Charlie Hills's banner

Charlie Hills

@charliejhills • 15,788 subscribers

I help you (actually) use AI | [email protected]

Shorts

Anthropic just published its official prompting guide for Opus 5.5. If you're still writing prompts the way you did for Opus 5, you're paying more and getting less. Here's what changed 👇 1. Default to medium effort Medium on 5.5 already outperforms high on Opus 5, at a lower cost. Maxing it out by habit just burns tokens. 2. Drop "think step by step" Reasoning is built in now. The model decides how much thinking a task needs, so asking it to think harder adds nothing. 3. A check-in isn't a finish line On long runs, it sends progress updates along the way. If it stops to report, tell it to keep going. 4. Fence off anything you paste Put emails, docs, and web text in clearly labeled sections or tags. That way it can tell your instructions apart from the material it's working on. 5. Retire your image workarounds Those custom chart readers and OCR steps you built are probably dead weight. It reads screenshots, diagrams, and charts accurately on its own. 6. For design work, name what you don't want "Make it unique" gets you generic. "No purple gradients, no centered hero, no emoji icons" gets you something different. It follows specific bans much better than vague direction. ♻️ Repost to save someone a few API bills.

Sensitive content

Anthropic just published its official prompting guide for Opus 5.5. If you're still writing prompts the way you did for Opus 5, you're paying more and getting less. Here's what changed 👇 1. Default to medium effort Medium on 5.5 already outperforms high on Opus 5, at a lower cost. Maxing it out by habit just burns tokens. 2. Drop "think step by step" Reasoning is built in now. The model decides how much thinking a task needs, so asking it to think harder adds nothing. 3. A check-in isn't a finish line On long runs, it sends progress updates along the way. If it stops to report, tell it to keep going. 4. Fence off anything you paste Put emails, docs, and web text in clearly labeled sections or tags. That way it can tell your instructions apart from the material it's working on. 5. Retire your image workarounds Those custom chart readers and OCR steps you built are probably dead weight. It reads screenshots, diagrams, and charts accurately on its own. 6. For design work, name what you don't want "Make it unique" gets you generic. "No purple gradients, no centered hero, no emoji icons" gets you something different. It follows specific bans much better than vague direction. ♻️ Repost to save someone a few API bills.

190,126 görüntüleme

GitHub is blowing up with free alternatives to paid AI tools Here are 10 GitHub repos worth bookmarking if you’re tired of paying monthly for tools you could run yourself: - TradingAgents: Multi-agent AI trading research - LibreChat: ChatGPT, Claude and Gemini in one interface - HyperFrames: Open-source video generation by HeyGen - Fincept Terminal: An open-source Bloomberg alternative - MoneyPrinterTurbo: One-click short-form videos - Agentic Inbox: AI email assistant by Cloudflare - VoxCPM: Realistic AI voice cloning - Flowsint: OSINT investigation and analysis - agent-skills: Ready-made skills for Claude Code - Nango: Open-source API integrations

GitHub is blowing up with free alternatives to paid AI tools Here are 10 GitHub repos worth bookmarking if you’re tired of paying monthly for tools you could run yourself: - TradingAgents: Multi-agent AI trading research - LibreChat: ChatGPT, Claude and Gemini in one interface - HyperFrames: Open-source video generation by HeyGen - Fincept Terminal: An open-source Bloomberg alternative - MoneyPrinterTurbo: One-click short-form videos - Agentic Inbox: AI email assistant by Cloudflare - VoxCPM: Realistic AI voice cloning - Flowsint: OSINT investigation and analysis - agent-skills: Ready-made skills for Claude Code - Nango: Open-source API integrations

19,435 görüntüleme

This is getting ridiculous. GPT Image 2.5 is here. Look at the image on the right (that's AI-generated). DALL·E 3 came out in September 2023. GPT Image 1 was huge for editing, but the portraits still had that AI look. Then 1.5 came along. Now look at 2.0 and 2.5. Imagine where we'll be in another 3 years. Here's the exact portrait prompt (unchanged): "A high-resolution, photorealistic, close-up portrait of a woman. The woman, softly and evenly lit, has an oval-shaped face with an even more pronounced oval jawline. She sports an asymmetric bob hairstyle, her hair cut to ear-length. She has an impressively straight nose contour, with the base of her nose being equally straight. The image is a splendid display of macrophotography, with a shallow depth of field adding an extra layer of interest to it. The textures are incredibly detailed, adding much to the overall realism of the image." Try it yourself. You'll see. Get my free AI workflows → Repost ♻️ to help someone in your network.

This is getting ridiculous. GPT Image 2.5 is here. Look at the image on the right (that's AI-generated). DALL·E 3 came out in September 2023. GPT Image 1 was huge for editing, but the portraits still had that AI look. Then 1.5 came along. Now look at 2.0 and 2.5. Imagine where we'll be in another 3 years. Here's the exact portrait prompt (unchanged): "A high-resolution, photorealistic, close-up portrait of a woman. The woman, softly and evenly lit, has an oval-shaped face with an even more pronounced oval jawline. She sports an asymmetric bob hairstyle, her hair cut to ear-length. She has an impressively straight nose contour, with the base of her nose being equally straight. The image is a splendid display of macrophotography, with a shallow depth of field adding an extra layer of interest to it. The textures are incredibly detailed, adding much to the overall realism of the image." Try it yourself. You'll see. Get my free AI workflows → Repost ♻️ to help someone in your network.

55,049 görüntüleme

This Mac launch film is 100% code. Opus 5.5 made the notch, the widgets and the wallpapers from one brief. The bit that made the difference was the free apple-design skill. I had it tear apart my first version, list everything that looked cheap, and rebuild it. Full brief is here if you want to try it:

This Mac launch film is 100% code. Opus 5.5 made the notch, the widgets and the wallpapers from one brief. The bit that made the difference was the free apple-design skill. I had it tear apart my first version, list everything that looked cheap, and rebuild it. Full brief is here if you want to try it:

19,944 görüntüleme

I rewrote my system prompt for GPT-6 Astra this week and cut it in half. It works better now. Here's why, straight from OpenAI's new Astra guide: Astra isn't a faster GPT-5 It's a different worker GPT-5 needed instructions. Astra needs boundaries. So most of what I had written was noise. → "Run tests after every change." It already does that. → "Check with me before continuing." It already does that too, sometimes too much. The stuff that actually matters: → Where can it assume, and where does it need to ask? Spell that out. → What does done look like? If you don't say, it won't know when to stop. → Which rule wins when two clash? Old AGENTS.md files are full of contradictions Astra now takes literally. → Keep your skills short. One sentence each. Long descriptions blur together and it ends up ignoring all of them. Old way → Micromanage every step → Astra stalls New way → Set the boundaries → Astra runs Stop writing prompts like a manager hovering over someone's desk. Write them like a brief you'd hand to a senior engineer and then leave the room. The full guide is on OpenAI's developer docs. Worth 10 minutes before your next build.

I rewrote my system prompt for GPT-6 Astra this week and cut it in half. It works better now. Here's why, straight from OpenAI's new Astra guide: Astra isn't a faster GPT-5 It's a different worker GPT-5 needed instructions. Astra needs boundaries. So most of what I had written was noise. → "Run tests after every change." It already does that. → "Check with me before continuing." It already does that too, sometimes too much. The stuff that actually matters: → Where can it assume, and where does it need to ask? Spell that out. → What does done look like? If you don't say, it won't know when to stop. → Which rule wins when two clash? Old AGENTS.md files are full of contradictions Astra now takes literally. → Keep your skills short. One sentence each. Long descriptions blur together and it ends up ignoring all of them. Old way → Micromanage every step → Astra stalls New way → Set the boundaries → Astra runs Stop writing prompts like a manager hovering over someone's desk. Write them like a brief you'd hand to a senior engineer and then leave the room. The full guide is on OpenAI's developer docs. Worth 10 minutes before your next build.

21,478 görüntüleme

Holy moly. 🤯 Jack Dorsey just gave away, for free, a full toolkit for running a company where AI agents work right next to your human team. His company Block put it on GitHub. It's already past 29,000 stars. Here's how you set it up takes about 5 minutes: 1. Copy (clone) the code from GitHub. 2. Run your own server. This is where your chats, search, code, and automatic tasks all live. 3. Add your AI agent into a chat channel, just like adding a new team member. Tell it what it's allowed to do, and let it work with your team live. No fees. No middleman. Just you, your team, and your AI agents all in one place you control. This might be what running a business looks like from now on Worth saving.

Holy moly. 🤯 Jack Dorsey just gave away, for free, a full toolkit for running a company where AI agents work right next to your human team. His company Block put it on GitHub. It's already past 29,000 stars. Here's how you set it up takes about 5 minutes: 1. Copy (clone) the code from GitHub. 2. Run your own server. This is where your chats, search, code, and automatic tasks all live. 3. Add your AI agent into a chat channel, just like adding a new team member. Tell it what it's allowed to do, and let it work with your team live. No fees. No middleman. Just you, your team, and your AI agents all in one place you control. This might be what running a business looks like from now on Worth saving.

14,039 görüntüleme

I had to write the same Claude Code prompt 40 times in one month. Good news! Anthropic already made them. The official Claude Code prompts are sorted by task and role in the documentation and are ready to be copied and pasted. These prompts were drawn from what our teams use on a daily basis while working with Claude Code. Examples of the types of tasks these prompts cover include: * Planning * Debugging * Code review * Security * Automation Even better, each prompt describes why it works and what you're trying to achieve. This helps you learn what makes a good prompt, and eventually craft your own versions. The prompts are completely free, and we have the link below ⬇️

I had to write the same Claude Code prompt 40 times in one month. Good news! Anthropic already made them. The official Claude Code prompts are sorted by task and role in the documentation and are ready to be copied and pasted. These prompts were drawn from what our teams use on a daily basis while working with Claude Code. Examples of the types of tasks these prompts cover include: * Planning * Debugging * Code review * Security * Automation Even better, each prompt describes why it works and what you're trying to achieve. This helps you learn what makes a good prompt, and eventually craft your own versions. The prompts are completely free, and we have the link below ⬇️

17,461 görüntüleme

PewDiePie just hit 20K GitHub stars in under 24 hours. The project? Odysseus. A self-hosted AI workspace that runs 100% on your machine. • Agents with tools • MCP built in • Persistent memory • File handling • Windows, macOS, Linux Your data never leaves your device. It supports Ollama, llama.cpp, and vLLM locally with OpenAI and OpenRouter support if you want cloud models too. The crazy part? A YouTuber with 110M+ subscribers just out-shipped most AI startups. And he built half of it using AI.

PewDiePie just hit 20K GitHub stars in under 24 hours. The project? Odysseus. A self-hosted AI workspace that runs 100% on your machine. • Agents with tools • MCP built in • Persistent memory • File handling • Windows, macOS, Linux Your data never leaves your device. It supports Ollama, llama.cpp, and vLLM locally with OpenAI and OpenRouter support if you want cloud models too. The crazy part? A YouTuber with 110M+ subscribers just out-shipped most AI startups. And he built half of it using AI.

16,546 görüntüleme

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Claude Motion makes the animation now You bring the taste. My 4 steps: 1. Find a style reference (I went for Apple) 2. Turn it into one file: your colours, fonts and how things move 3. Attach the file and describe one moment 4. Change words in Tweaks, colours in Style, then export It checked its own frames and fixed them before it showed me. (Team and Enterprise plans only for now.) Comment APPLE and I'll send you my full Apple brief. Make sure you follow me so I can DM you!

Claude Motion makes the animation now You bring the taste. My 4 steps: 1. Find a style reference (I went for Apple) 2. Turn it into one file: your colours, fonts and how things move 3. Attach the file and describe one moment 4. Change words in Tweaks, colours in Style, then export It checked its own frames and fixed them before it showed me. (Team and Enterprise plans only for now.) Comment APPLE and I'll send you my full Apple brief. Make sure you follow me so I can DM you!

29,826 görüntüleme • 7 gün önce

I gave Opus 5.5, GPT-6 Astra and Fable 5.1 the same raw video, the same brief and my real YouTube editing process (the one I use for my own videos): 1. Give each model the same footage and reference. 2. Ask to cut the pauses and turn your words into visuals. 3. Review the first 10 seconds, then fix it round by round. Which edit came out better? You can get the guide here:

I gave Opus 5.5, GPT-6 Astra and Fable 5.1 the same raw video, the same brief and my real YouTube editing process (the one I use for my own videos): 1. Give each model the same footage and reference. 2. Ask to cut the pauses and turn your words into visuals. 3. Review the first 10 seconds, then fix it round by round. Which edit came out better? You can get the guide here:

77,218 görüntüleme • 20 gün önce

This is the one prompt that stops AI from gaslighting you. Force AI to tell the truth. No sugarcoating. No hallucinations. No fake confidence. Brutally honest answers. Every time. I packaged my reality filter prompt into a plug-and-play guide To get it, just: → Comment “REALITY” → Follow me (so I can DM)

This is the one prompt that stops AI from gaslighting you. Force AI to tell the truth. No sugarcoating. No hallucinations. No fake confidence. Brutally honest answers. Every time. I packaged my reality filter prompt into a plug-and-play guide To get it, just: → Comment “REALITY” → Follow me (so I can DM)

343,603 görüntüleme • 8 ay önce

This is insane. Opus 5.5 made this entire video. Here's how I set it up in 10 steps: Every prompt I used is in my newsletter (free). Get the full walkthrough First, get Claude ready (both installs are free): 1. Open Claude Code and pick Opus 5.5 2. Install the HyperFrames video skill 3. Add my 13 free motion skills 4. Test it. Tell it to go all out It writes the animation as code, then renders an MP4. So you edit it by describing the change. Then make something people actually share: 5. Give it a proper brief, not one line 6. Give notes like you would a designer Mine was "Why do we dream?" (it found a source for every fact before it drew a thing). Now make it look like yours, not everyone else's: 7. Turn 5 frames you like into MOTION.md 8. Make Claude read them before every build 9. Add Apple's motion rules, then ask for an audit 10. Use real components from not drawn ones Step 8 is the one that makes it look like mine. Without it, the same prompt picks its own style. Repost ♻️ to help someone in your network.

This is insane. Opus 5.5 made this entire video. Here's how I set it up in 10 steps: Every prompt I used is in my newsletter (free). Get the full walkthrough First, get Claude ready (both installs are free): 1. Open Claude Code and pick Opus 5.5 2. Install the HyperFrames video skill 3. Add my 13 free motion skills 4. Test it. Tell it to go all out It writes the animation as code, then renders an MP4. So you edit it by describing the change. Then make something people actually share: 5. Give it a proper brief, not one line 6. Give notes like you would a designer Mine was "Why do we dream?" (it found a source for every fact before it drew a thing). Now make it look like yours, not everyone else's: 7. Turn 5 frames you like into MOTION.md 8. Make Claude read them before every build 9. Add Apple's motion rules, then ask for an audit 10. Use real components from not drawn ones Step 8 is the one that makes it look like mine. Without it, the same prompt picks its own style. Repost ♻️ to help someone in your network.

20,855 görüntüleme • 21 gün önce

Someone gave GPT-6 and Fable 5.1 access to Canva. One smoked the other (it's not even close). Claude Fable 5.1 is on the left. GPT-6 Astra is on the right. The gap is not small. It comes down to one test (ARC-AGI 3). It drops a model into a game with no instructions and makes it work them out. Astra solved levels in fewer moves than you or I would, 96% of the time. Claude Opus 5 managed less than half of that. That's why everyone is shouting about AGI again. You can turn this on yourself in about two minutes: 1. Open the ChatGPT desktop app, switch to Work. 2. Go to Plugins, then Computer Use. Install it. 3. Switch on the server and skill toggles. 4. Allow Screen Recording and Accessibility. 5. Point it at one app and ask it do something. I wrote up the full Claude → Codex migration. Access it here → Repost ♻️ to help someone in your network.

Someone gave GPT-6 and Fable 5.1 access to Canva. One smoked the other (it's not even close). Claude Fable 5.1 is on the left. GPT-6 Astra is on the right. The gap is not small. It comes down to one test (ARC-AGI 3). It drops a model into a game with no instructions and makes it work them out. Astra solved levels in fewer moves than you or I would, 96% of the time. Claude Opus 5 managed less than half of that. That's why everyone is shouting about AGI again. You can turn this on yourself in about two minutes: 1. Open the ChatGPT desktop app, switch to Work. 2. Go to Plugins, then Computer Use. Install it. 3. Switch on the server and skill toggles. 4. Allow Screen Recording and Accessibility. 5. Point it at one app and ask it do something. I wrote up the full Claude → Codex migration. Access it here → Repost ♻️ to help someone in your network.

38,355 görüntüleme • 1 ay önce

Run a full coding agent locally. No API bills. No limits. No data leaving your machine. Private. Powerful. 100% free. I made a step-by-step guide anyone can follow in minutes. To get it, just: → Like + Repost → Comment “LOCAL” → Follow me (so I can DM)

Run a full coding agent locally. No API bills. No limits. No data leaving your machine. Private. Powerful. 100% free. I made a step-by-step guide anyone can follow in minutes. To get it, just: → Like + Repost → Comment “LOCAL” → Follow me (so I can DM)

169,950 görüntüleme • 8 ay önce

Someone gave Claude Code permanent memory. → 95% fewer tokens per session → Never hits context limits → Picks up exactly where you left off → 46,000 GitHub stars in 48 hours One command: `npx claude-mem install` Completely free. Community-built. Not Anthropic. Claude Code is exceptional. It just kept forgetting everything. This fixes that.

Someone gave Claude Code permanent memory. → 95% fewer tokens per session → Never hits context limits → Picks up exactly where you left off → 46,000 GitHub stars in 48 hours One command: `npx claude-mem install` Completely free. Community-built. Not Anthropic. Claude Code is exceptional. It just kept forgetting everything. This fixes that.

120,661 görüntüleme • 6 ay önce

This Mac launch film is 100% code. Opus 5.5 made the notch, the widgets and the wallpapers from one brief. The bit that made the difference was the free apple-design skill. I had it tear apart my first version, list everything that looked cheap, and rebuild it. Full brief is here if you want to try it:

This Mac launch film is 100% code. Opus 5.5 made the notch, the widgets and the wallpapers from one brief. The bit that made the difference was the free apple-design skill. I had it tear apart my first version, list everything that looked cheap, and rebuild it. Full brief is here if you want to try it:

19,944 görüntüleme • 24 gün önce

Gemini turns your best posts into a writing machine. Knowing the right reverse prompts is the edge. That’s why I’m giving away my $500 Gemini voice-cloning prompt system. Next 24hrs. it’s FREE To get it, just: → Like + Repost → Comment “Reverse” → Follow me (so I can DM)

Gemini turns your best posts into a writing machine. Knowing the right reverse prompts is the edge. That’s why I’m giving away my $500 Gemini voice-cloning prompt system. Next 24hrs. it’s FREE To get it, just: → Like + Repost → Comment “Reverse” → Follow me (so I can DM)

137,980 görüntüleme • 8 ay önce

Claude Code just shipped three updates. None of them need installing (they're already on your machine). 1. Sessions can talk to each other ↳ @ a session by name, same as tagging a person 2. /design ↳ editable artboards on a canvas, inside Claude Code 3. Concise output style ↳ /config, output style, concise I ran one real job through all three, four terminals arguing with each other, and filmed the whole thing. My free Claude Code guide, 10 minutes and you'll know 80% of it → Repost ♻️ to help someone in your network.

Claude Code just shipped three updates. None of them need installing (they're already on your machine). 1. Sessions can talk to each other ↳ @ a session by name, same as tagging a person 2. /design ↳ editable artboards on a canvas, inside Claude Code 3. Concise output style ↳ /config, output style, concise I ran one real job through all three, four terminals arguing with each other, and filmed the whole thing. My free Claude Code guide, 10 minutes and you'll know 80% of it → Repost ♻️ to help someone in your network.

23,408 görüntüleme • 1 ay önce

Fable 5 goes paid in 4 days. After that, usage credits only. Five things to do before the window closes. 1. Build a website. It's brilliant at front end design. 2. Build an internal tool instead of Slack or Notion. 3. Get it to review everything you've made in Claude since the ban. 4. Hand it your goals. Ask how to start your first business. 5. Ask how to run a local LLM. Stay unlocked from closed models. Comment FABLE for the guide.

Fable 5 goes paid in 4 days. After that, usage credits only. Five things to do before the window closes. 1. Build a website. It's brilliant at front end design. 2. Build an internal tool instead of Slack or Notion. 3. Get it to review everything you've made in Claude since the ban. 4. Hand it your goals. Ask how to start your first business. 5. Ask how to run a local LLM. Stay unlocked from closed models. Comment FABLE for the guide.

30,646 görüntüleme • 3 ay önce

Instead of watching Netflix, watch this 36-min masterclass on Claude

Instead of watching Netflix, watch this 36-min masterclass on Claude

43,759 görüntüleme • 6 ay önce

Your Claude has a tell, and almost nobody uses it. Make it start every reply with your name. One line in custom instructions, no code. The moment it stops saying your name, its context window is full. That is the exact point the output starts drifting, and you do not notice. Name stops? Start a fresh chat. It has killed about 90% of my “why has Claude gone weird” moments. Miners sent a canary down the pit to catch the gas they could not see. Same trick, for your context. Comment GUIDE and I’ll send you the exact canary setup.

Your Claude has a tell, and almost nobody uses it. Make it start every reply with your name. One line in custom instructions, no code. The moment it stops saying your name, its context window is full. That is the exact point the output starts drifting, and you do not notice. Name stops? Start a fresh chat. It has killed about 90% of my “why has Claude gone weird” moments. Miners sent a canary down the pit to catch the gas they could not see. Same trick, for your context. Comment GUIDE and I’ll send you the exact canary setup.

24,185 görüntüleme • 3 ay önce

Day 2 of 5 building with Claude Fable 5 before it goes paid. Today: an internal tool that replaces another monthly SaaS bill. List your five most repetitive weekly tasks. Claude picks the biggest time drain. It builds the replacement in one file. Host it as an artifact, or deploy it with Claude Code and Vercel. Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 3 tomorrow.

Day 2 of 5 building with Claude Fable 5 before it goes paid. Today: an internal tool that replaces another monthly SaaS bill. List your five most repetitive weekly tasks. Claude picks the biggest time drain. It builds the replacement in one file. Host it as an artifact, or deploy it with Claude Code and Vercel. Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 3 tomorrow.

25,133 görüntüleme • 3 ay önce

🚨Stop gambling on the wrong local LLM. Most people download a model, watch it crawl, then start over. LLM Hardware Scanner is a CLI tool that scans your actual specs and ranks hundreds of LLMs before you waste the bandwidth: ⤷ Reads your RAM, CPU, and GPU to score real compatibility ⤷ Accounts for MoE activation not just bloated total parameter counts ⤷ Auto-selects the optimal quantization for your exact setup ⤷ Ranks models across quality, speed, context length, and true memory fit ⤷ Works natively with Ollama, llama.cpp, and MLX ⤷ Shows a composite score plus a speed estimate before you download a single byte Not a benchmark site. Not a spec sheet. A hardware-aware ranker that tells you the truth about what will actually run on your machine. One scan. Instant ranking. Zero wasted downloads.

🚨Stop gambling on the wrong local LLM. Most people download a model, watch it crawl, then start over. LLM Hardware Scanner is a CLI tool that scans your actual specs and ranks hundreds of LLMs before you waste the bandwidth: ⤷ Reads your RAM, CPU, and GPU to score real compatibility ⤷ Accounts for MoE activation not just bloated total parameter counts ⤷ Auto-selects the optimal quantization for your exact setup ⤷ Ranks models across quality, speed, context length, and true memory fit ⤷ Works natively with Ollama, llama.cpp, and MLX ⤷ Shows a composite score plus a speed estimate before you download a single byte Not a benchmark site. Not a spec sheet. A hardware-aware ranker that tells you the truth about what will actually run on your machine. One scan. Instant ranking. Zero wasted downloads.

37,499 görüntüleme • 7 ay önce

Skip Netflix tonight this Stanford lecture on AI agents is the most useful hour you'll spend this week.

Skip Netflix tonight this Stanford lecture on AI agents is the most useful hour you'll spend this week.

30,157 görüntüleme • 6 ay önce

Day 3 of 5 building with Claude Fable 5 before it goes paid. Today: an audit of everything you have already made. 1. Fable 5 reads back through all your past Claude chats 2. It flags what worked, what you dropped, and where value is going to waste 3. It ranks the top 10 fixes by effort against impact 4. Then it hands you a concrete plan for the top 3 5. Run that plan on a cheaper model and save Fable 5 for the thinking Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 4 tomorrow.

Day 3 of 5 building with Claude Fable 5 before it goes paid. Today: an audit of everything you have already made. 1. Fable 5 reads back through all your past Claude chats 2. It flags what worked, what you dropped, and where value is going to waste 3. It ranks the top 10 fixes by effort against impact 4. Then it hands you a concrete plan for the top 3 5. Run that plan on a cheaper model and save Fable 5 for the thinking Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 4 tomorrow.

13,617 görüntüleme • 3 ay önce

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

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

16,692 görüntüleme • 5 ay önce

This is the shortcut that builds full PowerPoint decks in seconds. No manual slides. No formatting pain. No wasted hours. Instant presentations directly inside PowerPoint. I packaged my step-by-step Claude tutorial into a plug-and-play guide To get it, just: → Comment “PPT” → Follow me so I can DM

This is the shortcut that builds full PowerPoint decks in seconds. No manual slides. No formatting pain. No wasted hours. Instant presentations directly inside PowerPoint. I packaged my step-by-step Claude tutorial into a plug-and-play guide To get it, just: → Comment “PPT” → Follow me so I can DM

18,235 görüntüleme • 8 ay önce

Most people are recreating images in Nano Banana the wrong way. They throw in random prompts. They hope for magic. They get “almost right” results. You can get near 1:1 recreations without guessing. I’m giving away the exact “Image to JSON” prompt I use 🎁 → Like + Repost → Comment “GEM” → Follow me (so I can DM)

Most people are recreating images in Nano Banana the wrong way. They throw in random prompts. They hope for magic. They get “almost right” results. You can get near 1:1 recreations without guessing. I’m giving away the exact “Image to JSON” prompt I use 🎁 → Like + Repost → Comment “GEM” → Follow me (so I can DM)

14,390 görüntüleme • 7 ay önce