正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Every skill file I write ends with a self-improvement loop. It sits at the bottom of the skill.md and runs before the skill finishes: - Did any step fail or need a workaround? - Did I correct or reject anything meaningful? - Did you discover something a future run... show more

The Startup Ideas Podcast (SIP) 🧃

46,499 subscribers

11,799 次观看 • 5 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

shmidt

16,085 次观看 • 2 个月前

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 次观看 • 4 个月前

“There is a letter written by Brink speaking about you not passing a competency assessment report, did you do a competency assessment and did you pass it or you didn't pass it” MK Party MP Vusi Shongwe “I I don't it doesn't say you failed it like it's a comp it's like whether you passed a yeah what do you call it, I, I let me say it was not positive” General Shadrack Sibiya “Did you pass it or failed it” uMkhonto WeSizwe Party (Official) MP “I failed it” Lt-General Shadrack Sibiya testifying at the Ad Hoc committee

“There is a letter written by Brink speaking about you not passing a competency assessment report, did you do a competency assessment and did you pass it or you didn't pass it” MK Party MP Vusi Shongwe “I I don't it doesn't say you failed it like it's a comp it's like whether you passed a yeah what do you call it, I, I let me say it was not positive” General Shadrack Sibiya “Did you pass it or failed it” uMkhonto WeSizwe Party (Official) MP “I failed it” Lt-General Shadrack Sibiya testifying at the Ad Hoc committee

News Live SA

144,966 次观看 • 10 个月前

Hyperagent is great if you want agents without having to deal with configuration, servers, or any complexity whatsoever. You don't need a Mac Mini or a server. Every agent runs in the cloud, in its own isolated and secure environment. You get: 1. The ability to learn any new API as a skill 2. Browser support 3. Code execution 4. Image and video generation 5. Integration with hundreds of tools Despite the simplicity, I think their best differentiator is the ability for these agents to learn new skills. Basically, you can teach an agent how your company does marketing, and it will never forget your rules and processes. Obviously, it also lets you deploy your agents to Slack with a single click, so everyone can use them. You don't even need to mention them since they will pay attention to chats and act when necessary. I built a simple agent that allows me to translate any message into French. I installed it on Slack, and every time I ping it, it gives me translations. Took me 10 minutes tops.

Hyperagent is great if you want agents without having to deal with configuration, servers, or any complexity whatsoever. You don't need a Mac Mini or a server. Every agent runs in the cloud, in its own isolated and secure environment. You get: 1. The ability to learn any new API as a skill 2. Browser support 3. Code execution 4. Image and video generation 5. Integration with hundreds of tools Despite the simplicity, I think their best differentiator is the ability for these agents to learn new skills. Basically, you can teach an agent how your company does marketing, and it will never forget your rules and processes. Obviously, it also lets you deploy your agents to Slack with a single click, so everyone can use them. You don't even need to mention them since they will pay attention to chats and act when necessary. I built a simple agent that allows me to translate any message into French. I installed it on Slack, and every time I ping it, it gives me translations. Took me 10 minutes tops.

Santiago

213,012 次观看 • 29 天前

Right now, I have a few dozen tools to automate my life. Every single thing that I do more than once every week is now a tool: either a Claude Code skill, a scheduled workflow, or an application. • I spend the time doing this once. • I schedule it. • I forget about it (or at least, try to) CREAO is one of the platforms I've used extensively for building some of these automations. They are partnering with me on this post. They are one of the only platforms where you can go from a conversation to a scheduled agent that quickly. This is how it works: 1. You describe the problem you want to solve 2. CREAO's agent builds the logic and executes it 3. You can iterate with the agent to improve the solution 4. When you are done, you turn that solution into a mini app 5. You can schedule that app to run any time you need it Something important: These agents are deterministic. They don't use an LLM to generate answers, so they will always return the same output given the same input. This is critical: when you're automating something that runs every Monday at 9 am, you need it to return the same result every time, not a "creative" answer.

Right now, I have a few dozen tools to automate my life. Every single thing that I do more than once every week is now a tool: either a Claude Code skill, a scheduled workflow, or an application. • I spend the time doing this once. • I schedule it. • I forget about it (or at least, try to) CREAO is one of the platforms I've used extensively for building some of these automations. They are partnering with me on this post. They are one of the only platforms where you can go from a conversation to a scheduled agent that quickly. This is how it works: 1. You describe the problem you want to solve 2. CREAO's agent builds the logic and executes it 3. You can iterate with the agent to improve the solution 4. When you are done, you turn that solution into a mini app 5. You can schedule that app to run any time you need it Something important: These agents are deterministic. They don't use an LLM to generate answers, so they will always return the same output given the same input. This is critical: when you're automating something that runs every Monday at 9 am, you need it to return the same result every time, not a "creative" answer.

Santiago

13,712 次观看 • 4 个月前

One of the best applications for agentic loops is SEO. Here's why it works: the outcome is "black or white." You moved up this month, you moved down, or you stayed the same. That's the entire requirement for a loop — a metric that grades the work for you. Build it in five parts: 1) Access. - Connect it to your real data, not your description of your data. - Google Search Console has an API. - DataForSEO shows you the four pages ranking above yours. 2) Action. - Let it audit and fix before it experiments. - Meta tags, JSON-LD, a missing sitemap. - Quick wins on most sites. 3) Memory. - A markdown file where it logs every change it made and why. 4) Judgment. - Every two weeks it reopens that file and checks its own work: I rewrote that description — did it rank us higher or lower? 5) Reversal. - A change that took you from position 20 to 30 gets undone. - Nothing here is set in stone. Then put it on a routine so it picks up where it left off without you. The catch: this takes months, not days. Months of nothing, then month four, bam bam bam, page one. So find the number in your business that can't be argued with. Build the loop around that one.

One of the best applications for agentic loops is SEO. Here's why it works: the outcome is "black or white." You moved up this month, you moved down, or you stayed the same. That's the entire requirement for a loop — a metric that grades the work for you. Build it in five parts: 1) Access. - Connect it to your real data, not your description of your data. - Google Search Console has an API. - DataForSEO shows you the four pages ranking above yours. 2) Action. - Let it audit and fix before it experiments. - Meta tags, JSON-LD, a missing sitemap. - Quick wins on most sites. 3) Memory. - A markdown file where it logs every change it made and why. 4) Judgment. - Every two weeks it reopens that file and checks its own work: I rewrote that description — did it rank us higher or lower? 5) Reversal. - A change that took you from position 20 to 30 gets undone. - Nothing here is set in stone. Then put it on a routine so it picks up where it left off without you. The catch: this takes months, not days. Months of nothing, then month four, bam bam bam, page one. So find the number in your business that can't be argued with. Build the loop around that one.

The Startup Ideas Podcast (SIP) 🧃

11,505 次观看 • 18 天前

The type of shows or movies I can’t watch because the mom told you not to answer and you still did it

The type of shows or movies I can’t watch because the mom told you not to answer and you still did it

ladyperpetual

32,032 次观看 • 2 个月前

Do you know the pain of wanting to send a client an invoice, then you have to open your laptop, find your invoice document and start typing it in Or if you're one of those who use Canva for it You need an invoice and you need it in 3 minutes so you can close a deal I GOT YOU, I will show you how I made an invoice for my company using AI and then created a Webapp for it, the WebApp installs like an android app and I can open it and use anytime without internet. That's the next video Let me show you how I did my own P.S: It was my first time, so we do it together... Video dropping soon

Do you know the pain of wanting to send a client an invoice, then you have to open your laptop, find your invoice document and start typing it in Or if you're one of those who use Canva for it You need an invoice and you need it in 3 minutes so you can close a deal I GOT YOU, I will show you how I made an invoice for my company using AI and then created a Webapp for it, the WebApp installs like an android app and I can open it and use anytime without internet. That's the next video Let me show you how I did my own P.S: It was my first time, so we do it together... Video dropping soon

Richard U. | Web Developer

26,235 次观看 • 27 天前

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

Sprytix

153,690 次观看 • 1 个月前

Today we're launching Claude for marketing. One skill turns it into a full marketing team: > Drop your URL: ads, launch films and social cuts come back > Say "punchier" or "different hook": it re-runs on the spot > Every format, every ratio, one message Comment "VIRAL" and I'll send you the skill. 👇

Today we're launching Claude for marketing. One skill turns it into a full marketing team: > Drop your URL: ads, launch films and social cuts come back > Say "punchier" or "different hook": it re-runs on the spot > Every format, every ratio, one message Comment "VIRAL" and I'll send you the skill. 👇

Motion

94,550 次观看 • 15 天前

I built a Claude skill that helps you review a report as an analyst. Now, it thinks like a senior analyst for you. The readme file will explain how to use it as a skill on Claude or Copilot or Chatgpt Use & let me how it works. My gift to U

I built a Claude skill that helps you review a report as an analyst. Now, it thinks like a senior analyst for you. The readme file will explain how to use it as a skill on Claude or Copilot or Chatgpt Use & let me how it works. My gift to U

David Abu _

42,369 次观看 • 5 个月前

I made a tool that allows you to add or remove delay while streaming without the need of restarting your stream or OBS, without the need of a dual PC or any external plugins. This is the tutorial how to use it.

I made a tool that allows you to add or remove delay while streaming without the need of restarting your stream or OBS, without the need of a dual PC or any external plugins. This is the tutorial how to use it.

Lyp

249,586 次观看 • 7 个月前

Karpathy compressed the agent problem into 1 sentence: "If you can't evaluate then you can't auto research it, right?" That's the rule I keep coming back to with long-running coding agents Before you launch /goal or /loop, write the verifier: - what counts as done - what evidence proves it - which checks run every pass - which artifact gets saved - which failure sends it back into the loop Then let the agent run The loop can keep going because proof sits outside the agent's own explanation Tests, screenshots, benchmark curves, browser runs, changed files That's how you get autonomy without babysitting a transcript for 6 hours Read the full breakdown on goals, verifiers, loops, artifacts, and session memory in the article below

Karpathy compressed the agent problem into 1 sentence: "If you can't evaluate then you can't auto research it, right?" That's the rule I keep coming back to with long-running coding agents Before you launch /goal or /loop, write the verifier: - what counts as done - what evidence proves it - which checks run every pass - which artifact gets saved - which failure sends it back into the loop Then let the agent run The loop can keep going because proof sits outside the agent's own explanation Tests, screenshots, benchmark curves, browser runs, changed files That's how you get autonomy without babysitting a transcript for 6 hours Read the full breakdown on goals, verifiers, loops, artifacts, and session memory in the article below

Alpha Batcher

43,806 次观看 • 2 个月前

When the trial started, I began working on this timeline to help keep track of everything as it unfolded. Somewhere near the end, I put it aside and never quite finished it. Recently though, after seeing things in the news, a few people who hadn’t followed the trial closely reached out to me with questions and asking for a timeline of certain events. Even though mine was still unfinished at the time, it already had most of the key information, so I shared it with them. That interest gave me the push I needed to go back, clean it up, and complete it and now that it’s done, I wanted to share it with all of you. I did my best to nail down the exact timing of events by going through the testimony of officers, experts, and civilian witnesses. When I couldn’t find a precise time, I gave my best estimate, which is noted on the timeline. Just a heads-up: you might need to pause in a few spots to read everything. The video was already over 30 minutes and I couldn’t dedicate as much time as I would have liked on every slide. Hope it’s helpful and if you catch anything I may have missed or gotten wrong, feel free to let me know!

When the trial started, I began working on this timeline to help keep track of everything as it unfolded. Somewhere near the end, I put it aside and never quite finished it. Recently though, after seeing things in the news, a few people who hadn’t followed the trial closely reached out to me with questions and asking for a timeline of certain events. Even though mine was still unfinished at the time, it already had most of the key information, so I shared it with them. That interest gave me the push I needed to go back, clean it up, and complete it and now that it’s done, I wanted to share it with all of you. I did my best to nail down the exact timing of events by going through the testimony of officers, experts, and civilian witnesses. When I couldn’t find a precise time, I gave my best estimate, which is noted on the timeline. Just a heads-up: you might need to pause in a few spots to read everything. The video was already over 30 minutes and I couldn’t dedicate as much time as I would have liked on every slide. Hope it’s helpful and if you catch anything I may have missed or gotten wrong, feel free to let me know!

Jamz

58,897 次观看 • 1 年前

Skills are the quickest way to 10x the quality and consistency of what you get from Claude Code. And you don't need to be a developer to use them. Anthropic just published how they use hundreds of skills internally every day. Most skill tutorials are made for developers — if you're in marketing, sales, content ops, or GTM, you probably watched those and moved on. But skills are just as important for non-developers. A skill is just a reusable prompt with clear instructions for a specific task. Instead of prompting Claude the same way over and over, you build it once and invoke it every time. I have a skill for writing on LinkedIn. A different one for YouTube outlines. Another for X. Each platform has different rules, different voice, different structure — so each one gets its own skill. If you're doing something repeatedly, it's time to make a skill. The biggest mistake most people make: building skills as a single .md file. A single file dumps everything into context whether Claude needs it or not. Wastes tokens. Gets worse results. Skills should be folders. Here's the structure that works: skill.md — the orchestrator. Tells Claude which files to read and when. It doesn't contain rules itself — it's the playbook. instructions/ — separate files for voice, structure, scope. Claude only loads the one it needs for the current step. examples/ — good AND bad. Good examples show what success looks like. Bad examples show patterns to avoid — AI writing tells, weak hooks, generic CTAs. Most people skip bad examples. Don't. eval/ — a checklist that scores every output before you see it. "Does it have a clear hook?" "Is it free of AI buzzwords?" Pass or fail on each item. templates/ — output formatting so you get consistent structure every time. The three types of skills that matter most for non-developers: 1. Business automation. Writing a newsletter. Checking reports and drafting follow-ups. Running programmatic ad campaigns. Any workflow you repeat — build a skill for it. 2. Content templates. Landing page copy, meta ads, email sequences, SEO briefs. Each one has specific requirements. Each one gets its own skill. 3. Thinking partners. This is the one people miss. Skills don't have to produce output. They can help you think — an advisory board that reviews your work from your ICP's perspective, a coach that pressure-tests your strategy, an ideation partner that researches competitors before suggesting your next move. If you already have skills as .md files, here's the exact prompt to restructure them in the Anthropic approved format: "I want to restructure my Claude Code skill file. Right now my skill is a single .md file and I want to break it into a folder system following Anthropic's best practices. Read my current skill file, then restructure it into a folder with: a skill.md orchestrator, an instructions/ folder with separate files for each concern (voice, structure, scope), an examples/ folder with good and bad examples, an eval/ folder with a quality checklist, and a templates/ folder for output formatting. Keep all my existing rules and intent — just reorganize them into the modular structure." Paste that into Claude Code pointed at the folder where your skill lives. It handles the rest. A few caveats: 1. Don't add too many skills. Every skill adds context Claude has to process. 50 skills loaded means everything slows down. Start with 3-5 covering your most repeated workflows. 2. Vet skills before downloading. If you grab a skill from the internet, read what's inside first. Skills can include shell commands and scripts. Check what you're running. 3. Share what works. Build a skill that performs well, put it in a shared GitHub repo. Your marketing org gets shared skills for copywriting, SEO, ad copy — new hires invoke the skill instead of learning every playbook from scratch. Onboarding time drops dramatically. 4. Keep your skills updated. When you see output you love, add it as a good example. When you see a pattern you hate, add it as a bad example. The skill gets sharper every time. I made a full video walking through all of this — including a live build of two skills from scratch (no terminal, no code), the exact prompt I use to restructure old skills, and 5 pro tips from Anthropic's internal playbook. Share this with your non-developer friends that want to do more with AI; or bookmark it to come back to at a later time.

Skills are the quickest way to 10x the quality and consistency of what you get from Claude Code. And you don't need to be a developer to use them. Anthropic just published how they use hundreds of skills internally every day. Most skill tutorials are made for developers — if you're in marketing, sales, content ops, or GTM, you probably watched those and moved on. But skills are just as important for non-developers. A skill is just a reusable prompt with clear instructions for a specific task. Instead of prompting Claude the same way over and over, you build it once and invoke it every time. I have a skill for writing on LinkedIn. A different one for YouTube outlines. Another for X. Each platform has different rules, different voice, different structure — so each one gets its own skill. If you're doing something repeatedly, it's time to make a skill. The biggest mistake most people make: building skills as a single .md file. A single file dumps everything into context whether Claude needs it or not. Wastes tokens. Gets worse results. Skills should be folders. Here's the structure that works: skill.md — the orchestrator. Tells Claude which files to read and when. It doesn't contain rules itself — it's the playbook. instructions/ — separate files for voice, structure, scope. Claude only loads the one it needs for the current step. examples/ — good AND bad. Good examples show what success looks like. Bad examples show patterns to avoid — AI writing tells, weak hooks, generic CTAs. Most people skip bad examples. Don't. eval/ — a checklist that scores every output before you see it. "Does it have a clear hook?" "Is it free of AI buzzwords?" Pass or fail on each item. templates/ — output formatting so you get consistent structure every time. The three types of skills that matter most for non-developers: 1. Business automation. Writing a newsletter. Checking reports and drafting follow-ups. Running programmatic ad campaigns. Any workflow you repeat — build a skill for it. 2. Content templates. Landing page copy, meta ads, email sequences, SEO briefs. Each one has specific requirements. Each one gets its own skill. 3. Thinking partners. This is the one people miss. Skills don't have to produce output. They can help you think — an advisory board that reviews your work from your ICP's perspective, a coach that pressure-tests your strategy, an ideation partner that researches competitors before suggesting your next move. If you already have skills as .md files, here's the exact prompt to restructure them in the Anthropic approved format: "I want to restructure my Claude Code skill file. Right now my skill is a single .md file and I want to break it into a folder system following Anthropic's best practices. Read my current skill file, then restructure it into a folder with: a skill.md orchestrator, an instructions/ folder with separate files for each concern (voice, structure, scope), an examples/ folder with good and bad examples, an eval/ folder with a quality checklist, and a templates/ folder for output formatting. Keep all my existing rules and intent — just reorganize them into the modular structure." Paste that into Claude Code pointed at the folder where your skill lives. It handles the rest. A few caveats: 1. Don't add too many skills. Every skill adds context Claude has to process. 50 skills loaded means everything slows down. Start with 3-5 covering your most repeated workflows. 2. Vet skills before downloading. If you grab a skill from the internet, read what's inside first. Skills can include shell commands and scripts. Check what you're running. 3. Share what works. Build a skill that performs well, put it in a shared GitHub repo. Your marketing org gets shared skills for copywriting, SEO, ad copy — new hires invoke the skill instead of learning every playbook from scratch. Onboarding time drops dramatically. 4. Keep your skills updated. When you see output you love, add it as a good example. When you see a pattern you hate, add it as a bad example. The skill gets sharper every time. I made a full video walking through all of this — including a live build of two skills from scratch (no terminal, no code), the exact prompt I use to restructure old skills, and 5 pro tips from Anthropic's internal playbook. Share this with your non-developer friends that want to do more with AI; or bookmark it to come back to at a later time.

JJ Englert

29,322 次观看 • 4 个月前

ANTHROPIC LEAKED A SETUP WHERE ONE FILE STARTS 7 LOOPS THAT TURN A PROMPT INTO A WORKING BUSINESS AI engineer drops in 1 file - the other 95% of the work closes automatically without them. spec → tasks → code → tests → docs → release → monitoring → back into the spec you don't write tickets anymore - you write the thing tickets get derived from, and Opus 5 cuts the spec into 6 tasks by itself. a task that fails its test comes back to itself, not to you - and runs a second lap without a single notification. 6 lanes of code run in parallel and none of them wait on you - the critic filters the diff before you ever open it. every new production bug becomes a permanent line in the eval set - the system never steps on it twice. monitoring isn't the end of the line, it's the start of the next spec - those back edges are what make it a graph instead of a conveyor. and one place is left where you say yes - release, 5 minutes instead of 5 hours. save this and paste it into Claude Code - and you get 7 loops that run without you ↓

ANTHROPIC LEAKED A SETUP WHERE ONE FILE STARTS 7 LOOPS THAT TURN A PROMPT INTO A WORKING BUSINESS AI engineer drops in 1 file - the other 95% of the work closes automatically without them. spec → tasks → code → tests → docs → release → monitoring → back into the spec you don't write tickets anymore - you write the thing tickets get derived from, and Opus 5 cuts the spec into 6 tasks by itself. a task that fails its test comes back to itself, not to you - and runs a second lap without a single notification. 6 lanes of code run in parallel and none of them wait on you - the critic filters the diff before you ever open it. every new production bug becomes a permanent line in the eval set - the system never steps on it twice. monitoring isn't the end of the line, it's the start of the next spec - those back edges are what make it a graph instead of a conveyor. and one place is left where you say yes - release, 5 minutes instead of 5 hours. save this and paste it into Claude Code - and you get 7 loops that run without you ↓

Sprytix

66,250 次观看 • 14 天前

This month and every month make sure you take care of your mental health. Every morning I wake up and tell myself it’s going to be a great day. Then I hit the gym, even 15 or 20 minutes if that’s all I have, because I know if I do that, I’ve already accomplished something before the day really starts. Watch what you put in your brain too. If you fill it with garbage, it starts reacting to the world through a garbage prism. Practice gratitude by telling the people around you that you love them. Getting two or three real things done at work. And every so often — disappear for three days. Read a book, go to a spa or just stare at a wall. You have to take care of the mind. Nobody else is going to do it for you.

This month and every month make sure you take care of your mental health. Every morning I wake up and tell myself it’s going to be a great day. Then I hit the gym, even 15 or 20 minutes if that’s all I have, because I know if I do that, I’ve already accomplished something before the day really starts. Watch what you put in your brain too. If you fill it with garbage, it starts reacting to the world through a garbage prism. Practice gratitude by telling the people around you that you love them. Getting two or three real things done at work. And every so often — disappear for three days. Read a book, go to a spa or just stare at a wall. You have to take care of the mind. Nobody else is going to do it for you.

Anthony Scaramucci

37,204 次观看 • 2 个月前

OFFROAD X AFReality2026 #TRUEAF2026xOFFROAD #ออฟโรด #Offroad #OffroadKTP 💬 Have you ever been on stage and felt scared of disappointing your fans? 🚗: Honestly… I did worry about that a lot because I had no experience in singing or dancing and had never worked in this field before. Every day there was this question, “How can you be an artist when you sing and dance like this?” I have always been aware of this. However, what do I really gain from focusing on it? I just feel like, if I want to make the fans proud or not let them down, I just need to practice and improve myself, right? Like taking singing classes to improve my skills. Show it to them. You don’t have to say much. (Just be like), “Alright, just wait and see. I will show you how good I can get” (and) “I am going to make you proud, watch me”. When they see my progress with every stage, it becomes something that makes me proud like “Yeah, I did it”

OFFROAD X AFReality2026 #TRUEAF2026xOFFROAD #ออฟโรด #Offroad #OffroadKTP 💬 Have you ever been on stage and felt scared of disappointing your fans? 🚗: Honestly… I did worry about that a lot because I had no experience in singing or dancing and had never worked in this field before. Every day there was this question, “How can you be an artist when you sing and dance like this?” I have always been aware of this. However, what do I really gain from focusing on it? I just feel like, if I want to make the fans proud or not let them down, I just need to practice and improve myself, right? Like taking singing classes to improve my skills. Show it to them. You don’t have to say much. (Just be like), “Alright, just wait and see. I will show you how good I can get” (and) “I am going to make you proud, watch me”. When they see my progress with every stage, it becomes something that makes me proud like “Yeah, I did it”

𝐟𝐢𝐥𝐦.

11,568 次观看 • 1 个月前

So I spent the last hour turning it into a mini game lol... I'll polish it up and release it tomorrow on itch for free or donations. I need more balloons...so if you have SFW transparent PNGs of your inflated self, give me them, I'll add you.

Sensitive content

So I spent the last hour turning it into a mini game lol... I'll polish it up and release it tomorrow on itch for free or donations. I need more balloons...so if you have SFW transparent PNGs of your inflated self, give me them, I'll add you.

Mistress Bubblicious

22,709 次观看 • 2 年前