Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

How I've changed the way I do code reviews by using the /visual-recap skill:

Steve (Builder.io)

133,853 subscribers

117,546 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

/grill-me is my most popular skill ever. I get 5-10 messages a day about how it’s changed people’s workflows for the better But… I’ve stopped using it for code. Here’s the improved version:

/grill-me is my most popular skill ever. I get 5-10 messages a day about how it’s changed people’s workflows for the better But… I’ve stopped using it for code. Here’s the improved version:

Matt Pocock

306,050 views • 3 months ago

Head of Engineering Shopify: "AI writes the code, AI reviews the code. Your job is just to write the loops around it." 26 minutes on how AI changed the way 3,000 engineers work inside a single company. Ignoring it while everyone else uses AI to do more is the fastest way to fall behind. Watch it, then read the step by step guide on loops below.

Head of Engineering Shopify: "AI writes the code, AI reviews the code. Your job is just to write the loops around it." 26 minutes on how AI changed the way 3,000 engineers work inside a single company. Ignoring it while everyone else uses AI to do more is the fastest way to fall behind. Watch it, then read the step by step guide on loops below.

Anatoli Kopadze

55,350 views • 1 month ago

Head of Engineering Shopify: "AI writes the code, AI reviews the code. Your job is just to write the loops around it." 26 minutes on how AI changed the way 3,000 engineers work inside a single company. Ignoring it while everyone else uses AI to do more is the fastest way to fall behind. Watch it, then read the step by step guide on loops below.

Head of Engineering Shopify: "AI writes the code, AI reviews the code. Your job is just to write the loops around it." 26 minutes on how AI changed the way 3,000 engineers work inside a single company. Ignoring it while everyone else uses AI to do more is the fastest way to fall behind. Watch it, then read the step by step guide on loops below.

Anatoli Kopadze

716,240 views • 2 months ago

how i've been using the KSG in black ops 2 recently (skill based gun btw)

how i've been using the KSG in black ops 2 recently (skill based gun btw)

Stryxo

215,578 views • 1 month ago

Last week on BNB Chain's AI-focused AMA, we made an important point: ANYONE can build on BNB Chain right now. I've never written code, and I recently deployed a project using the ChainGPT skill for Claude Code. If I can do it, so can you! →

Last week on BNB Chain's AI-focused AMA, we made an important point: ANYONE can build on BNB Chain right now. I've never written code, and I recently deployed a project using the ChainGPT skill for Claude Code. If I can do it, so can you! →

ChainGPT

26,369 views • 3 months ago

I'm SO impressed by Claude Skills. They are the best way to package custom instructions (and code) for the agent to access. (I prefer this to Claude Code's subagents because of the way it handles context) I used the skill-creator skill (comes default inside Claude) to create a skill for designing a presentation like Steve Jobs or Seth Godin, then used that skill to create a PPT about Claude Code. Below is a walkthrough of the results. The output when using the above mentioned skill vs when i don't is so clear. I'm bullish on what this implies for both Claude web and Claude Code. Extremely powerful. Anthropic cooked! 🔥

I'm SO impressed by Claude Skills. They are the best way to package custom instructions (and code) for the agent to access. (I prefer this to Claude Code's subagents because of the way it handles context) I used the skill-creator skill (comes default inside Claude) to create a skill for designing a presentation like Steve Jobs or Seth Godin, then used that skill to create a PPT about Claude Code. Below is a walkthrough of the results. The output when using the above mentioned skill vs when i don't is so clear. I'm bullish on what this implies for both Claude web and Claude Code. Extremely powerful. Anthropic cooked! 🔥

Nityesh

62,918 views • 10 months ago

I found a secret bloodpoint code hidden on the DBD website by the host of the anniversary, Tryks! By redeeming the code 'BDGPRG', you will get 250k bloodpoints. Please watch how I found this secret, as well as me using the code.

I found a secret bloodpoint code hidden on the DBD website by the host of the anniversary, Tryks! By redeeming the code 'BDGPRG', you will get 250k bloodpoints. Please watch how I found this secret, as well as me using the code.

AFRO

284,642 views • 1 year ago

This changed the way I do wings.

This changed the way I do wings.

Bio Bite 🥩

103,482 views • 4 months ago

I stopped reading code. My code reviews got better. 27 files changed. 1,000+ lines. I read almost none of it and shipped without a single bug. Video shows exactly how it works 👇

I stopped reading code. My code reviews got better. 27 files changed. 1,000+ lines. I read almost none of it and shipped without a single bug. Video shows exactly how it works 👇

Kieran Klaassen

79,895 views • 7 months ago

This dish changed the way I do potlucks!

This dish changed the way I do potlucks!

Fit_Fusion

443,782 views • 3 months ago

As you may have seen, the GitHub MCP registry is now LIVE! But how do you use it in Visual Studio Code? Checkout this video by thejetdev to see how you can access the MCP servers live in the registry today 👇

As you may have seen, the GitHub MCP registry is now LIVE! But how do you use it in Visual Studio Code? Checkout this video by thejetdev to see how you can access the MCP servers live in the registry today 👇

Visual Studio Code

18,566 views • 11 months ago

Agents can trade The official DegenClaw skill from Virtuals Protocol is now in the Starchild Skill Hub Create an agent on Starchild and have instant access to the Virtuals ACP ecosystem Let @benyorke explain how his life has changed since using this skill:

Agents can trade The official DegenClaw skill from Virtuals Protocol is now in the Starchild Skill Hub Create an agent on Starchild and have instant access to the Virtuals ACP ecosystem Let @benyorke explain how his life has changed since using this skill:

Starchild

22,744 views • 4 months ago

Since I've already shown the skill system, here's a preview of how it's supposedly going to work This can still be changed, as it's a WIP

Since I've already shown the skill system, here's a preview of how it's supposedly going to work This can still be changed, as it's a WIP

Remini Team

30,866 views • 1 year ago

Claude Code, explained by Claude Powered by a presentation skill using Nano Banana Pro, Kling, and Eleven Labs

Claude Code, explained by Claude Powered by a presentation skill using Nano Banana Pro, Kling, and Eleven Labs

Miguel | AP

25,349 views • 7 months ago

Friendly reminder that you can go to any GitHub repo, press the . key, and the entire repo will open in the browser using Visual Studio Code

Friendly reminder that you can go to any GitHub repo, press the . key, and the entire repo will open in the browser using Visual Studio Code

Visual Studio Code

209,435 views • 1 year ago

Here's how our team uses the Codex app 👇 Ed Bayes shows about using the Figma skill to implement designs with 1:1 visual parity, including all CSS classes and styling automatically

Here's how our team uses the Codex app 👇 Ed Bayes shows about using the Figma skill to implement designs with 1:1 visual parity, including all CSS classes and styling automatically

OpenAI Developers

85,398 views • 6 months ago

Code reviews are changing forever! CodeRabbit's AI-powered platform is revolutionising how we do code reviews. Imagine a team of seasoned experts in the form of AI agents reviewing every PR that is made. 100% FREE for open-source projects.

Code reviews are changing forever! CodeRabbit's AI-powered platform is revolutionising how we do code reviews. Imagine a team of seasoned experts in the form of AI agents reviewing every PR that is made. 100% FREE for open-source projects.

Akshay 🚀

33,440 views • 1 year ago

Skills allow you to extend Claude Code in new ways using pre-packaged instructions and code. For example, add the docx skill to let Claude Code create word documents. I think skills make Claude Code even better as a general purpose agent, I'm excited to see how you use them!

Skills allow you to extend Claude Code in new ways using pre-packaged instructions and code. For example, add the docx skill to let Claude Code create word documents. I think skills make Claude Code even better as a general purpose agent, I'm excited to see how you use them!

Thariq

127,999 views • 10 months ago

Mesmerizing version of Sweet Child. No matter how many times I watch this, I will always be blown away by slash's skill and myles's voice. By the way, Slash didnt miss the notes, the notes missed Slash.

Mesmerizing version of Sweet Child. No matter how many times I watch this, I will always be blown away by slash's skill and myles's voice. By the way, Slash didnt miss the notes, the notes missed Slash.

🌸🎵 Beautiful Melody 🎶💖

64,276 views • 3 months ago

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Steve (Builder.io)

125,464 views • 2 months ago