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.

Most AI coding demos stop at “here’s the code.” MiniMax Code kept going with its latest M3.1 Flash model: it built the game, tested the gameplay, fixed bugs, and iterated inside the same workflow. I gave it one simple idea: Build me a playable adveranturous pixel-style game from scratch.... What caught my attention wasn’t just that it generated the game. I could actually watch MiniMax Code work on the project, open the result in its built-in browser, test it, and then make changes to the same project based on my instructions, it also tests the gameplay itself, and catches bugs. For example, I could ask it to change the gameplay or UI, and it would go back into the project and implement the changes. That browser + coding workflow is what made it feel different from simply asking an AI to generate a piece of code. You can actually see the agent build, test, and iterate on the project. It’s like having an autonomous dev partner who builds, tests, and refines alongside you. Now in MiniMax Code you can build daily workflows with its latest M3.1 Flash model, and get 400 free credits every day. Try it cuz it's worth it.show more

Jay Bisen

49,969 subscribers

59,338 views • 8 days ago •via X (Twitter)

Science & Technology Gaming Education

Anya Rossi• Live Now

Private livecam show

34 Comments

Milano8 days ago

The real value isn't just generating a game, but having an agent that can keep improving it based on feedback. That's an interesting workflow.

Aiden Tech8 days ago

Great use case! The right AI tools can save time and improve creative workflows.

Md Santo8 days ago

Wow, that's seriously impressive! It's like having a whole development team in one AI. I'm definitely going to check out those free credits.

Alex hals8 days ago

M3.1 Flash looks promising, especially with the focus on building and testing in one place.

Ziven Tech8 days ago

Wow great

Raja Chichulkar8 days ago

The real value is in the iteration. Building something is one thing, improving it automatically is another.

Ma_AI_sha coredorX8 days ago

awesome

Holland Tech Marco8 days ago

This is the kind of practical AI innovation developers need right now.

Liam Holt8 days ago

Being able to test the result immediately and refine it with simple instructions is fantastic.

Flix Muller8 days ago

Turning a simple idea into a playable game with AI is seriously impressive.

Himanshu Chaure8 days ago

The future of coding is looking more interactive, iterative, and accessible than ever! 🚀

ZaraAI8 days ago

That's awesome

Easton Coleford8 days ago

Curious to see how this plays out.

Prime AI8 days ago

From an initial concept to a working game, this is a great demonstration of agentic coding.

kamran Hassan8 days ago

The combination of coding, testing, and iteration is what makes this interesting.

Abbas AI8 days ago

Amazing share

Alex hals8 days ago

Amazing

Dhruv kumar8 days ago

MiniMax Code is making game development more accessible to everyone.

Regaltos AI8 days ago

MiniMax Code is showing how AI can help turn creative ideas into working experiences, not just code on a screen.

Sakhil Khan8 days ago

AI development is becoming less about generating snippets and more about completing real projects.

Tom Rei8 days ago

Fewer manual steps and faster iterations make a big difference in development workflows.

Meenakshi Yadav8 days ago

AI that builds, tests, and fixes. That’s the real game changer.

Shamim Hossain8 days ago

That’s great

Harsh Pawar8 days ago

400 free credits every day makes this even more interesting. Can't wait to see what developers build with M3.1 Flash!

Eloise AI8 days ago

AI coding is evolving from generating code to actually building, testing, and fixing projects.

Al Tech World8 days ago

The built-in browser plus autonomous testing makes this much more than just code generation. MiniMax Code is taking things to another level!

Rishi8 days ago

This is what AI-powered development should look like. Building, testing, and fixing bugs in one workflow is impressive.

Pori8 days ago

Sound intriguing

Mostofa |AI Tools & News8 days ago

This is a great example of turning simple ideas into working projects.

kieran Drew8 days ago

Amazing share

Manish Kumar Shah8 days ago

I like that you can give feedback and watch the AI implement changes in the same project.

Safwan8 days ago

Imagine how much faster developers can experiment with ideas using this workflow.

Justin Brave💡8 days ago

Impressive share

marium8 days ago

That's awesome! It sounds like a huge leap forward for AI development. Having a partner that can actually build and test is really cool.

Related Videos

I gave an AI one instruction: “Build me a playable 3D game from scratch.” Then I let it cook. 👀 I tested Tencent Hy4 preview inside WorkBuddy, and it went way beyond just generating a few snippets of code. It could: → Plan the game structure → Generate the code across files → Create the UI and interactions → Debug problems along the way → Iterate on the project while keeping context That last part is what caught my attention. Hy4 preview is built for these long-horizon tasks, with 770B total parameters, 49B active parameters, and a 1M-token context window. It’s designed for coding agents, game development, tool use, research, and other workflows where the model has to actually do the work, not just answer a prompt. And right now, you can try Hy4 preview for free on WorkBuddy until September 10. If you want to see how far an AI agent can take a real project, try it yourself: See what you can build with it. Tencent AI

I gave an AI one instruction: “Build me a playable 3D game from scratch.” Then I let it cook. 👀 I tested Tencent Hy4 preview inside WorkBuddy, and it went way beyond just generating a few snippets of code. It could: → Plan the game structure → Generate the code across files → Create the UI and interactions → Debug problems along the way → Iterate on the project while keeping context That last part is what caught my attention. Hy4 preview is built for these long-horizon tasks, with 770B total parameters, 49B active parameters, and a 1M-token context window. It’s designed for coding agents, game development, tool use, research, and other workflows where the model has to actually do the work, not just answer a prompt. And right now, you can try Hy4 preview for free on WorkBuddy until September 10. If you want to see how far an AI agent can take a real project, try it yourself: See what you can build with it. Tencent AI

Toha Khan

66,214 views • 2 months ago

I built a playable zombie game with MiniMax Code, then used its new H3 Skill to generate the opening cinematic. The result feels less like a coding demo and more like the start of an actual game. H3 handles the story sequence. MiniMax Code handles the game. All from the same workflow.

I built a playable zombie game with MiniMax Code, then used its new H3 Skill to generate the opening cinematic. The result feels less like a coding demo and more like the start of an actual game. H3 handles the story sequence. MiniMax Code handles the game. All from the same workflow.

Farhan

56,401 views • 2 months ago

Meet MiniMax M3.1 Flash: The Model Behind Space Bunny Remember Space Bunny? The model behind it is officially revealed: MiniMax M3.1 Flash. For this experiment, I explored its coding capabilities through Fish Survival: From Aquarium to Ocean, a 3D browser game concept where players grow, avoid predators, and explore new underwater worlds. Beyond creative coding, MiniMax M3.1 Flash is built for complex software engineering and agentic tasks, combining performance with cost efficiency. According to MiniMax, it scores 73.7% on DeepSWE v1.1 and reduces overall agentic task costs by 70% compared with its predecessor. Ready to try it? Existing MiniMax Code subscribers New subscribers and M Plan upgrades: 50% off the first month through October 31. Explore MiniMax Code: Explore M Plans: #MiniMax #M31Flash #AICoding #AgenticAI

Meet MiniMax M3.1 Flash: The Model Behind Space Bunny Remember Space Bunny? The model behind it is officially revealed: MiniMax M3.1 Flash. For this experiment, I explored its coding capabilities through Fish Survival: From Aquarium to Ocean, a 3D browser game concept where players grow, avoid predators, and explore new underwater worlds. Beyond creative coding, MiniMax M3.1 Flash is built for complex software engineering and agentic tasks, combining performance with cost efficiency. According to MiniMax, it scores 73.7% on DeepSWE v1.1 and reduces overall agentic task costs by 70% compared with its predecessor. Ready to try it? Existing MiniMax Code subscribers New subscribers and M Plan upgrades: 50% off the first month through October 31. Explore MiniMax Code: Explore M Plans: #MiniMax #M31Flash #AICoding #AgenticAI

𝐒𝐢𝐦𝐚𝐧𝐭𝐨 । 𝐀𝐈 𝐍𝐞𝐰𝐬 𝐇𝐮𝐛

64,858 views • 8 days ago

I just built a playable car racing game using Step 5 Preview And the most interesting part wasn't just the code generation I tested StepFun's new flagship model on a real coding workflow, turning a simple game idea into an HTML browser game with moving traffic, car controls, speed tracking, and a scoring system What impressed me was seeing the development process turn into something I could actually open and play in Chrome Step 5 Preview is now available on OpenRouter, with integrations including Kilo Code, Cline, Hermes Agent, and OpenCode You can keep your existing coding workflow and simply switch models Try it here: StepFun

I just built a playable car racing game using Step 5 Preview And the most interesting part wasn't just the code generation I tested StepFun's new flagship model on a real coding workflow, turning a simple game idea into an HTML browser game with moving traffic, car controls, speed tracking, and a scoring system What impressed me was seeing the development process turn into something I could actually open and play in Chrome Step 5 Preview is now available on OpenRouter, with integrations including Kilo Code, Cline, Hermes Agent, and OpenCode You can keep your existing coding workflow and simply switch models Try it here: StepFun

Elara AI

40,054 views • 24 days ago

I wanted to see how far you can take the idea of “just describe a game.” So I gave Gear Zero a game concept in plain English and watched it go from an idea to a playable game in the browser. No game engine. No coding. No project files. No setup. Gear’s AI handles the planning, code, visuals, and level building and the first version can come together in around 20 minutes. But that’s not even the part I find most interesting. You can keep talking to it, ask for changes, refine the gameplay, and keep building on the same game instead of starting over every time. And because it’s designed for collaboration, other people can join the conversation and help shape the game too. That makes Gear Zero feel less like a one-click AI game generator and more like an AI-powered game-building workspace. If you’ve ever had a game idea but never opened a game engine, this is worth trying: Gear Zero

I wanted to see how far you can take the idea of “just describe a game.” So I gave Gear Zero a game concept in plain English and watched it go from an idea to a playable game in the browser. No game engine. No coding. No project files. No setup. Gear’s AI handles the planning, code, visuals, and level building and the first version can come together in around 20 minutes. But that’s not even the part I find most interesting. You can keep talking to it, ask for changes, refine the gameplay, and keep building on the same game instead of starting over every time. And because it’s designed for collaboration, other people can join the conversation and help shape the game too. That makes Gear Zero feel less like a one-click AI game generator and more like an AI-powered game-building workspace. If you’ve ever had a game idea but never opened a game engine, this is worth trying: Gear Zero

Md Riyazuddin

43,480 views • 2 months ago

🧵 1/7 I gave a Flash model a written spec for a 3D physics game. It broke the task into steps, wrote the code, used the tools, ran the project, and eventually produced a billiards game I could actually play. Ant Ling Ling-3.0-flash has 124B total parameters, but activates just 5.1B per token. That low activation count didn’t limit it to a simple one-shot demo. It kept a multi-stage 3D build moving from spec to playable result. This test made one thing clear: stop using your biggest model for every step of an agent workflow. The project may be complex. Most of the execution steps inside it don’t need a heavyweight planner to rethink everything from scratch. Ling-3.0-flash is built to execute. Here’s the full hands-on video: 👇

🧵 1/7 I gave a Flash model a written spec for a 3D physics game. It broke the task into steps, wrote the code, used the tools, ran the project, and eventually produced a billiards game I could actually play. Ant Ling Ling-3.0-flash has 124B total parameters, but activates just 5.1B per token. That low activation count didn’t limit it to a simple one-shot demo. It kept a multi-stage 3D build moving from spec to playable result. This test made one thing clear: stop using your biggest model for every step of an agent workflow. The project may be complex. Most of the execution steps inside it don’t need a heavyweight planner to rethink everything from scratch. Ling-3.0-flash is built to execute. Here’s the full hands-on video: 👇

Lonely

123,844 views • 3 months ago

I just watched AI build a game from a sentence. No Unity. No Unreal. No code. No files. I simply described the game I wanted to make, and Gear Zero planned it, coded it, created the visuals, and turned it into a playable game in my browser. But this is the part that got me 👇 You don’t just generate it and leave. You keep talking to Gear. Change things. Add features. Polish the game. Keep building. It feels less like using an AI game generator… …and more like having a game dev team you can talk to 24/7. The future of making games might actually look like this. Try it →

I just watched AI build a game from a sentence. No Unity. No Unreal. No code. No files. I simply described the game I wanted to make, and Gear Zero planned it, coded it, created the visuals, and turned it into a playable game in my browser. But this is the part that got me 👇 You don’t just generate it and leave. You keep talking to Gear. Change things. Add features. Polish the game. Keep building. It feels less like using an AI game generator… …and more like having a game dev team you can talk to 24/7. The future of making games might actually look like this. Try it →

RAVI KUMAR SAHU

30,938 views • 2 months ago

Many kept asking how I build my game with AI. Today I open-sourced the whole workspace. A year of building went into it: one repo that keeps project context, knowledge and workflows in one place, so Claude Code, Codex, Blender and Unity all work from the same memory. Every asset in my game goes through it. Full walkthrough and setup:

Many kept asking how I build my game with AI. Today I open-sourced the whole workspace. A year of building went into it: one repo that keeps project context, knowledge and workflows in one place, so Claude Code, Codex, Blender and Unity all work from the same memory. Every asset in my game goes through it. Full walkthrough and setup:

Stefan 3D AI

19,123 views • 1 month ago

Most AI models feel like assistants. MiniMax M3 felt like a teammate. I used Cursor + the MiniMax M3 API to build TweetGen — a tool that generates tweets instantly for any topic. What surprised me wasn’t just the speed, but how naturally M3 handled the whole workflow. It scaffolded the repo, wrote clean code, corrected itself, and kept context across iterations. I wasn’t nudging it line by line — it was committing changes like a real collaborator. Instead of “AI that helps you code,” it felt like “AI that codes with you.” That shift is huge.

Most AI models feel like assistants. MiniMax M3 felt like a teammate. I used Cursor + the MiniMax M3 API to build TweetGen — a tool that generates tweets instantly for any topic. What surprised me wasn’t just the speed, but how naturally M3 handled the whole workflow. It scaffolded the repo, wrote clean code, corrected itself, and kept context across iterations. I wasn’t nudging it line by line — it was committing changes like a real collaborator. Instead of “AI that helps you code,” it felt like “AI that codes with you.” That shift is huge.

Mr. Jason💡

12,832 views • 4 months ago

Wait… IQuest-Q1 actually built this from a written brief. I asked it to build Velora, an interactive SaaS analytics dashboard The result? A complete working dashboard I could click through, filter and explore. This is what makes IQuest-Q1 interesting. It’s built for more than standard code generation. IQuest-Q1 is a large, code-focused model from IQuest Research, and its capabilities go beyond simply writing code. It is being evaluated across: → Game & application development → 3D spatial generation → Code diagnosis & repair → Multimodal tasks with tools And that matters because real-world software development is rarely just about writing code. You need to build, debug, reason, use tools, and work across different environments. That’s why the Velora demo is interesting: I gave it a product brief, and it turned that idea into an interactive web experience. The goal is not just to generate code. It’s to handle more of the workflow from idea → implementation → working product. #coding #LLM

Wait… IQuest-Q1 actually built this from a written brief. I asked it to build Velora, an interactive SaaS analytics dashboard The result? A complete working dashboard I could click through, filter and explore. This is what makes IQuest-Q1 interesting. It’s built for more than standard code generation. IQuest-Q1 is a large, code-focused model from IQuest Research, and its capabilities go beyond simply writing code. It is being evaluated across: → Game & application development → 3D spatial generation → Code diagnosis & repair → Multimodal tasks with tools And that matters because real-world software development is rarely just about writing code. You need to build, debug, reason, use tools, and work across different environments. That’s why the Velora demo is interesting: I gave it a product brief, and it turned that idea into an interactive web experience. The goal is not just to generate code. It’s to handle more of the workflow from idea → implementation → working product. #coding #LLM

Atal

41,419 views • 1 month ago

I’ve been testing Qoder, and the biggest difference I noticed is that it feels less like asking an AI to write code and more like handing an AI agent an actual task. I started from Qoder’s new task screen, described the outcome I wanted, selected my workspace, model, and permissions, then let it run. What I could actually watch: = Qoder planning the task = Reading the project context = Executing commands and making file changes = Working through the steps instead of stopping at an answer = Verifying the result at the end The interesting part is that I can still watch the process, adjust the direction, pause it, or take over when needed. I also tested Qwen3.8-Flash, which is currently showing 0.0x Credits - meaning it’s free for all users through September 30. New users can get: - 300 Credits from the 14-day Pro trial - 300 additional Credits with my creator code Enter C46T6F here first: Then download Qoder: My first impression: the real value isn’t just generating code, it’s giving the agent an outcome and letting it actually work toward a verified result.

I’ve been testing Qoder, and the biggest difference I noticed is that it feels less like asking an AI to write code and more like handing an AI agent an actual task. I started from Qoder’s new task screen, described the outcome I wanted, selected my workspace, model, and permissions, then let it run. What I could actually watch: = Qoder planning the task = Reading the project context = Executing commands and making file changes = Working through the steps instead of stopping at an answer = Verifying the result at the end The interesting part is that I can still watch the process, adjust the direction, pause it, or take over when needed. I also tested Qwen3.8-Flash, which is currently showing 0.0x Credits - meaning it’s free for all users through September 30. New users can get: - 300 Credits from the 14-day Pro trial - 300 additional Credits with my creator code Enter C46T6F here first: Then download Qoder: My first impression: the real value isn’t just generating code, it’s giving the agent an outcome and letting it actually work toward a verified result.

Ethan Cole AI

251,655 views • 1 month ago

From a simple prompt to a polished game in minutes. Built this 3D pixel-style game while testing M3.1 Flash in the latest MCode. I could watch it create files and make changes in real time, then jump straight into the built-in browser to preview and refine the result. The refreshed UI makes the whole process much easier to follow, especially when the agent is working through multiple steps. What stood out most was how continuous the workflow felt: prompt → build → preview → tweak, all without breaking the flow. And M3.1 Flash handled the follow-ups really well. The final site came together surprisingly clean.

From a simple prompt to a polished game in minutes. Built this 3D pixel-style game while testing M3.1 Flash in the latest MCode. I could watch it create files and make changes in real time, then jump straight into the built-in browser to preview and refine the result. The refreshed UI makes the whole process much easier to follow, especially when the agent is working through multiple steps. What stood out most was how continuous the workflow felt: prompt → build → preview → tweak, all without breaking the flow. And M3.1 Flash handled the follow-ups really well. The final site came together surprisingly clean.

Jay Bisen

35,416 views • 26 days ago

Most AI models feel like assistants. MiniMax M3 felt like a teammate. I used Trae AI + the MiniMax M3 API to build HookCraft — a tool that takes one topic and instantly turns it into: → an X thread → a LinkedIn post → a TikTok script What surprised me wasn’t just the speed, but how naturally M3 handled the whole workflow. It scaffolded the repo, wrote clean code, corrected itself, and kept context across iterations. I wasn’t nudging it line by line — it was committing changes like a real collaborator. Instead of “AI that helps you code,” it felt like “AI that codes with you.” That shift is huge.

Most AI models feel like assistants. MiniMax M3 felt like a teammate. I used Trae AI + the MiniMax M3 API to build HookCraft — a tool that takes one topic and instantly turns it into: → an X thread → a LinkedIn post → a TikTok script What surprised me wasn’t just the speed, but how naturally M3 handled the whole workflow. It scaffolded the repo, wrote clean code, corrected itself, and kept context across iterations. I wasn’t nudging it line by line — it was committing changes like a real collaborator. Instead of “AI that helps you code,” it felt like “AI that codes with you.” That shift is huge.

Z-Coder

49,767 views • 4 months ago

Grok Build made this fun lil Mars simulator game for my nephew. I gave it simple prompts. It did the rest: wrote systems, built and tested it, studied gameplay, found and fixed bugs, then kept iterating. Grok Build is very powerful. It feels like having a game studio on demand.

Grok Build made this fun lil Mars simulator game for my nephew. I gave it simple prompts. It did the rest: wrote systems, built and tested it, studied gameplay, found and fixed bugs, then kept iterating. Grok Build is very powerful. It feels like having a game studio on demand.

DogeDesigner

594,356 views • 2 months ago

You don't need to know how to code to turn a messy spreadsheet into something you can actually use. I had an Excel file of 20 brands I want to pitch. I dropped it in a folder, opened Qoder, and typed one sentence: turn this into a dashboard with search. Then I watched. It read the file, made a plan, wrote the code, opened the page in the browser, and tested the search on its own. I added a /goal so it knew when it was done: every brand shows, search works. The model: Qwen3.8-Flash, free through September 30. Zero Credits for this whole run. Want to try it? Enter my code BPU7C6 at first, then download Qoder and sign in. You will get 600 Credits: 300 from the trial and 300 from my code.

Jay

143,443 views • 1 month ago

I tried to see how far I could push my current AI + 3D workflow and build a playable 3D game prototype in just 3 days😶 Not by asking AI to make the whole game in one prompt. I had my own idea, knew what I wanted to build, and used AI as a tool: - for concepting, - asset generation & texturing, - gameplay logic with the new UE 5.8 MCP + Claude Code. And honestly, it is crazy how far you can get now with the right workflow. Full video - #UE5 #ClaudeCode #AI3D #3DAI

I tried to see how far I could push my current AI + 3D workflow and build a playable 3D game prototype in just 3 days😶 Not by asking AI to make the whole game in one prompt. I had my own idea, knew what I wanted to build, and used AI as a tool: - for concepting, - asset generation & texturing, - gameplay logic with the new UE 5.8 MCP + Claude Code. And honestly, it is crazy how far you can get now with the right workflow. Full video - #UE5 #ClaudeCode #AI3D #3DAI

Stefan 3D AI

21,406 views • 4 months ago

what the hell did this free stealth model just build 💀 I asked Space Bunny, a Flash-level model, to make Minecraft in one HTML file and left it running it came back with a playable survival game inside my browser I could explore the generated world, break and place blocks, and switch items through the hotbar easily the best result I have got from a coding model on this test Space Bunny is free on OpenCode for the next week prompt below:

what the hell did this free stealth model just build 💀 I asked Space Bunny, a Flash-level model, to make Minecraft in one HTML file and left it running it came back with a playable survival game inside my browser I could explore the generated world, break and place blocks, and switch items through the hotbar easily the best result I have got from a coding model on this test Space Bunny is free on OpenCode for the next week prompt below:

Israfil

44,311 views • 1 month ago

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.

The Startup Ideas Podcast (SIP) 🧃

17,326 views • 1 month ago

There’s a free model that beats paid coding AIs. And it runs locally on your own machine. Here’s the exact “MiniMax M2.1 + NotebookLM + Gemini + Antigravity” workflow. → NotebookLM: paste your project goal + constraints + examples → Gemini: turn that into a clean spec and prompt → Antigravity: run the build loop with agent testing and terminal execution → MiniMax M2.1: generate clean code, tests, fixes, and refactors fast → Ship: deploy the landing page or automation and iterate weekly Save this video, you’ll build apps in minutes. Want the SOP? DM me. 💬

There’s a free model that beats paid coding AIs. And it runs locally on your own machine. Here’s the exact “MiniMax M2.1 + NotebookLM + Gemini + Antigravity” workflow. → NotebookLM: paste your project goal + constraints + examples → Gemini: turn that into a clean spec and prompt → Antigravity: run the build loop with agent testing and terminal execution → MiniMax M2.1: generate clean code, tests, fixes, and refactors fast → Ship: deploy the landing page or automation and iterate weekly Save this video, you’ll build apps in minutes. Want the SOP? DM me. 💬

Julian Goldie SEO

57,291 views • 10 months ago

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

Paras Chopra

216,705 views • 5 months ago