laughing code

244 posts

laughing code banner
laughing code

laughing code

@laughing_code

Indie Hacker Deconstruct money-making cases. Share amazing products.

Beigetreten Mart 2023
124 Folgt168 Follower
laughing code
laughing code@laughing_code·
today that can do exactly this for Claude Code.I recently needed to get some YouTube subtitles. I happened to see an iterated open-source skill from @dotey I just threw the GitHub link into OpenClaw, and it installed automatically! I tested it with the video Starter Story just dropped today: "I Make $250K/Month From 13 Businesses (After Losing Everything to AI)". It was awesome! I got all the captions with no login and no API key required. The only issue was that it sent me the subtitles in 30 different messages! My screen got totally spammed by an 11-minute video! So I started talking to OpenClaw, hoping it could just give me the file directly. After a lot of discussion, we finally got it working. Here is the practical process: 👇 x.com/laughing_code/…
宝玉@dotey

发布一个新的 Skill:baoyu-youtube-transcript 输入 YouTube URL,直接抓取视频字幕,生成带章节、发言人和封面图的文档,不需要任何 API Key。 【怎么用】 选择这个 Skill,把 YouTube 链接丢进去就行。支持完整链接、短链接、嵌入链接、Shorts 链接,甚至直接输入视频 ID 都可以。 默认输出带时间戳的 Markdown 格式,也可以导出 SRT 字幕文件。支持多语言,可以指定优先语言,也可以翻译成其他语言。 第一次抓取后会自动缓存原始数据,之后换格式、换参数都不用重新请求,秒出结果。 【工作原理】 底层调用的是 YouTube 的 InnerTube API,这是 YouTube 内部用来获取字幕数据的接口,公开可用但没有官方文档。好处是不需要 Google API Key,不需要 OAuth 认证,脚本直接发请求就能拿到字幕数据。 拿到原始字幕后,脚本会做一次智能断句处理:按句末标点(句号、问号、感叹号等)切分,跨字幕片段合并成完整句子,时间戳按字符长度等比分配,对中日韩文字做了专门适配。这样输出的文本是自然的句子,不是 YouTube 那种碎片化的逐行字幕。 【章节分割】 如果视频描述里有章节时间戳(比如 "0:00 Introduction"),脚本会自动解析,按章节把字幕分段,生成带目录的 Markdown。没有章节信息的视频,就按段落分组输出。 【说话人识别】 这是最有意思的部分。YouTube 字幕本身不带说话人信息,所以识别说话人需要 AI 后处理。 流程是这样的:先用 --speakers 参数抓取原始字幕,脚本会把视频元数据(标题、频道名、简介)和 SRT 格式的原始字幕一起输出到一个 Markdown 文件里。然后启动一个 AI 子代理(用 Claude Sonnet,够用且省成本),按预设的 Prompt 模板处理这个文件。 AI 识别说话人的逻辑分三层优先级:首先从元数据推断,视频标题通常包含嘉宾名字,频道名就是主持人;其次从对话内容判断,比如自我介绍、互相称呼;都不行就用通用标签(Speaker 1、Host 之类),保持全文一致。如果后面对话中才出现名字,会回溯更新前面所有标签。 处理完的输出是带说话人标签的分段对话,长独白会被切成 2-4 句一段,每段末尾带时间范围。 【缓存机制】 第一次运行会缓存四样东西:视频元数据(meta.json)、原始字幕片段(transcript-raw.json)、断句后的字幕(transcript-sentences.json)、视频封面图(cover.jpg)。之后不管切换格式还是重新生成,都直接用缓存,不再请求网络。加 --refresh 参数可以强制刷新。 安装命令: $ npx skills add jimliu/baoyu-skills --skill baoyu-youtube-transcript 项目地址:github.com/jimliu/baoyu-s…

English
1
0
2
45
laughing code
laughing code@laughing_code·
Congratulations to MuleRun on this exciting new opportunity! I know firsthand their professionalism and hard work. As one of their first creators, I have already withdrawn my earnings multiple times. MuleRun has successfully built a closed-loop business model connecting creators, users, and the platform. I hope more people get to use such a fantastic product!
laughing code tweet media
MuleRun@mulerun_ai

Introducing MuleRun 2.0. Your personal AI, act before you ask. It learns your habits, anticipates your needs, and works while you sleep — running 24/7 on your Personal Computer assigned to you alone. No complex setup. Just talk to it.

English
0
0
2
41
Mansi
Mansi@MeMansi12·
I launched my SaaS 6 months ago. Here's my MRR progress 👇 Month 1 : $0 Month 2 : $00 Month 3 : $000 Month 4 : $0000 Month 5 : $00000 Month 6 : $000000
English
595
171
5.4K
152.6K
laughing code
laughing code@laughing_code·
@gregisenberg This is exactly why 'keep building, keep learning' matters so much. The barrier to entry is dropping, but the vision and experience of the founder matter more than ever. 🛠️
English
0
0
0
7
GREG ISENBERG
GREG ISENBERG@gregisenberg·
ai is going to massively increase the number of one person companies within the next ~10 years - 1 one person $10b company - 10 one person $1b companies - 100 one person $100m companies - 1,000 one person $10m companies - 10,000 one person $1m companies
English
279
56
832
41.8K
laughing code
laughing code@laughing_code·
“pick a problem you personally have. you need to understand your user better than anyone else, and the easiest way to do that is to be your own user” Couldn't agree more! How many people just abandon their products right after launch and move on? If you don't even use it yourself, why would anyone else?
English
0
0
0
59
Tibo
Tibo@tibo_maker·
the best startup founders in 2026 won't be the best coders they'll be the best Product Managers here's the full playbook: 1. pick a problem you personally have. you need to understand your user better than anyone else, and the easiest way to do that is to be your own user 2. spin up a landing page with AI fast. make it about the pain and the fix, no fluff. and make signup 2 clicks max, remove every possible friction 3. learn to write specs, describe features and explain edge cases. that's all you really need now 4. let AI build the first version. your job is to direct, not develop 5. use whatever stack you're most comfortable with. just ship. don't overthink the tech decision - that's not your job anymore 6. host on the simplest platform possible - Vercel, Railway, whatever - don't touch servers 7. test thoroughly - especially edge cases. you're a QA now 8. charge from day 0. free users give you nothing but false hope 9. list your product on every directory you can find. it compounds your SEO and builds DR over time 10. start building in public. share the micro wins, the losses, everything. invite people to try it through DMs. I did this for all my products 11. do customer support yourself, always. redirect questions to your socials, never automate this. every support request is a product insight - that's why you do it yourself, always (I still do this for all 5 of my products) 12. automate everything else you do more than twice 13. improve one thing in your product every single day once users start coming in. watch your competitors' G2 and Trustpilot reviews closely for ideas 14. a PM's most important skill is deciding what NOT to build. for every feature request you get, say no to 9 of them - build less, but build it right 15. every week, build one free tool targeting a keyword that benefits you. it compounds over time 16. work your SEO early. build your affiliate setup early. only run paid acquisition after you're sure about PMF every day your only 2 priorities are: - get more users - and keep the ones you have that's it. everything else is noise
English
141
75
749
39.6K
laughing code
laughing code@laughing_code·
Here are the five projects I've compiled that made money during the OpenClaw craze. The highest-earning one reached a staggering $70,000 in just 30 days. I was truly amazed. Many other projects offered services related to deploying OpenClaw. Since OpenClaw is open-source, developers with the right skills made extensive modifications and adaptations. This is incredibly valuable. Additionally, despite AI assistance, compiling, writing, and proofreading these tweets consumed considerable time. Most crucially, video production has become a streamlined workflow where I input a single link to analyze websites, record voiceovers, and capture screen content. Even the subtitles required multiple refinements to achieve the current quality—over 30 test videos were generated for this purpose. Videos offer a more intuitive and clear presentation than images, and I hope this aids your understanding of the project. If you found this helpful, please give it a like. Feel free to leave a comment with any questions you may have.
laughing code tweet media
English
0
0
1
24
laughing code
laughing code@laughing_code·
NO.1 Claw Mart $79,000 Last 30 days ! ! Stop wasting weeks on prompt engineering and trial-and-error. Claw Mart is where battle-tested AI personas and skill packages live. From "AI CEOs" that manage code and comms to full YouTube toolkits and operational playbooks — these are configurations plucked from real, high-performing production setups. Don't build from scratch. Just plug in an operator's brain and start shipping today. author: @FelixCraftAI shopclawmart.com
English
1
0
1
42
laughing code
laughing code@laughing_code·
Top 5 Websites Making Money with OpenClaw: The #1 Site Earned $79,000 in Just 30 Days!! See If It Inspires You⬇️
English
1
0
1
48
laughing code
laughing code@laughing_code·
This opening effect will leave your audience in awe.
English
0
0
0
35
laughing code
laughing code@laughing_code·
@charlierward This video was incredibly insightful, especially the part about the future of artificial intelligence. I created an intro sequence—hope you like it!
English
0
0
0
23
Quanta Magazine
Quanta Magazine@QuantaMagazine·
A vast construction project is underway to bridge disparate fields of mathematics. Learn about the incredible Langlands program in our video explainer: youtube.com/watch?v=_bJeKU…
YouTube video
YouTube
English
2
23
138
14.3K
laughing code
laughing code@laughing_code·
@tibo_maker These insights are invaluable! Especially for beginners. I hope this effect helps you attract more attention.
English
0
0
0
14
Tibo
Tibo@tibo_maker·
Sharing the playbook that turned years of failure into an $8m acquisition and multiple $100k+ MRR SaaS creations actionable growth tactic behind-the-scene stories no sponsors • no ads • always free Join 60k+ founders & makers here → tmaker.io See you in your inbox 👇
English
4
0
1
2.5K
Tibo
Tibo@tibo_maker·
taking VC money is such a headache nobody tells you what actually happens after you take VC money. you stop building a company and start building a story for the next round projections have to be unrealistic, growth has to be aggressive "good business" stops being enough - it has to be venture-scale or you're failing by definition first-time founders chase funding because that's what X, TechCrunch, and every startup podcast celebrates. the raise IS the headline - the proof you made it they don't realize they just signed up for a completely different game I raised hundreds of thousands for my first two startups. both failed I'm now bootstrapping 5 SaaS products, trying to get each to $100K MRR. no board pressure, no forced narratives, 100% freedom - just building things that work for me VC money isn't bad. it's just a different game with different rules, and most founders just don't read them before signing the game you pick matters the most are you building a company or building a fundraising story?
Tibo tweet media
English
56
9
130
16.5K
laughing code
laughing code@laughing_code·
Lost count of how many times I’ve tweaked these parameters just to get that 'space-tearing' friction right. 🚀 ​At first, the particles looked like static; then they looked like noodles. After 50+ iterations, I think I finally nailed that hyperspace jump into a dead stop. ​That 'LAUGHING' moment at the end? That’s exactly how I felt when the code finally clicked. ​What do you think of the transition? Let me know! 👇
English
0
0
0
40
laughing code
laughing code@laughing_code·
@TTrimoreau yep! I didn't see any other products in your tweet. I saw it in your introduction. I noticed it didn't change the favicon, so I guessed it might still be in development. Looking forward to your new product.
English
1
0
1
15
Thomas Trimoreau
Thomas Trimoreau@TTrimoreau·
Hey founders, Looking to connect with people building in: 🛠️ SaaS 🚀 Tech 💻 Full Stack 🧠 AI tools for growth 📱 Product Development Drop what you're working on👇
English
243
0
221
13K
laughing code
laughing code@laughing_code·
x Compressing the video caused the display to differ slightly from what I saw. 😅
English
0
0
0
38
laughing code
laughing code@laughing_code·
Spacecraft shuttle effect with accompanying sound effects. Works well as an opening sequence for videos. Demo video:
English
1
0
1
76