Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Most people don't know the difference between skills, subagents, and MCPs. Here's the simple breakdown: Skills: Written guides that tell the LLM exactly how to do a task "Analyze spreadsheets this way" or "write emails in this voice" Reusable. Consistent output. Subagents: Extra copies of the LLM, each with... show more

The Startup Ideas Podcast (SIP) 🧃

39,812 subscribers

36,675 Aufrufe • vor 7 Monaten •via X (Twitter)

Bildung Nachrichten & Politik Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

OpenAI just launched "agent skills", their version of what Claude calls skills. It finally clicked to me how these agents, skills and MCPs will work together. Basically, a skill is just the recipe for how something should be done, subagents are extra hands you spin up when the task is big, and MCPs are how the agent actually touches real systems like your repo or dashboards. Imagine a solo graphic designer setting up a “launch assets” skill: the skill defines brand rules, layouts, and export formats, sub-agents generate variations for social, web, and email in parallel, and MCPs pull from the actual Figma library and push finished assets into the client’s folder. Cool to see this kind of structure emerge in both OpenAI and Claude.... it feels like an early step toward a common way of building workflows that are reliable, composable, and actually useful in real work. I also gave away a trend, a business idea, an app ive been using for 14 years and more. (i answer every comment there) Happy building, my friends. Btw, what should I cover next? Or tag who should come on the show. Have a creative day.

GREG ISENBERG

70,525 Aufrufe • vor 8 Monaten

Claude Skills might be the biggest upgrade to AI agents so far! Some say it's even bigger than MCP. I've been testing skills for the past 3-4 days, and they're solving a problem most people don't talk about: agents just keep forgetting everything. In this video, I'll share everything I've learned so far. It covers: > The core idea (skills as SOPs for agents) > Anatomy of a skill > Skills vs. MCP vs. Projects vs. Subagents > Building your own skill > Hands-on example Skills are the early signs of continual learning, and they can change how we work with agents forever! Here's everything you need to know:

Claude Skills might be the biggest upgrade to AI agents so far! Some say it's even bigger than MCP. I've been testing skills for the past 3-4 days, and they're solving a problem most people don't talk about: agents just keep forgetting everything. In this video, I'll share everything I've learned so far. It covers: > The core idea (skills as SOPs for agents) > Anatomy of a skill > Skills vs. MCP vs. Projects vs. Subagents > Building your own skill > Hands-on example Skills are the early signs of continual learning, and they can change how we work with agents forever! Here's everything you need to know:

Akshay 🚀

286,274 Aufrufe • vor 10 Monaten

Introducing Claude Code Hook - Context Timeline (Saving this to try later) Install with: npx claude-code-templates@latest --hook monitoring/context-timeline Managing the context window and the subagents running in Claude Code is hard to keep track of That's why I built this hook... It starts the moment you open a session and shows a timeline with the main agent's context window and how subagents start working in their own separate context Every subagent you have running will show up in real time This way you can manage the context and the subagents you run, and see everything in a much simpler way than in the console

Introducing Claude Code Hook - Context Timeline (Saving this to try later) Install with: npx claude-code-templates@latest --hook monitoring/context-timeline Managing the context window and the subagents running in Claude Code is hard to keep track of That's why I built this hook... It starts the moment you open a session and shows a timeline with the main agent's context window and how subagents start working in their own separate context Every subagent you have running will show up in real time This way you can manage the context and the subagents you run, and see everything in a much simpler way than in the console

Daniel San

51,706 Aufrufe • vor 4 Monaten

IF YOU'RE NEW TO CLAUDE CODE - WATCH THIS BEFORE ANYTHING ELSE > most people open it and start chatting they're using 20% of what it can actually do this short guide covers everything that actually matters: > how skills work and how to use them > subagents - what they are and why they change everything > connecting MCP servers in 5 minutes > a real professional setup you can copy immediately 30 minutes. you'll understand more than most people who've been using it for months save this. watch it today. 👇

IF YOU'RE NEW TO CLAUDE CODE - WATCH THIS BEFORE ANYTHING ELSE > most people open it and start chatting they're using 20% of what it can actually do this short guide covers everything that actually matters: > how skills work and how to use them > subagents - what they are and why they change everything > connecting MCP servers in 5 minutes > a real professional setup you can copy immediately 30 minutes. you'll understand more than most people who've been using it for months save this. watch it today. 👇

Mr. Buzzoni

51,156 Aufrufe • vor 4 Monaten

Boris Cherny: "I don't write code anymore, I just prompt with Claude" he spent 57 minutes explaining exactly where this is all going here's what stood out: > Claude Code grew faster than anyone at Anthropic expected > AI agents are moving beyond coding into every industry > running 1,000 agents in parallel is already happening > SaaS may not survive the agent era if the Head of Claude Code prompts instead of codes, what does that tell you about the next 2 years? that's exactly why I put together an article on Claude features most people don't know exist it will change how you work with Claude completely you can find it below

Boris Cherny: "I don't write code anymore, I just prompt with Claude" he spent 57 minutes explaining exactly where this is all going here's what stood out: > Claude Code grew faster than anyone at Anthropic expected > AI agents are moving beyond coding into every industry > running 1,000 agents in parallel is already happening > SaaS may not survive the agent era if the Head of Claude Code prompts instead of codes, what does that tell you about the next 2 years? that's exactly why I put together an article on Claude features most people don't know exist it will change how you work with Claude completely you can find it below

Anatoli Kopadze

20,003 Aufrufe • vor 3 Monaten

Important new course: Agent Skills with Anthropic, built with Anthropic and taught by Elie Schoppik! Skills are constructed as folders of instructions that equip agents with on-demand knowledge and workflows. This short course teaches you how to create them following best practices. Because skills follow an open standard format, you can build them once and deploy across any skills-compatible agent, like Claude Code. What you'll learn: - Create custom skills for code generation and review, data analysis, and research - Build complex workflows using Anthropic's pre-built skills (Excel, PowerPoint, skill creation) and custom skills - Combine skills with MCP and subagents to create agentic systems with specialized knowledge - Deploy the same skills across Claude Code, the Claude API, and the Claude Agent SDK Join and learn to equip agents with the specialized knowledge they need for reliable, repeatable workflows.

Important new course: Agent Skills with Anthropic, built with Anthropic and taught by Elie Schoppik! Skills are constructed as folders of instructions that equip agents with on-demand knowledge and workflows. This short course teaches you how to create them following best practices. Because skills follow an open standard format, you can build them once and deploy across any skills-compatible agent, like Claude Code. What you'll learn: - Create custom skills for code generation and review, data analysis, and research - Build complex workflows using Anthropic's pre-built skills (Excel, PowerPoint, skill creation) and custom skills - Combine skills with MCP and subagents to create agentic systems with specialized knowledge - Deploy the same skills across Claude Code, the Claude API, and the Claude Agent SDK Join and learn to equip agents with the specialized knowledge they need for reliable, repeatable workflows.

Andrew Ng

889,034 Aufrufe • vor 6 Monaten

Skills shopping cart for Claude Code In this video I show how I add Railway Skills to a “shopping cart”. After selecting the Skills I need, I copy a single command and they’re added directly to my project. I built to make the composition of Claude Code components as flexible as possible. You can install settings, hooks, subagents, and anything new that gets added to Claude Code will appear on the site. It’s fully open source and community-maintained. If you want to contribute, you’re welcome to fix or update components, download and use the existing ones, or simply support the project by leaving a star on GitHub. Repo:

Skills shopping cart for Claude Code In this video I show how I add Railway Skills to a “shopping cart”. After selecting the Skills I need, I copy a single command and they’re added directly to my project. I built to make the composition of Claude Code components as flexible as possible. You can install settings, hooks, subagents, and anything new that gets added to Claude Code will appear on the site. It’s fully open source and community-maintained. If you want to contribute, you’re welcome to fix or update components, download and use the existing ones, or simply support the project by leaving a star on GitHub. Repo:

Daniel San

20,460 Aufrufe • vor 7 Monaten

Anthropic engineers finally showed how they actually use Claude Code internally 31 minutes of internal workflow that most Claude users will never see on their own here's what they cover: > how to set up project context files the right way > custom commands that save hours of repeated work > hooks that make Claude behave exactly how you need > subagents and how to actually spec them properly "your agent isn't the problem, your spec is" the people who understand how Claude Code actually works inside Anthropic are shipping things everyone else thinks requires a whole team that's exactly why I put together a breakdown of Claude features most people have never discovered you can find it below

Anthropic engineers finally showed how they actually use Claude Code internally 31 minutes of internal workflow that most Claude users will never see on their own here's what they cover: > how to set up project context files the right way > custom commands that save hours of repeated work > hooks that make Claude behave exactly how you need > subagents and how to actually spec them properly "your agent isn't the problem, your spec is" the people who understand how Claude Code actually works inside Anthropic are shipping things everyone else thinks requires a whole team that's exactly why I put together a breakdown of Claude features most people have never discovered you can find it below

Anatoli Kopadze

311,391 Aufrufe • vor 3 Monaten

MIT GAVE DEBUGGING ITS OWN FULL LECTURE -- BECAUSE MOST DEVS STILL HUNT BUGS WITH PRINT STATEMENTS LIKE IT'S 1995 54 minutes that take the thing you do every single day, badly, and show you the tools schools never bothered to teach. -> The moment it lands, you realize "add a print, run it, add another print" was never debugging. It was guessing with extra steps. Most people never learned the real toolkit. A proper debugger, breakpoints, tracing what the program actually does instead of what you assume it does. In 2026 guessing isn't good enough -> the bug is buried in code you didn't even write, and printf won't find it for you. An AI agent will generate hundreds of lines in seconds. When one of them quietly breaks, finding it runs on exactly the skills in this lecture. Anyone can add a print statement. The person who can actually trace a bug to its source is the one who ships while everyone else guesses. Bookmark & Watch it ↓

MIT GAVE DEBUGGING ITS OWN FULL LECTURE -- BECAUSE MOST DEVS STILL HUNT BUGS WITH PRINT STATEMENTS LIKE IT'S 1995 54 minutes that take the thing you do every single day, badly, and show you the tools schools never bothered to teach. -> The moment it lands, you realize "add a print, run it, add another print" was never debugging. It was guessing with extra steps. Most people never learned the real toolkit. A proper debugger, breakpoints, tracing what the program actually does instead of what you assume it does. In 2026 guessing isn't good enough -> the bug is buried in code you didn't even write, and printf won't find it for you. An AI agent will generate hundreds of lines in seconds. When one of them quietly breaks, finding it runs on exactly the skills in this lecture. Anyone can add a print statement. The person who can actually trace a bug to its source is the one who ships while everyone else guesses. Bookmark & Watch it ↓

slash1s

10,864 Aufrufe • vor 2 Monaten

Google Brain founder, Andrew Ng: "One of the most important skills of the future is the ability to tell a computer exactly what you want so it can do it for you." In this talk, he explains why the biggest opportunity isn't just using AI. It's learning how to turn work into agentic workflows, break tasks into steps, give agents the right tools and context, add evals, and make the whole system reliable. That's the difference between prompting an AI and engineering an agent that actually works. Watch it today, then read the full guide in the article below.

Google Brain founder, Andrew Ng: "One of the most important skills of the future is the ability to tell a computer exactly what you want so it can do it for you." In this talk, he explains why the biggest opportunity isn't just using AI. It's learning how to turn work into agentic workflows, break tasks into steps, give agents the right tools and context, add evals, and make the whole system reliable. That's the difference between prompting an AI and engineering an agent that actually works. Watch it today, then read the full guide in the article below.

Rahul

14,431 Aufrufe • vor 17 Tagen

Here's what the Founder of Claude Code does before he starts ANY project: 1. Plans first, codes never, he goes back and forth with Claude on the plan until it's perfect. No code gets written yet 2. Creates a CLAUDE.md file (a simple doc that Claude reads every session so it knows your project, your rules, your style) 3. Gives Claude a way to verify its own work - For backend: write and run tests - For UI: take screenshots, check in browser Claude should never finish a task without proving it works 4. Sets up project-level permission rules in settings.json instead of skipping permissions entirely. Shared with the whole team 5. Five more preparation steps in VIDEO BELOW 6. Only then switches to auto-accept mode and lets Claude build The part most people miss: he doesn't treat Claude as a magic box that gets things right first try he treats it like a junior dev that needs clear instructions, feedback loops, and guardrails at scale he runs multiple sessions in parallel, uses Opus with thinking enabled because it makes fewer mistakes even though it's slower and relies on background agents that push code for later review his setup is surprisingly simple. no crazy custom tools. just slash commands, subagents, and a clean CLAUDE.md the difference isn't the tool. it's how you set it up before you start ❤️ P.S. for sure 99.5% of readers will scroll down this tweet, but I send it to 0.5% who loves to learn how to improve your workflow daily and control 99.5% in 2 years Hard skills literally mean nothing in our world The most important skills which you can have are: building architectures and orchestrations If you master it and use a creative approach, CONGRATS

Here's what the Founder of Claude Code does before he starts ANY project: 1. Plans first, codes never, he goes back and forth with Claude on the plan until it's perfect. No code gets written yet 2. Creates a CLAUDE.md file (a simple doc that Claude reads every session so it knows your project, your rules, your style) 3. Gives Claude a way to verify its own work - For backend: write and run tests - For UI: take screenshots, check in browser Claude should never finish a task without proving it works 4. Sets up project-level permission rules in settings.json instead of skipping permissions entirely. Shared with the whole team 5. Five more preparation steps in VIDEO BELOW 6. Only then switches to auto-accept mode and lets Claude build The part most people miss: he doesn't treat Claude as a magic box that gets things right first try he treats it like a junior dev that needs clear instructions, feedback loops, and guardrails at scale he runs multiple sessions in parallel, uses Opus with thinking enabled because it makes fewer mistakes even though it's slower and relies on background agents that push code for later review his setup is surprisingly simple. no crazy custom tools. just slash commands, subagents, and a clean CLAUDE.md the difference isn't the tool. it's how you set it up before you start ❤️ P.S. for sure 99.5% of readers will scroll down this tweet, but I send it to 0.5% who loves to learn how to improve your workflow daily and control 99.5% in 2 years Hard skills literally mean nothing in our world The most important skills which you can have are: building architectures and orchestrations If you master it and use a creative approach, CONGRATS

Ronin

147,367 Aufrufe • vor 4 Monaten

IBM dropped CUGA, open-source enterprise agent to automate boring tasks 🔥 > given workspace files, it writes and executes code to accomplish any task 🤯 > comes with a ton of tools built for enterprise tasks, supports MCPs > plug in your favorite LLM 👏 here's a small demo where it retrieves info from a file, calculates revenue by writing code, and drafts an e-mail 🤯 they release code, a blog and a demo 🙌🏻 you can run this locally

IBM dropped CUGA, open-source enterprise agent to automate boring tasks 🔥 > given workspace files, it writes and executes code to accomplish any task 🤯 > comes with a ton of tools built for enterprise tasks, supports MCPs > plug in your favorite LLM 👏 here's a small demo where it retrieves info from a file, calculates revenue by writing code, and drafts an e-mail 🤯 they release code, a blog and a demo 🙌🏻 you can run this locally

merve

32,941 Aufrufe • vor 8 Monaten

Apple CEO Tim Cook has a counterintuitive philosophy for achieving excellence: stop following the rules entirely. "I think you should rarely follow the rules. I think you should write the rules." When asked about when it's okay to break the rules, Tim Cook reframes the question itself as flawed. He explains: "If you do follow things in a formulaic manner, you will wind up at best being the same as everybody else. Maybe you missed something and you're a little worse. And if you want to excel, you can't do that." Tim has seen this play out repeatedly in business: "I've watched a lot of companies do that. And I think that's a rotten strategy. Maybe they'll be good for a few months or something." But he's careful to distinguish rule-writing from ignorance. The real skill, he argues, is mastering: "How to learn, how to collaborate, how to think about something, and how to work with people that have a very different point of view than you do." In other words, master the fundamentals of thinking and collaboration —then use those skills to author your own playbook rather than following someone else's. His conclusion is direct: "That's what I really think about it. Write your own rules."

Apple CEO Tim Cook has a counterintuitive philosophy for achieving excellence: stop following the rules entirely. "I think you should rarely follow the rules. I think you should write the rules." When asked about when it's okay to break the rules, Tim Cook reframes the question itself as flawed. He explains: "If you do follow things in a formulaic manner, you will wind up at best being the same as everybody else. Maybe you missed something and you're a little worse. And if you want to excel, you can't do that." Tim has seen this play out repeatedly in business: "I've watched a lot of companies do that. And I think that's a rotten strategy. Maybe they'll be good for a few months or something." But he's careful to distinguish rule-writing from ignorance. The real skill, he argues, is mastering: "How to learn, how to collaborate, how to think about something, and how to work with people that have a very different point of view than you do." In other words, master the fundamentals of thinking and collaboration —then use those skills to author your own playbook rather than following someone else's. His conclusion is direct: "That's what I really think about it. Write your own rules."

Big Brain Business

130,154 Aufrufe • vor 7 Monaten

This is a website where you can find remote jobs and it also work for people that is in Nigeria. Tune your CV well to match each job description. I will also tell you guys how to get good CV templates in the next video if you don't already know how to do that.

This is a website where you can find remote jobs and it also work for people that is in Nigeria. Tune your CV well to match each job description. I will also tell you guys how to get good CV templates in the next video if you don't already know how to do that.

UnfilteredLife

115,128 Aufrufe • vor 1 Monat

Claude Skills are a cheat code for DTC creative teams 🤯 One setup, reusable forever. Claude automatically follows your exact creative process — briefs, hooks, ad copy, research — without you explaining anything twice. Perfect for e-comm brands and agencies who are using Claude for creative work but wasting time re-explaining context every single conversation. Here's the problem: You open Claude: you paste in your brand guidelines, explain your brief format, write the copy, you close the chat. Next day, you do it all over again. Every conversation starts from zero. You're burning 20 minutes on setup before you even get to the actual work. Claude Skills fix this: → Write your creative process once as a Skill (a simple markdown file) → Claude reads it automatically whenever the task comes up → Skills compose — research triggers the research Skill, briefs trigger the brief Skill, copy triggers the copy Skill → All in one conversation, all building on each other → Share across your team so everyone gets the same quality output No re-explaining your brand voice. No pasting the same context every chat. No siloed projects that don't talk to each other. What's in the playbook: → The full architecture (how Skills trigger, chain, and compose) → 5 ready-to-use Skill templates built for DTC and agency creative teams → Step-by-step setup from zero to working Skills → How to write instructions that produce consistent output every time → The composability framework for running multi-step creative workflows in one conversation I put together the complete Claude Skills Playbook for DTC brands and creative agencies. Want it for free? >Like this post >Comment "SKILLS" And I'll send it over (must be following so I can DM)

Mike Futia

31,934 Aufrufe • vor 6 Monaten

Claude Code can parse the whole Internet using Apify actors. And with MCP connectors, you can talk to servers and have your agents perform operations behind paywalls. Example (see the video here): Analyze a YouTube video and write the summary in a Notion page. Another example: Scrape the school calendar and automatically add the events to your Google Calendar. You can do all of this using Claude Code + Apify Skills. Setting this up takes a few seconds: • Open your Apify settings > API & Integrations • Connect your tool (Notion, Google Calendar, ...) • Authorize once Your actors will now have direct read and write access to those services. Here is a blog post with an explanation of how MCP connectors work in Apify: Thanks to the Apify team for partnering with me on this post.

Claude Code can parse the whole Internet using Apify actors. And with MCP connectors, you can talk to servers and have your agents perform operations behind paywalls. Example (see the video here): Analyze a YouTube video and write the summary in a Notion page. Another example: Scrape the school calendar and automatically add the events to your Google Calendar. You can do all of this using Claude Code + Apify Skills. Setting this up takes a few seconds: • Open your Apify settings > API & Integrations • Connect your tool (Notion, Google Calendar, ...) • Authorize once Your actors will now have direct read and write access to those services. Here is a blog post with an explanation of how MCP connectors work in Apify: Thanks to the Apify team for partnering with me on this post.

Santiago

19,783 Aufrufe • vor 2 Monaten

Naval Ravikant on why hard work isn't linear: "We like to view the world as linear: I'm gonna put in eight hours of work, I'm gonna get back eight hours of output. It doesn't work that way. A guy running the corner grocery store is working just as hard or harder than you and me — how much output is he getting? What you do, who you do it with, and how you do it is way more important than how hard you work. Output is nonlinear, based on the quality of the work that you put in."

Naval Ravikant on why hard work isn't linear: "We like to view the world as linear: I'm gonna put in eight hours of work, I'm gonna get back eight hours of output. It doesn't work that way. A guy running the corner grocery store is working just as hard or harder than you and me — how much output is he getting? What you do, who you do it with, and how you do it is way more important than how hard you work. Output is nonlinear, based on the quality of the work that you put in."

Startup Wisdom

19,189 Aufrufe • vor 2 Monaten

PROMPTS ARE DEAD. LOOPS JUST REPLACED YOUR $200K ENGINEER. Claire Vo showed how to turn one prompt into a self-running loop. It reviews your aging pull requests every morning and hunts for new skills every week. And it spins up its own subagents to check its own work. Runs on Claude Code + Codex. One afternoon. One prompt. The numbers are insane: - Senior doing code review: $200K/year - Automation engineer: $150K/year - This setup: about $200/month - Time to build: one afternoon - Skill required: describe the job like you are onboarding a hire The opportunity is even wilder: Teams pay people to babysit pull requests and chase stale reviews. The loop does it itself at 10:15 a.m., alerts the team, and validates itself with subagents. An agency would charge thousands to wire this up. One person + Claude Code + Codex + one prompt = an engineering team that reviews code and finds new skills while you sleep. Save and watch the clip.

PROMPTS ARE DEAD. LOOPS JUST REPLACED YOUR $200K ENGINEER. Claire Vo showed how to turn one prompt into a self-running loop. It reviews your aging pull requests every morning and hunts for new skills every week. And it spins up its own subagents to check its own work. Runs on Claude Code + Codex. One afternoon. One prompt. The numbers are insane: - Senior doing code review: $200K/year - Automation engineer: $150K/year - This setup: about $200/month - Time to build: one afternoon - Skill required: describe the job like you are onboarding a hire The opportunity is even wilder: Teams pay people to babysit pull requests and chase stale reviews. The loop does it itself at 10:15 a.m., alerts the team, and validates itself with subagents. An agency would charge thousands to wire this up. One person + Claude Code + Codex + one prompt = an engineering team that reviews code and finds new skills while you sleep. Save and watch the clip.

shmidt

51,155 Aufrufe • vor 1 Monat

The single best way to break into the Hedge Fund industry — and most people still won't do it: Derek Pilecki, 18-year track record, 21%+ annualized in financials, entire net worth in his own fund. "Since we have the internet, there's a way to break into the industry that didn't exist in the nineties." "You can write up stock ideas. You can research how to write up a stock idea. You can write up your own idea and post it to Seeking Alpha or create your own blog, post it to Twitter." "If you do that 10 times, you'll have a following." "There'll be professional money managers who will read your blog because you wrote up 10 small cap stocks and they own one or two of them." "They read your idea on this bank. They agreed with you. Now they wanna see what other banks you like." "You can find a job that way by just writing up stock ideas and posting them to the internet." "You can break into this industry if you're willing to do that work on your own and put yourself out there." You can just write up 10 stock ideas.

The single best way to break into the Hedge Fund industry — and most people still won't do it: Derek Pilecki, 18-year track record, 21%+ annualized in financials, entire net worth in his own fund. "Since we have the internet, there's a way to break into the industry that didn't exist in the nineties." "You can write up stock ideas. You can research how to write up a stock idea. You can write up your own idea and post it to Seeking Alpha or create your own blog, post it to Twitter." "If you do that 10 times, you'll have a following." "There'll be professional money managers who will read your blog because you wrote up 10 small cap stocks and they own one or two of them." "They read your idea on this bank. They agreed with you. Now they wanna see what other banks you like." "You can find a job that way by just writing up stock ideas and posting them to the internet." "You can break into this industry if you're willing to do that work on your own and put yourself out there." You can just write up 10 stock ideas.

Ethan Kho

200,481 Aufrufe • vor 4 Monaten