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.

Your Claude has a tell, and almost nobody uses it. Make it start every reply with your name. One line in custom instructions, no code. The moment it stops saying your name, its context window is full. That is the exact point the output starts drifting, and you do... show more

Charlie Hills

13,156 subscribers

24,121 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

If you're hitting Claude Code's context limit, check your terminal output before blaming your project size. Every command Claude runs dumps raw output into your context window. git status : 76% of it is noise. A failed cargo test : 155 lines becomes 3. A grep across your codebase : same story You're not running out of context because your code is too big. You're running out because the commands are bleeding you dry before you get anywhere. RTK intercepts that output, compresses it, and hands Claude a clean version instead. 60–90% fewer tokens. Same information. Runs in the background after a one-command setup. Real numbers from 2,900+ commands: average 89% compression across the board. MIT license. Free. 39k GitHub stars. rtk init -g That's it. Restart Claude Code and every command is compressed automatically.

If you're hitting Claude Code's context limit, check your terminal output before blaming your project size. Every command Claude runs dumps raw output into your context window. git status : 76% of it is noise. A failed cargo test : 155 lines becomes 3. A grep across your codebase : same story You're not running out of context because your code is too big. You're running out because the commands are bleeding you dry before you get anywhere. RTK intercepts that output, compresses it, and hands Claude a clean version instead. 60–90% fewer tokens. Same information. Runs in the background after a one-command setup. Real numbers from 2,900+ commands: average 89% compression across the board. MIT license. Free. 39k GitHub stars. rtk init -g That's it. Restart Claude Code and every command is compressed automatically.

Charlie Hills

16,680 Aufrufe • vor 3 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

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.

Mnimiy

113,663 Aufrufe • vor 2 Monaten

Claude Code creator: "100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too. The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops" in this interview he breaks down exactly how a system changes everything: - the memory and context features that turn Claude into a second brain - the knowledge architecture most users don't know Claude can build - the integration layer that connects Claude to your actual workflow - why typing one question at a time is the most expensive way to use Claude if you've been using Claude for months and still start every conversation from scratch with zero context, you don't have a Claude problem. you have a system problem instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed full guide in the article below

Claude Code creator: "100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too. The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops" in this interview he breaks down exactly how a system changes everything: - the memory and context features that turn Claude into a second brain - the knowledge architecture most users don't know Claude can build - the integration layer that connects Claude to your actual workflow - why typing one question at a time is the most expensive way to use Claude if you've been using Claude for months and still start every conversation from scratch with zero context, you don't have a Claude problem. you have a system problem instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed full guide in the article below

Khairallah AL-Awady

39,292 Aufrufe • vor 2 Monaten

someone with your exact Claude plan, is out-producing you three to one it isn't talent and it isn't a secret prompt they built the setup once, so their Claude walks in already briefed yours walks in a stranger every time, the gap is a config, not a ceiling

someone with your exact Claude plan, is out-producing you three to one it isn't talent and it isn't a secret prompt they built the setup once, so their Claude walks in already briefed yours walks in a stranger every time, the gap is a config, not a ceiling

Lagosaur

13,620 Aufrufe • vor 1 Monat

Type ! followed by your bash command to run it instantly without leaving Claude Code. The output is injected in the context window. Saves you tokens, time, and keeps you in the flow.

Type ! followed by your bash command to run it instantly without leaving Claude Code. The output is injected in the context window. Saves you tokens, time, and keeps you in the flow.

Ado

97,284 Aufrufe • vor 7 Monaten

i genuinely can't understand why this isn't the first thing every claude user builds... anthropic quietly shipped a folder system where claude loads specialized instructions on its own based on what you ask. no prompt engineering after setup. almost nobody uses it here's how it actually works... you drop a folder into your skills directory. inside: a SKILL.md that says "trigger this when the user asks about X". claude reads the description once at startup. next time you ask about X, it silently pulls in the whole skill - custom instructions, scripts, examples - like a specialist walking into the room 1. skill for your writing voice - loads only when you draft, never when you analyze 2. skill for your codebase conventions - loads only when you edit that repo, not others 3. skill for your accounting flow - loads only when you say invoice, receipt, or expense your context window stays empty until you need it. one claude behaves like 30 different specialists in one chat and you never manage the switching full breakdown in the article below i test things like this on myself and share the results. follow kai if you want to see what's next

i genuinely can't understand why this isn't the first thing every claude user builds... anthropic quietly shipped a folder system where claude loads specialized instructions on its own based on what you ask. no prompt engineering after setup. almost nobody uses it here's how it actually works... you drop a folder into your skills directory. inside: a SKILL.md that says "trigger this when the user asks about X". claude reads the description once at startup. next time you ask about X, it silently pulls in the whole skill - custom instructions, scripts, examples - like a specialist walking into the room 1. skill for your writing voice - loads only when you draft, never when you analyze 2. skill for your codebase conventions - loads only when you edit that repo, not others 3. skill for your accounting flow - loads only when you say invoice, receipt, or expense your context window stays empty until you need it. one claude behaves like 30 different specialists in one chat and you never manage the switching full breakdown in the article below i test things like this on myself and share the results. follow kai if you want to see what's next

kai

69,978 Aufrufe • vor 26 Tagen

$THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this$

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,177 Aufrufe • vor 2 Monaten

A PHD JUST EXPLAINED HOW TO BECOME IMMORTAL WITH FABLE + GOD-MODE SECOND BRAIN ASSISTANT. This was science fiction in February, BUT now it's a weekend setup: > step one: build the second brain: every note, every decision, every opinion, the raw material of how you actually think > step two: Fable 5 tunes your own agent against that vault, iterating until the answers start sounding like yours > step three: Fable interviews you, deeply. the questions pull out the thinking you never bothered to write down And the catch he's right about, that everyone will skip: if your vault is full of AI slop, you're not cloning yourself. you're cloning ChatGPT with your name on it. the training data has to be YOU, handwritten takes, real decisions, actual taste. That's the quiet flip nobody says out loud: everyone is scared AI will replace them. operators are building the replacement themselves and sending it to work. Step one is the whole foundation, and I broke it down in the article below: the vault structure, the Claude wiring, the exact prompts. P.S. send the article to your Claude and let it start interviewing you tonight. the clone is only as good as what you feed it.

A PHD JUST EXPLAINED HOW TO BECOME IMMORTAL WITH FABLE + GOD-MODE SECOND BRAIN ASSISTANT. This was science fiction in February, BUT now it's a weekend setup: > step one: build the second brain: every note, every decision, every opinion, the raw material of how you actually think > step two: Fable 5 tunes your own agent against that vault, iterating until the answers start sounding like yours > step three: Fable interviews you, deeply. the questions pull out the thinking you never bothered to write down And the catch he's right about, that everyone will skip: if your vault is full of AI slop, you're not cloning yourself. you're cloning ChatGPT with your name on it. the training data has to be YOU, handwritten takes, real decisions, actual taste. That's the quiet flip nobody says out loud: everyone is scared AI will replace them. operators are building the replacement themselves and sending it to work. Step one is the whole foundation, and I broke it down in the article below: the vault structure, the Claude wiring, the exact prompts. P.S. send the article to your Claude and let it start interviewing you tonight. the clone is only as good as what you feed it.

Miraqle

32,328 Aufrufe • vor 1 Monat

Claude Code + Obsidian + 1 free GitHub skill = unlimited memory. Almost nobody is running this yet. Here’s the problem nobody tells you. Claude forgets you. Every new chat starts at 0. You re explain your business, your projects, your style every single time. That tax is why most people never compound anything with AI. The fix is 1 skill. It’s called Obsidian Mind. It turns your Obsidian vault into Claude’s long term brain. 2,000 notes, 14 projects, every idea you’ve ever dumped Claude reads it live and writes back to it live. It stops being a chatbot. It becomes a second brain that builds. What it does: → Bridges Claude Code straight into your vault. → Pulls any note in real time no copy paste, no context limit. → Updates your vault as you work Claude writes its own memory. → Links everything into 1 graph Claude can navigate. Day 1: Claude knows your last 6 months. Week 2: it drafts off your own past notes. Week 4: it’s running plays you forgot you wrote down. The people making real money with AI right now aren’t smarter. They just stopped starting from 0 every morning. Setup takes 11 minutes. The skill is free. You’ll have a brain that never forgets.

Claude Code + Obsidian + 1 free GitHub skill = unlimited memory. Almost nobody is running this yet. Here’s the problem nobody tells you. Claude forgets you. Every new chat starts at 0. You re explain your business, your projects, your style every single time. That tax is why most people never compound anything with AI. The fix is 1 skill. It’s called Obsidian Mind. It turns your Obsidian vault into Claude’s long term brain. 2,000 notes, 14 projects, every idea you’ve ever dumped Claude reads it live and writes back to it live. It stops being a chatbot. It becomes a second brain that builds. What it does: → Bridges Claude Code straight into your vault. → Pulls any note in real time no copy paste, no context limit. → Updates your vault as you work Claude writes its own memory. → Links everything into 1 graph Claude can navigate. Day 1: Claude knows your last 6 months. Week 2: it drafts off your own past notes. Week 4: it’s running plays you forgot you wrote down. The people making real money with AI right now aren’t smarter. They just stopped starting from 0 every morning. Setup takes 11 minutes. The skill is free. You’ll have a brain that never forgets.

West Lord

110,516 Aufrufe • vor 2 Monaten

You can now add a live browser to Claude Code to click any element and edit it 🤯 Your app runs embedded. You click a button. Claude instantly knows the exact selector, the exact component, the exact location in your code. No more “the red button in the top left of the third card.” Just click it. 100% open source.

You can now add a live browser to Claude Code to click any element and edit it 🤯 Your app runs embedded. You click a button. Claude instantly knows the exact selector, the exact component, the exact location in your code. No more “the red button in the top left of the third card.” Just click it. 100% open source.

Alvaro Cintas

47,136 Aufrufe • vor 3 Monaten

We made an MCP for your phone. Your laptop is just half of your life, and the other half is in your phone. Now your agent gets the mobile screen too. No connectors, no complex setup, it has access to everything that lives on your phone, all the logged-in apps, your notes, your calls, you name it. It sees the screen, taps it, types on it, from Claude Code, Codex, or any MCP client. Live now at $20 in credits, $20 more for the first 100 who connect a phone and run a task. Comment "discord" if you want the invite to the builder Discord, I'll DM it to you.

We made an MCP for your phone. Your laptop is just half of your life, and the other half is in your phone. Now your agent gets the mobile screen too. No connectors, no complex setup, it has access to everything that lives on your phone, all the logged-in apps, your notes, your calls, you name it. It sees the screen, taps it, types on it, from Claude Code, Codex, or any MCP client. Live now at $20 in credits, $20 more for the first 100 who connect a phone and run a task. Comment "discord" if you want the invite to the builder Discord, I'll DM it to you.

Div Garg

43,638 Aufrufe • vor 22 Tagen

i genuinely can't understand why this isn't the first thing every claude user builds... andrej karpathy, co-founder of openai, quietly solved the exact problem making your ai useless and almost nobody noticed here's the problem he solved... every session claude starts from zero, rereads the same files, forgets every contradiction it already caught, burns tokens relearning what it knew yesterday, forever 1. raw holds the truth once, wiki holds the compiled answer forever, instructions hold the one rule that stops it from ever getting messy again 2. claude opens a raw file exactly one time in its entire life, after that it only speaks in wiki pages with the sources already cited 3. the moment claude catches you contradicting yourself, it writes both versions into the wiki with dates, so it never asks you the same wrong question twice your raw files are disposable... the compiled wiki is the only thing that actually compounds full breakdown is in the article below

i genuinely can't understand why this isn't the first thing every claude user builds... andrej karpathy, co-founder of openai, quietly solved the exact problem making your ai useless and almost nobody noticed here's the problem he solved... every session claude starts from zero, rereads the same files, forgets every contradiction it already caught, burns tokens relearning what it knew yesterday, forever 1. raw holds the truth once, wiki holds the compiled answer forever, instructions hold the one rule that stops it from ever getting messy again 2. claude opens a raw file exactly one time in its entire life, after that it only speaks in wiki pages with the sources already cited 3. the moment claude catches you contradicting yourself, it writes both versions into the wiki with dates, so it never asks you the same wrong question twice your raw files are disposable... the compiled wiki is the only thing that actually compounds full breakdown is in the article below

kai

375,956 Aufrufe • vor 1 Monat

I turned cursor + claude 3.7 into a powerhouse content writer using a custom agent mode. it: - researches your topic - plans out your content - writes one section at a time - has full context of previously written sections - adds relevant links, tables, code examples, etc - writes for users NOT seo slop watch the video - it literally one-shot a killer article in minutes and the output looks nothing like AI check the link to the article in the first reply below if this post gets a million views i'll share the custom agent instructions prompt ;)

I turned cursor + claude 3.7 into a powerhouse content writer using a custom agent mode. it: - researches your topic - plans out your content - writes one section at a time - has full context of previously written sections - adds relevant links, tables, code examples, etc - writes for users NOT seo slop watch the video - it literally one-shot a killer article in minutes and the output looks nothing like AI check the link to the article in the first reply below if this post gets a million views i'll share the custom agent instructions prompt ;)

Ian Nuttall

117,186 Aufrufe • vor 1 Jahr

Glen is building the organizational learning and context layer for agents. Every agent session your team runs produces reasoning worth keeping, and nearly all of it is discarded the moment the window closes. Glen is the layer that unifies every agent and model your company run. Glen pulls in agent sessions from Claude Code, Codex and Cursor, plus Slack messages, GitHub prs, tickets, docs and calls. When a new agent picks up a task, Glen finds relevant prior context and injects it in the agents context window to steer it, producing knowledge work that is significantly higher quality, faster and cheaper than ever before. 29% less context and 21% faster to be exact. And Glen does more... > query the original agent behind any line of code > search every session your org has ever run > dynamic skill distillation > multiplayer agents > unified transcripts you can hand between Claude Code, Codex, and Cursor mid-task, > a company brain in Slack. Glen is in early access, sign up for the waitlist below.

Glen is building the organizational learning and context layer for agents. Every agent session your team runs produces reasoning worth keeping, and nearly all of it is discarded the moment the window closes. Glen is the layer that unifies every agent and model your company run. Glen pulls in agent sessions from Claude Code, Codex and Cursor, plus Slack messages, GitHub prs, tickets, docs and calls. When a new agent picks up a task, Glen finds relevant prior context and injects it in the agents context window to steer it, producing knowledge work that is significantly higher quality, faster and cheaper than ever before. 29% less context and 21% faster to be exact. And Glen does more... > query the original agent behind any line of code > search every session your org has ever run > dynamic skill distillation > multiplayer agents > unified transcripts you can hand between Claude Code, Codex, and Cursor mid-task, > a company brain in Slack. Glen is in early access, sign up for the waitlist below.

Nikos

15,524 Aufrufe • vor 8 Tagen

CLAUDE CODE JUST SHIPPED THE FEATURE THAT SOLVES THE BIGGEST PROBLEM EVERY BUILDER HAS WITH AI AGENTS. The problem: Claude starts a task, gets distracted by a sub-problem, goes down a rabbit hole, and never finishes the original thing you asked for. The solution: /goal One command. You set the goal at the start of the session. Claude now has a north star it checks against every action it takes. Not just at the beginning. Throughout the entire session. Every time Claude is about to do something it asks: does this action move me toward the goal the user set or am I drifting? If it is drifting it corrects. If it completes a sub-task it returns to the primary goal. If it hits a blocker it reports back instead of spending 45 minutes solving the wrong problem. This sounds like a small feature. It is not. The reason most people do not trust Claude Code for long autonomous runs is not capability. It is reliability. A Claude Code session that reliably finishes what it started is worth 10 times more than one that is more capable but wanders. /goal is the feature that makes long autonomous sessions reliable. Set the goal. Let it run. Come back to a finished result. Not a result that got 70% done before Claude decided the sub-problem was more interesting. Done. The builders running overnight agent sessions are going to use this command on everything from today forward. Bookmark this. Follow CyrilXBT for every Claude Code feature the moment it ships.

CLAUDE CODE JUST SHIPPED THE FEATURE THAT SOLVES THE BIGGEST PROBLEM EVERY BUILDER HAS WITH AI AGENTS. The problem: Claude starts a task, gets distracted by a sub-problem, goes down a rabbit hole, and never finishes the original thing you asked for. The solution: /goal One command. You set the goal at the start of the session. Claude now has a north star it checks against every action it takes. Not just at the beginning. Throughout the entire session. Every time Claude is about to do something it asks: does this action move me toward the goal the user set or am I drifting? If it is drifting it corrects. If it completes a sub-task it returns to the primary goal. If it hits a blocker it reports back instead of spending 45 minutes solving the wrong problem. This sounds like a small feature. It is not. The reason most people do not trust Claude Code for long autonomous runs is not capability. It is reliability. A Claude Code session that reliably finishes what it started is worth 10 times more than one that is more capable but wanders. /goal is the feature that makes long autonomous sessions reliable. Set the goal. Let it run. Come back to a finished result. Not a result that got 70% done before Claude decided the sub-problem was more interesting. Done. The builders running overnight agent sessions are going to use this command on everything from today forward. Bookmark this. Follow CyrilXBT for every Claude Code feature the moment it ships.

CyrilXBT

19,586 Aufrufe • vor 3 Monaten

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

GREG ISENBERG

193,721 Aufrufe • vor 4 Monaten

I just built a Brand Operating System inside Claude Cowork 🤯 A connected system of files that every skill automatically reads from, so your hook writer, brief generator, and script writer all speak in your exact brand voice. All inside Claude Cowork. Perfect for DTC brands and agencies tired of generic AI output that sounds like every other brand in their category. If you're opening a new Claude chat and re-explaining your brand, re-pasting your voice guidelines, and re-describing your customers every single time, a Brand OS fixes the entire loop: → Build 3 foundation files once per brand → Every skill you create reads from the Brand OS automatically → Hook writer pulls your voice + customer pain points → Brief generator pulls your positioning + angles → Script writer pulls the brief + brand DNA → Every output is calibrated to your brand on the first pass No re-briefing Claude on every chat. No editing for an hour to fix generic AI phrasing. No creative that sounds like it could belong to any brand. What you get in the playbook: → The exact Brand OS file structure I use → Templates for all 3 files you can fill in for any brand → The architecture that makes every Claude skill 10x sharper → The exact setup for agencies running a Brand OS per client For agencies: this is how you build a perfect, reusable knowledge base for every client on your roster. Set up the Brand OS once per client, and every campaign after that is already calibrated. I put together a full playbook with the file templates, the architecture, and the exact setup process so you can build your own Brand OS for your brand or your clients. Want it for free? > Like this post > Comment "OS" And I'll send it over (must be following so I can DM)

Mike Futia

30,250 Aufrufe • vor 4 Monaten

This guy literally told Claude to run every day at 4am. Now it opens his website, writes a blog post, and optimizes it for SEO. Every single day. Zero involvement. Here's how Claude computer use actually works: It looks at your screen. Moves your mouse. Clicks buttons. Opens apps. Completes the full task on its own. No code. No workflow builder. No setup. You just tell it what you want done. And the 4am SEO trick? You schedule it once inside Claude Co-work. Claude runs it every night while you sleep. Your site gets fresh content. You wake up and check the results. That's not a chatbot. That's an AI employee.

This guy literally told Claude to run every day at 4am. Now it opens his website, writes a blog post, and optimizes it for SEO. Every single day. Zero involvement. Here's how Claude computer use actually works: It looks at your screen. Moves your mouse. Clicks buttons. Opens apps. Completes the full task on its own. No code. No workflow builder. No setup. You just tell it what you want done. And the 4am SEO trick? You schedule it once inside Claude Co-work. Claude runs it every night while you sleep. Your site gets fresh content. You wake up and check the results. That's not a chatbot. That's an AI employee.

Julian Goldie SEO

133,361 Aufrufe • vor 5 Monaten

Notch Clips. every other ad tool ignores the footage sitting in your dropbox and generates new clips from a prompt. notch opens your library instead. it watches every clip you have ever shot and understands what is inside each one. the mood. who is in frame. what they are doing. the quality. so when you ask it to build an ad, it does not start from scratch. it reaches into your past shoots, finds the clip that fits, and slots it into the exact moment that needs it. here is what that looks like. you had thirteen versions of one reaction shot. notch picked the one that worked and left the other twelve. not by filename. not by guessing from a reference image. it watched all thirteen and could tell the difference. that is the whole idea. the right clip was already in your library. every other tool was about to make a worse one. footage you already shot, turned into every ad you still need. drop your site and a few clips you have. notch builds the first ad from them.

Notch Clips. every other ad tool ignores the footage sitting in your dropbox and generates new clips from a prompt. notch opens your library instead. it watches every clip you have ever shot and understands what is inside each one. the mood. who is in frame. what they are doing. the quality. so when you ask it to build an ad, it does not start from scratch. it reaches into your past shoots, finds the clip that fits, and slots it into the exact moment that needs it. here is what that looks like. you had thirteen versions of one reaction shot. notch picked the one that worked and left the other twelve. not by filename. not by guessing from a reference image. it watched all thirteen and could tell the difference. that is the whole idea. the right clip was already in your library. every other tool was about to make a worse one. footage you already shot, turned into every ad you still need. drop your site and a few clips you have. notch builds the first ad from them.

Vinay Jain

406,286 Aufrufe • vor 3 Monaten