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。

ANTHROPIC LEAKED 6 RULES THAT LET ONE FOLDER REPLACE A WHOLE AI ENGINEERING TEAM COSTING $3.2M A YEAR folder with 6 files replaced the AI engineers - and the team that spent 4 years writing them isn't needed anymore. file → commit → description matches → loads → runs... → leaves a prompt has no history, a folder has a git log - one commit updates every session at once, and every edit shows up in the diff. two prompts fight over one window - two skills just both apply, and nobody merges anything by hand. 8 skills sit on disk, one enters the context - the other seven cost zero tokens until the description matches. a prompt can only ask - the folder carries build py and template.docx inside it, so the deterministic parts stay deterministic. the same skill works in Claude Code, in Cowork and through the API - a prompt lives only in the window you pasted it into. and the main one: a skill leaves the window when it's done - a prompt never leaves. save this - 6 rules, one folder, zero copy-paste ↓show more

Sprytix

6,271 subscribers

11,389 次观看 • 10 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

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 次观看 • 17 天前

New in Box Drive: right-click any file or folder and open it directly in the Claude or Cursor desktop apps. One right-click. One prompt. The agent reviews every contract in the folder, flags the risks, builds a comparison table and a risk memo, and saves both back to Box. All your content. Any AI agent. Right from your desktop.

New in Box Drive: right-click any file or folder and open it directly in the Claude or Cursor desktop apps. One right-click. One prompt. The agent reviews every contract in the folder, flags the risks, builds a comparison table and a risk memo, and saves both back to Box. All your content. Any AI agent. Right from your desktop.

Box

316,999 次观看 • 7 天前

REAL ESTATE PEOPLE WILL HATE HIM FOR THIS. HE BUILT A CLAUDE AGENT THAT TURNS ANY LISTING INTO A SELLABLE VIDEO ON ITS OWN Playbook: connect Claude to a video generator, paste a listing, get a cinematic tour of every room, sell it to the agent But typing the prompt for every listing doesn't scale. He turned it into a skill his Claude runs on its own Here's how to build the automated version: 1. Connect the video engine once. In Claude, go to Customize, Connectors, Add Custom Connector, name it Higgsfield, and paste the server URL from higgsfield. ai/mcp. Authenticate through your account. No API keys. Now Claude can generate video straight from chat 2. Turn the workflow into a skill. Instead of pasting the same prompt every time, have Claude build a skill. Tell it: "Create a skill called listing-to-video. When I give it a listing URL, scrape the room photos, generate a cinematic clip of each room with Higgsfield, and save them to a folder." Now the whole process is one command, not a wall of text 3. Let the agent run the listing. Hand it a URL and say "run listing-to-video on this." It pulls the photos, fires each room through the video model, and brings the clips back. You wrote the prompt once, inside the skill. You never write it again 4. Stitch and deliver. Drop the clips together into one tour. Send a free sample to the listing's agent, then charge per video or a monthly rate for ongoing listings 5. Scale it with your team. Add a skill that drafts the outreach email and one that builds a simple landing page for the agent. Now one operator runs sourcing, production, and pitching from a single Claude session The edge isn't generating one video. It's building the skill once so every future listing runs itself Bookmark this

REAL ESTATE PEOPLE WILL HATE HIM FOR THIS. HE BUILT A CLAUDE AGENT THAT TURNS ANY LISTING INTO A SELLABLE VIDEO ON ITS OWN Playbook: connect Claude to a video generator, paste a listing, get a cinematic tour of every room, sell it to the agent But typing the prompt for every listing doesn't scale. He turned it into a skill his Claude runs on its own Here's how to build the automated version: 1. Connect the video engine once. In Claude, go to Customize, Connectors, Add Custom Connector, name it Higgsfield, and paste the server URL from higgsfield. ai/mcp. Authenticate through your account. No API keys. Now Claude can generate video straight from chat 2. Turn the workflow into a skill. Instead of pasting the same prompt every time, have Claude build a skill. Tell it: "Create a skill called listing-to-video. When I give it a listing URL, scrape the room photos, generate a cinematic clip of each room with Higgsfield, and save them to a folder." Now the whole process is one command, not a wall of text 3. Let the agent run the listing. Hand it a URL and say "run listing-to-video on this." It pulls the photos, fires each room through the video model, and brings the clips back. You wrote the prompt once, inside the skill. You never write it again 4. Stitch and deliver. Drop the clips together into one tour. Send a free sample to the listing's agent, then charge per video or a monthly rate for ongoing listings 5. Scale it with your team. Add a skill that drafts the outreach email and one that builds a simple landing page for the agent. Now one operator runs sourcing, production, and pitching from a single Claude session The edge isn't generating one video. It's building the skill once so every future listing runs itself Bookmark this

Yarchi

54,840 次观看 • 2 个月前

ONE PROMPT AND ONE BUTTON NOW BUILDS A FULL SYSTEM, DATABASE, BACKEND, AND FRONTEND INCLUDED Most people still picture AI as something you ask questions to, then copy the answer into your own code by hand. A builder wired Claude into Obsidian through MCP instead, so a single written prompt becomes the actual spec for the system. Claude breaks that prompt into database schema, UI components, and API endpoints on its own, then writes, runs, and fixes the code until it actually works. MCP is what makes this possible, it lets the agent see the filesystem, installed packages, and running services before it starts building anything. The output isn't a code snippet sitting in a chat window, it's a live local app running on its own server, ready to open in a browser. What used to need a backend developer, a DevOps engineer, and two weeks now finishes in under fifteen minutes. See the full architecture and prompt structure below👇

ONE PROMPT AND ONE BUTTON NOW BUILDS A FULL SYSTEM, DATABASE, BACKEND, AND FRONTEND INCLUDED Most people still picture AI as something you ask questions to, then copy the answer into your own code by hand. A builder wired Claude into Obsidian through MCP instead, so a single written prompt becomes the actual spec for the system. Claude breaks that prompt into database schema, UI components, and API endpoints on its own, then writes, runs, and fixes the code until it actually works. MCP is what makes this possible, it lets the agent see the filesystem, installed packages, and running services before it starts building anything. The output isn't a code snippet sitting in a chat window, it's a live local app running on its own server, ready to open in a browser. What used to need a backend developer, a DevOps engineer, and two weeks now finishes in under fifteen minutes. See the full architecture and prompt structure below👇

wast3

20,348 次观看 • 1 个月前

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

MY FRIEND MADE $1.2M WRITING A 3D GAME WITH ONE PROMPT USING KIMI K3 open world, multiplayer, PVP mode, skins, team play with friends - all from one prompt in one session what used to take a team of 10 developers 6 months - he did alone in 10 minutes players started sharing the game themselves - organic growth with zero ads and zero marketing budget first $1,000 came the same day - a year later the account had $1.2M zero code written by hand, zero team, zero investment - just the right tool and the right prompt Kimi K3 - 2.8 trillion parameters, 1 million token context - exactly what made it possible to build the entire game in one request

MY FRIEND MADE $1.2M WRITING A 3D GAME WITH ONE PROMPT USING KIMI K3 open world, multiplayer, PVP mode, skins, team play with friends - all from one prompt in one session what used to take a team of 10 developers 6 months - he did alone in 10 minutes players started sharing the game themselves - organic growth with zero ads and zero marketing budget first $1,000 came the same day - a year later the account had $1.2M zero code written by hand, zero team, zero investment - just the right tool and the right prompt Kimi K3 - 2.8 trillion parameters, 1 million token context - exactly what made it possible to build the entire game in one request

Noisy

24,322 次观看 • 1 个月前

A guy runs 3 AI businesses from a chair and one prints $100,000 a month with zero employees. Everyone has the same AI now. Most of it spits out slop because they hand it a prompt and pray. He hands it a brain. Before his agent writes 1 word, it reads everything. A copywriting skill he built himself, a headline swipe file, his own marketing notes, and David Frey's 12-step sales letter system. Then it opens the context folder and swallows the whole company. The full knowledge base, the customer avatar, the exact questions real members ask in the private group. The tool is free and it's called Obsidian. Folders and files, nothing fancy. The skills are his, the context is his, and that's the part nobody can copy. Same model everyone else has. 1 guy builds slop, 1 guy builds $100,000 a month. The difference was never the AI. It was everything you fed it first.

Veltrx

15,691 次观看 • 1 个月前

i keep telling people to build this and they nod politely and never do it... andrej karpathy posted how to fix this a while ago, and everyone just keeps working the old way the dumb thing is this... you pay to teach claude the same lessons over and over, every chat is a fresh amnesia patient, every contradiction it catches evaporates the second you close the tab, and you accept this like it's just how ai works 1. one folder is a graveyard for originals that nobody edits, another folder is claude's active memory that only claude writes to, a third folder is a two-page rulebook that keeps claude from confusing them 2. a raw file gets read the day it arrives and then it's done, claude never touches it again, everything it needed is already extracted into wiki pages with the source cited right there 3. every time claude notices your new answer clashes with your old one, it doesn't pick a side, it writes both with dates, and from then on it treats you like someone who might be wrong the raw folder is a museum... the wiki is the actual working brain full breakdown is in the article below

i keep telling people to build this and they nod politely and never do it... andrej karpathy posted how to fix this a while ago, and everyone just keeps working the old way the dumb thing is this... you pay to teach claude the same lessons over and over, every chat is a fresh amnesia patient, every contradiction it catches evaporates the second you close the tab, and you accept this like it's just how ai works 1. one folder is a graveyard for originals that nobody edits, another folder is claude's active memory that only claude writes to, a third folder is a two-page rulebook that keeps claude from confusing them 2. a raw file gets read the day it arrives and then it's done, claude never touches it again, everything it needed is already extracted into wiki pages with the source cited right there 3. every time claude notices your new answer clashes with your old one, it doesn't pick a side, it writes both with dates, and from then on it treats you like someone who might be wrong the raw folder is a museum... the wiki is the actual working brain full breakdown is in the article below

kai

32,120 次观看 • 18 天前

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 次观看 • 1 个月前

Most people use Claude Code like a chatbot, then wonder why it forgets everything by Tuesday. The ones quietly building $10K AI workflows give it a second brain instead, and it’s free. It’s called Obsidian. You download it, point it at one folder on your computer, and that folder becomes a vault. Every note inside it is now something Claude Code can read end to end. Open Claude in that folder and it’s connected, that simple. The trick isn’t the tool, it’s the map. 3 folders, that’s the whole system. Raw, you dump everything here. Notes, transcripts, screenshots, half thoughts, zero structure. Wiki, Claude reads the raw pile and writes clean Wikipedia style articles about it, structured, searchable, permanent. Output, when you want a deliverable, a PDF, a slide deck, a script, it pulls from the wiki and ships it. Most people skip the wiki layer and feed Claude a junk drawer of 400 files, then blame the model when the answers are garbage. The model isn’t the problem, your folder is. Give it a path it can follow and it finds anything in 1 second, give it chaos and it guesses. You don’t even have to design the structure yourself. Open the vault, tell Claude to build a file system that fits your work, and watch it organize your entire brain in one prompt. Free tool, 3 folders, a second brain that compounds while you sleep. The people falling behind are still copy pasting into a chat window.

Most people use Claude Code like a chatbot, then wonder why it forgets everything by Tuesday. The ones quietly building $10K AI workflows give it a second brain instead, and it’s free. It’s called Obsidian. You download it, point it at one folder on your computer, and that folder becomes a vault. Every note inside it is now something Claude Code can read end to end. Open Claude in that folder and it’s connected, that simple. The trick isn’t the tool, it’s the map. 3 folders, that’s the whole system. Raw, you dump everything here. Notes, transcripts, screenshots, half thoughts, zero structure. Wiki, Claude reads the raw pile and writes clean Wikipedia style articles about it, structured, searchable, permanent. Output, when you want a deliverable, a PDF, a slide deck, a script, it pulls from the wiki and ships it. Most people skip the wiki layer and feed Claude a junk drawer of 400 files, then blame the model when the answers are garbage. The model isn’t the problem, your folder is. Give it a path it can follow and it finds anything in 1 second, give it chaos and it guesses. You don’t even have to design the structure yourself. Open the vault, tell Claude to build a file system that fits your work, and watch it organize your entire brain in one prompt. Free tool, 3 folders, a second brain that compounds while you sleep. The people falling behind are still copy pasting into a chat window.

West Lord

32,845 次观看 • 1 个月前

open Claude Code type a prompt. one model does everything. congrats, you just used 20% of it meanwhile I built 30 sub-agents one reviews my code before commit one finds bugs and writes the patch one drafts cold emails from one line one triages my inbox before I wake up one logs every decision so future me knows why each agent = one markdown file in .claude/agents/ most Claude Code users don't even know this exists. all 30 files in the article. ready to copy. the article has every file. every prompt. just copy and run.

open Claude Code type a prompt. one model does everything. congrats, you just used 20% of it meanwhile I built 30 sub-agents one reviews my code before commit one finds bugs and writes the patch one drafts cold emails from one line one triages my inbox before I wake up one logs every decision so future me knows why each agent = one markdown file in .claude/agents/ most Claude Code users don't even know this exists. all 30 files in the article. ready to copy. the article has every file. every prompt. just copy and run.

Nav Toor

71,467 次观看 • 3 个月前

you're running /compact every 10 minutes to fix a problem that disappears the second you give Claude one job instead of five. Anthropic shipped a clean 4-minute video on context management. /compact when the window fills up. /clear to reset. small files over big files. the practical tips work. the video covers the cleanup. it doesn't cover why your window keeps filling up in the first place, and the answer is usually that you're holding too many jobs in one prompt. look at what most people put in a single Claude call: > guess the right answer > choose between options > set the position size > watch the exit window > read the news for sentiment five tools' worth of state in one conversation. of course the window fills. i ran into this on a Polymarket bot: the prediction-layer version ate context constantly. /compact every 8-10 turns. i thought i needed better memory hygiene. i needed fewer jobs per call. i stripped the prompt down to one job: veto an entry i had already decided to take. the context window stopped filling. /compact went from every 8 turns to once a session, if ever. over 90 days that prompt blocked 128 trades. watch the 4 min, then ask why your window keeps needing it. clean context. lean prompt. nothing to compact.

you're running /compact every 10 minutes to fix a problem that disappears the second you give Claude one job instead of five. Anthropic shipped a clean 4-minute video on context management. /compact when the window fills up. /clear to reset. small files over big files. the practical tips work. the video covers the cleanup. it doesn't cover why your window keeps filling up in the first place, and the answer is usually that you're holding too many jobs in one prompt. look at what most people put in a single Claude call: > guess the right answer > choose between options > set the position size > watch the exit window > read the news for sentiment five tools' worth of state in one conversation. of course the window fills. i ran into this on a Polymarket bot: the prediction-layer version ate context constantly. /compact every 8-10 turns. i thought i needed better memory hygiene. i needed fewer jobs per call. i stripped the prompt down to one job: veto an entry i had already decided to take. the context window stopped filling. /compact went from every 8 turns to once a session, if ever. over 90 days that prompt blocked 128 trades. watch the 4 min, then ask why your window keeps needing it. clean context. lean prompt. nothing to compact.

Mnimiy

20,635 次观看 • 3 个月前

ANTHROPIC LEAKED A SETUP WHERE A $1.2M A-YEAR TEAM FITS INTO ONE FILE FOR $4 A DAY you hire nobody - you write one file, and $106,500 of salaries in it turn into $4 of tokens. architect → 4 builders → tests → critic → docs → scout → chief → back into the file the architect runs twice a day and decides everything - the priciest model on the sheet is the smallest line on the bill at $1.05. four builders cost $1.20 a day - and a fifth builder is one more number in the file, not one more quarter of recruiting. the tester asks does it run, the critic asks should it exist at all - $1.22 together for two roles a solo dev never fills. nothing reaches you that hasn't been rejected at least once. the scout and the scribe cost 40 cents - the exact two roles that get cut from every real budget. nobody hires a documentation engineer, and everybody wishes they had one. the chief at 14 cents is the only one who writes back into the file - without it this is a list, with it the list edits itself. hiring the eleventh is a paragraph: no req, no interviews, no ramp - and firing is one command. save this and paste it into Claude Code - and you get 10 roles for the price of one coffee ↓

ANTHROPIC LEAKED A SETUP WHERE A $1.2M A-YEAR TEAM FITS INTO ONE FILE FOR $4 A DAY you hire nobody - you write one file, and $106,500 of salaries in it turn into $4 of tokens. architect → 4 builders → tests → critic → docs → scout → chief → back into the file the architect runs twice a day and decides everything - the priciest model on the sheet is the smallest line on the bill at $1.05. four builders cost $1.20 a day - and a fifth builder is one more number in the file, not one more quarter of recruiting. the tester asks does it run, the critic asks should it exist at all - $1.22 together for two roles a solo dev never fills. nothing reaches you that hasn't been rejected at least once. the scout and the scribe cost 40 cents - the exact two roles that get cut from every real budget. nobody hires a documentation engineer, and everybody wishes they had one. the chief at 14 cents is the only one who writes back into the file - without it this is a list, with it the list edits itself. hiring the eleventh is a paragraph: no req, no interviews, no ramp - and firing is one command. save this and paste it into Claude Code - and you get 10 roles for the price of one coffee ↓

Sprytix

45,421 次观看 • 5 天前

A DEVELOPER PROVED YOU CAN FIND THE EXACT COMMIT THAT BROKE YOUR CODE IN A HISTORY OF 10,000 -- IN ABOUT 13 STEPS, AUTOMATICALLY.. 33 minutes from a Google engineer on git bisect: the built-in command that binary-searches your entire history to hunt down the one commit that introduced a bug. -> The moment it lands, "When did this break?" stops being an afternoon of guessing. You hand git a good commit, a bad one, and a test and it finds the culprit while you watch. Most people debug a regression by reading diffs by hand, blaming the obvious file, and hoping. Bisect doesn't hope. It cuts the search in half, then in half again, until only the guilty commit is left standing. Reading history by hand was never the skill -> letting git do the binary search for you is. And when an AI agent dumps hundreds of commits into your repo and one quietly breaks production, bisect is what finds the needle without you reading a single line. The bug isn't hiding. It's sitting in one exact commit. Most people just never learned to make git point at it. Bookmark & Watch it today ↓

A DEVELOPER PROVED YOU CAN FIND THE EXACT COMMIT THAT BROKE YOUR CODE IN A HISTORY OF 10,000 -- IN ABOUT 13 STEPS, AUTOMATICALLY.. 33 minutes from a Google engineer on git bisect: the built-in command that binary-searches your entire history to hunt down the one commit that introduced a bug. -> The moment it lands, "When did this break?" stops being an afternoon of guessing. You hand git a good commit, a bad one, and a test and it finds the culprit while you watch. Most people debug a regression by reading diffs by hand, blaming the obvious file, and hoping. Bisect doesn't hope. It cuts the search in half, then in half again, until only the guilty commit is left standing. Reading history by hand was never the skill -> letting git do the binary search for you is. And when an AI agent dumps hundreds of commits into your repo and one quietly breaks production, bisect is what finds the needle without you reading a single line. The bug isn't hiding. It's sitting in one exact commit. Most people just never learned to make git point at it. Bookmark & Watch it today ↓

slash1s

37,773 次观看 • 2 个月前

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.

NO1ennn

13,359 次观看 • 11 天前

The number one question I get in the Claude Code / Cowork Community: "how do I share my Cowork skills with my team?" Here's the problem. You build a great skill. You zip it up. You drop it in Slack. Your teammate downloads it, uploads it, and maybe it works. Maybe they upload it wrong. Maybe you update the skill next week and nobody gets the new version. You're now maintaining skills through chat messages and hoping for the best. That doesn't scale. I just put out a video breaking down the three methods I've tested for sharing skills and plugins across a team. From dead simple to fully synced. Method 1: Shared drive (Google Drive, SharePoint, etc). You put your skill files in a shared folder. Teammates download and upload them into Cowork. It works, but updates are manual and there's no version control. Method 2: Built-in sharing on Team and Enterprise plans. You can share any skill directly with a colleague or publish it to your org directory. When you update the skill, everyone gets the update automatically. This is the easiest path if you're on a paid plan. The catch: there's no approval workflow for org-wide sharing, so set a clear owner. Method 3: GitHub repo. This is what I use. Your entire Cowork workspace -- skills, plugins, claude.md, folder structure, project files -- lives in a private repo. Teammates clone it. When you push an update, they pull it. Everyone stays in sync. You get version history, access control, and a single source of truth. The GitHub method sounds technical, but it's really just two steps: clone the repo, point Cowork at the folder. I walk through the whole thing in the video, including how to use .gitignore to keep personal files (like your morning briefing) out of the shared repo. This works for Cowork, Claude Code, and Open Codex. The infrastructure is the same. Full video linked below. If you've found a different approach that works for your team, I want to hear about it. Comment or reply and let's figure out the best practices together.

The number one question I get in the Claude Code / Cowork Community: "how do I share my Cowork skills with my team?" Here's the problem. You build a great skill. You zip it up. You drop it in Slack. Your teammate downloads it, uploads it, and maybe it works. Maybe they upload it wrong. Maybe you update the skill next week and nobody gets the new version. You're now maintaining skills through chat messages and hoping for the best. That doesn't scale. I just put out a video breaking down the three methods I've tested for sharing skills and plugins across a team. From dead simple to fully synced. Method 1: Shared drive (Google Drive, SharePoint, etc). You put your skill files in a shared folder. Teammates download and upload them into Cowork. It works, but updates are manual and there's no version control. Method 2: Built-in sharing on Team and Enterprise plans. You can share any skill directly with a colleague or publish it to your org directory. When you update the skill, everyone gets the update automatically. This is the easiest path if you're on a paid plan. The catch: there's no approval workflow for org-wide sharing, so set a clear owner. Method 3: GitHub repo. This is what I use. Your entire Cowork workspace -- skills, plugins, claude.md, folder structure, project files -- lives in a private repo. Teammates clone it. When you push an update, they pull it. Everyone stays in sync. You get version history, access control, and a single source of truth. The GitHub method sounds technical, but it's really just two steps: clone the repo, point Cowork at the folder. I walk through the whole thing in the video, including how to use .gitignore to keep personal files (like your morning briefing) out of the shared repo. This works for Cowork, Claude Code, and Open Codex. The infrastructure is the same. Full video linked below. If you've found a different approach that works for your team, I want to hear about it. Comment or reply and let's figure out the best practices together.

JJ Englert

16,176 次观看 • 4 个月前

The gap between a PM getting AI slop from Claude Code and one getting 10x output is about one hour of file structure. Three folders. > A knowledge folder with static context: who you work with, what each stakeholder cares about, reference material that rarely changes. > A projects folder where every task accumulates research, drafts, and artifacts that load instantly into your next session. > And a people folder that auto-updates from meeting transcripts through Granola's MCP. The people folder is the part that compounds. Build a skill that pulls what each person said in your last meeting, what they pushed back on, what they committed to. Now when you draft a message to your VP of Engineering, Claude Code already knows their communication preferences from 30 real conversations. That's context no prompt can replicate. Carl walked through this system on the episode and the compounding math stuck with me. Day 1, Claude Code knows nothing about your work. Day 30, it knows your stakeholders, your project history, your patterns. Day 90, it's surfacing connections across your work you haven't consciously noticed. Then layer on skills. A standup command that pulls from GitHub, Linear, your calendar, and your task folder in one shot. Website traffic compared against your LinkedIn posts this week. Analyses that would be impossible clicking between individual UIs, running before your first meeting. One hour of setup. Compounding returns every day after. The PMs typing prompts into a blank terminal and the PMs who built the operating system around it are already producing completely different categories of work. Build the operating system.

The gap between a PM getting AI slop from Claude Code and one getting 10x output is about one hour of file structure. Three folders. > A knowledge folder with static context: who you work with, what each stakeholder cares about, reference material that rarely changes. > A projects folder where every task accumulates research, drafts, and artifacts that load instantly into your next session. > And a people folder that auto-updates from meeting transcripts through Granola's MCP. The people folder is the part that compounds. Build a skill that pulls what each person said in your last meeting, what they pushed back on, what they committed to. Now when you draft a message to your VP of Engineering, Claude Code already knows their communication preferences from 30 real conversations. That's context no prompt can replicate. Carl walked through this system on the episode and the compounding math stuck with me. Day 1, Claude Code knows nothing about your work. Day 30, it knows your stakeholders, your project history, your patterns. Day 90, it's surfacing connections across your work you haven't consciously noticed. Then layer on skills. A standup command that pulls from GitHub, Linear, your calendar, and your task folder in one shot. Website traffic compared against your LinkedIn posts this week. Analyses that would be impossible clicking between individual UIs, running before your first meeting. One hour of setup. Compounding returns every day after. The PMs typing prompts into a blank terminal and the PMs who built the operating system around it are already producing completely different categories of work. Build the operating system.

Aakash Gupta

82,865 次观看 • 4 个月前

A 26-YEAR-OLD AI ENGINEER WHOSE BIRMINGHAM THESIS OUTPERFORMED GOOGLE SCHOLAR BY 50% JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN Safi Shamsi built Graphify 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 43x fewer tokens per query. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: /safishamsi/graphify Setup, end to end: 1. Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. 2. Install the skill in Claude Code: graphify claude install. This wires Graphify into Claude Code so you can call it as a skill. 3. Open the folder you want mapped in Claude Code. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. 4. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. 5. Open the new vault in Obsidian (Manage vaults → Open folder as a vault), or drag it as a subfolder into your existing one. That's it. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this

A 26-YEAR-OLD AI ENGINEER WHOSE BIRMINGHAM THESIS OUTPERFORMED GOOGLE SCHOLAR BY 50% JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN Safi Shamsi built Graphify 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 43x fewer tokens per query. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: /safishamsi/graphify Setup, end to end: 1. Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. 2. Install the skill in Claude Code: graphify claude install. This wires Graphify into Claude Code so you can call it as a skill. 3. Open the folder you want mapped in Claude Code. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. 4. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. 5. Open the new vault in Obsidian (Manage vaults → Open folder as a vault), or drag it as a subfolder into your existing one. That's it. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this

Yarchi

141,580 次观看 • 2 个月前

Anthropic engineer just built a second brain that reads 3 files instead of 5,000, and cut the token bill 40% no orchestrator, no plugin, just a router file, an index, and code that scores before the model ever opens anything point claude at a flat folder of notes and every question reads all of them, that’s the default and it’s expensive this breakdown turns that exact pattern into a system anyone can run CLAUDE.md → index.md → nodes → edges → retrieval as code → memory → ship it twelve steps, one shared rule, evidence lives in the index, the model reads three files while the notes folder still holds thousands the stale index test, one line drifts and the whole graph quietly turns back into the pile it was built to escape, no exceptions save it and watch, then read the article below

Anthropic engineer just built a second brain that reads 3 files instead of 5,000, and cut the token bill 40% no orchestrator, no plugin, just a router file, an index, and code that scores before the model ever opens anything point claude at a flat folder of notes and every question reads all of them, that’s the default and it’s expensive this breakdown turns that exact pattern into a system anyone can run CLAUDE.md → index.md → nodes → edges → retrieval as code → memory → ship it twelve steps, one shared rule, evidence lives in the index, the model reads three files while the notes folder still holds thousands the stale index test, one line drifts and the whole graph quietly turns back into the pile it was built to escape, no exceptions save it and watch, then read the article below

leopardracer

37,304 次观看 • 23 天前

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 次观看 • 2 个月前