (Twitter)

24 条评论

Santiago 的头像
Santiago1 年前

I'm using @coderabbitai's CLI here. They are partnering with me on this post. This CLI is available and free for everyone. The CLI analyzes and provides suggestions for your entire repository using static analysis, shell commands, and a combination of AI models. It will look for potential issues, security vulnerabilities, duplicated code, unreadable messes, etc. This is pretty cool! It's one of the easiest ways to improve the result you get from AI coding agents.

Joseph 的头像
Joseph1 年前

How to make Cluad Coool 10x better --> have it download Codex and use that instead.

Roberto Selbach 的头像
Roberto Selbach1 年前

I've been having a good experience with Claude Code, but I did see improvements when I removed MCPs

Josh English 的头像
Josh English1 年前

This is brilliant. Adding Code Rabbit AI to my workflow first thing tomorrow

Csaba Kissi 的头像
Csaba Kissi1 年前

I think this should also work with Warp. I mean Warp + Coderabbit integration.

Matt Wesney 的头像
Matt Wesney1 年前

How to make claude code better: let claude code.

Nicholas Vermeulen 的头像
Nicholas Vermeulen1 年前

That's what I really need but I don't use claude. Can this be used with other models, and what about existing projects? I'm the only techie person in our family and I'm trying to follow along with AI as best as I can but there's so much noise it's hard to stay focused. I have a pretty large project I've been working on for months it's nowhere near close to being finished. My main problem is that the project is large and I haven't been able to figure out how to get any of these models to be able to take understand and navigate the project without changing stuff it shouldn't be changing or doing something it should have knew better not to.

AIxBlock 的头像
AIxBlock1 年前

Ship the system, not just the model.

UI King 👑... 的头像
UI King 👑...1 年前

This doesn't work for me though. I am on coderabbit pro trial and claude code pro, everything it tries to start coderabbit to do the review, it always fails. I always have to use code rabbit in ide review functionality and copy and paste issues. Same issue experience with cursor

Alex Secara 的头像
Alex Secara1 年前

game changer

yorence.sol 的头像
yorence.sol1 年前

Have you heard of @tonkotsu_ai

Jake Wojak 的头像
Jake Wojak1 年前

What’s Clod Code?

rafael skovron 的头像
rafael skovron1 年前

This is a good pattern. Code with one, review with another. Of course, if you have CodeQL and can do deeper quality reviews right in GitHub…

VibeCodeTeddy 的头像
VibeCodeTeddy1 年前

Now that’s a solid idea. Integrating code reviews with AI is the way to go.

Spanky McDoob 的头像
Spanky McDoob1 年前

Mcp for fixing your facial hair when? 🐐

M1NDB3ND3R 的头像
M1NDB3ND3R1 年前

This looks awesome! Do you know if this kind of integration would work with opencode, or is it only for Claude? Would love to try something similar with my workflow

Scalper Joe 🇺🇦💙🇺🇸 的头像
Scalper Joe 🇺🇦💙🇺🇸1 年前

So Claude Code is not so good?

Paco Muro 的头像
Paco Muro1 年前

To make it x100 better. Make it call codex

Blahblah 的头像
Blahblah1 年前

Didn’t know they had a cli now… guess it’s time I’ll give it a try

Dustin 的头像
Dustin1 年前

Integrating automatic code review and prompt generation with Claude could truly enhance its efficiency and accuracy. Excited to see how this evolves and improves the coding workflow.

John (JR) Renaldi 的头像
John (JR) Renaldi1 年前

Have you tried just doing this same thing with Gemini CLI or Codex CLI. I'm not sure Code Rabbit is the unlock here, as much as it is having a second set of eyes from another LLM to review.

Michael Fecher 的头像
Michael Fecher1 年前

how can you use claude code if you’re behind a corporate proxy and cant connect to

Cronos 的头像
Cronos1 年前

You just solved a 41 day problem for me.

Guillermo 的头像
Guillermo1 年前

nice!

相关视频

Anthropic just released a talk on building headless automation with Claude Code. Presented by Sid Bidasaria, Member of Technical Staff at Anthropic live at Code with Claude on May 22, 2025 in San Francisco. Here is what the talk covers. Headless mode lets you run Claude Code without a person actively typing prompts from inside an automated script. Instead of a live session, a script calls Claude with a pre-written instruction using the -p flag. This opens the door for Claude Code to become a piece of a much larger, automated process. In plain terms: Claude Code stops being a tool you use and starts being a service that runs on its own. What this unlocks: Scheduled tasks: Run Claude Code on a cron schedule without anyone at a keyboard. Fix linting errors across an entire codebase. Automatically. Overnight. CI/CD integration: Trigger Claude Code as a step in your build process. Open a PR. Claude reviews it, flags issues, and pushes fixes before a human ever looks at it. GitHub automation: A project manager comments "Claude fix this" on a GitHub issue. Claude reads the request, finds the code, writes the fix, and opens the PR. Multi-machine workflows: One orchestrator dispatches tasks to multiple Claude Code instances running in parallel across different repos simultaneously. When you combine headless mode, hooks, and GitHub Actions, development teams can automate tasks that usually eat up significant time freeing senior engineers to focus on architectural problems while Claude handles the repetitive ones. If you use Claude Code for anything beyond single sessions this talk is worth 20 minutes of your time.

Elias

14,096 次观看 • 5 个月前