I rank 23 AI tools from S to F. This will make some of you (very) angry: ✦ 𝗦 𝗧𝗜𝗘𝗥 ✦ Claude Fable-5 - ☑ The smartest AI model. ☑ Included in Max subscription. ☑ It solves what every other model gives up on. ✦ 𝗔 𝗧𝗜𝗘𝗥 ✦ Grok Bot - ☑ The only AI agent I use. ☑ Super simple to use & set up. ☑ For people who are not technical. Wispr Flow - ☑ Write text with your voice. ☑ Insanely fast & accurate. ☑ Keeps on training on your edits. Gamma - ☑ Make slides, with AI. ☑ The best PowerPoint killer. ☑ Unmatched taste in their designs. Granola - ☑ The best AI meeting notetaker. ☑ Made for simplicity & efficiency. ☑ It does NOT connect to the call. Seedance - ☑ The best AI model for videos. ☑ 30 secs in one shot (Veo gives you 8). ☑ Free credits every day. ✦ 𝗕 𝗧𝗜𝗘𝗥 ✦ ChatGPT 5.6 Sol/Luna - ☑ Sol for the hard stuff, Luna for the rest. ☑ The best free chatbot, & it's not close. ☑ Connected to more apps. Kimi – ☑ 2.8 trillion parameters, & open-source. ☑ The best AI for long, autonomous tasks. ☑ Free on the app, cheap on the API. DeepSeek – ☑ The Chinese ChatGPT, for free. ☑ And they just made the API 4x pricier. Cursor – ☑ The AI code editor everyone copied. ☑ SpaceX bought it for $60B. ☑ Free hobby plan, no card needed. ✦ 𝗖 𝗧𝗜𝗘𝗥 ✦ NotebookLM - ☑ A great AI to upload courses and learn. ☑ Create a podcast, quizzes, or mindmaps. ☑ Can take up to 50 sources, even from YouTube. Resend - ☑ Send emails from your app in 5 minutes. ☑ 3,000 emails per month, for free. ☑ You write the emails in code, not HTML. Supabase - ☑ The database behind most vibecoded apps. ☑ Logins, storage, and it's real Postgres. ☑ Free up to 50,000 users. ✦ 𝗗 𝗧𝗜𝗘𝗥 ✦ Claude Opus-5 ☑ Almost Fable-5, at half the price. ☑ You choose the effort level. I keep it on High. ☑ Great at executing tasks, after brainstorming with Fable Gemini veo - ☑ Google's video AI, now called Gemini Omni. ☑ 50 free credits per day inside Flow. ☑ Which is not even one good video. Notion - ☑ Where a lot of people keep everything. ☑ Claude and Cursor now work inside it. ☑ But the AI features are locked in the paid plan. Canva – ☑ Underwhelming AI features. ☑ Well-known non-designer design tool. ✦ 𝗘 𝗧𝗜𝗘𝗥 ✦ GitHub – ☑ Where the code of the world lives. ☑ Free forever BUT extremely buggy. Gemini (app) – ☑ The free model is 3.6-Flash. ☑ Far from the top 20 models. Grammarly – ☑ Grammar fixes, for free. ☑ Very annoying pop-ups to make you pay. ✦ 𝗙 𝗧𝗜𝗘𝗥 ✦ Copilot – the worst LLM at everything. Claude Sonnet 5 – Use ChatGPT for free instead. You want to help your network? ♻️ Repost this image so they can find the best AI. Subscribe to my free newsletter:

My 9 (most-used) Claude Skills to write prompts. Download the whole library for free: 👉 - get all the skills in a zip file. Everything below is what you'll get: 1. /prompt-master - restructures a brain-dump into a clean task spec before Claude runs anything. 2. /grill-me - interrogates until nothing is vague. The prompt fixes itself in the answers. 3. /how-to - for when I don't even know what to ask. Maps the steps first, then we prompt. 4. /5 - rewrites the optimised prompt for Opus 5. Models read differently. 5. /fable - same job, tuned for the new Fable 5. Two models, two ways of prompting. 6. /personal-voice - bakes my writing voice into the prompt. Outputs sound like me on the first try. 7. /anti-ai - remove the em-dashes and the dead giveaway AI words before they ever appear. 8. /write-a-skill - turns any prompt I reuse into a new Skill. The library builds itself. 9. /handoff - compresses the whole chat into the opening prompt of the next one. Nothing gets lost. …and the rest of the library, all done, all free. Stop spending hours perfecting your prompts. It's barely worth it now. Just download the Skills. I turned the optimised prompts into 9 Skills. Getting them takes 2 clicks: Step 1. Go to Step 2. Download the skills. Step 3. Put your email and verify with an OTP. Step 4. Save the downloaded zip file. Step 5. Upload to Claude → Settings → Skills. The best part: the Skills stack. Claude runs /grill-me into /5 into /personal-voice in one chat - you just answer the questions and watch. ♻️ Repost this to save someone from prompting.

Claude doesn't come with a manual. So I wrote a simple guide (like IKEA instructions): Most people open Claude, type a question, get a bad answer & decide it's "just another chatbot." The problem is nobody handed you the instructions. So I wrote one, like flat-pack furniture. Here's the whole thing: 1. Get the entire manual (for free) Go to Subscribe for free. Open the received email in your inbox. Go to the link, download "Ikea Claude manual" Keep it open in a second tab while you follow along. 2. The one sentence to end every prompt with - it makes you better at Claude than 99% of people 3. Goals vs. tasks: why "write me an email" gets a worse result than telling Claude what you want 4. The Claude rule that stops your chats getting slow, dumb, and expensive 5. How to give Claude a memory, so every chat already knows who you are 6. The expensive model nobody warns you about and when to use it 7. Connecting your Gmail and calendar, and the skills you build once and never rebuild No coding. No folders. No jargon. If you can build a bookshelf, you can do this. Keep it open in a second tab while you follow along: → I removed every word that wasn't necessary and drew the rest. If your team is still typing one-line questions into a Ferrari, send them this. (If you share it, mention the newsletter. Be nice.)

Everyone teaching Claude "tips" is a year behind. Folders? Dead. MD file? Dead. Global instructions? Empty. Here's what (actually) works in 2026: Everything on the image + 146 more Claude tips: (go to the link first, then read this) ✦ The Claude model changed. Start with Fable 5, let it figure out the problem, then switch to Opus-5. ✦ Delete any settings you have on by default. I heavily use Claude skills (when necessary). More context = Less creativity. ✦ Do yourself a favour and delete the folders. They leak. Skills & Projects are enough for any kind of tasks. If you could teach it to a person, make it a skill. If it's a client, make it a Project. ✦ Do not continue with old prompting habits. "Think step by step," giving loads of examples hurts more than they help. And never end a prompt with "right?" because Claude will just agree with you. The list is bigger but makes it simpler for you to master Claude: ✦ Start a fresh chat every 30 to 50 follow-up prompts. Otherwise, Claude will be unbearably annoying to follow any new instructions. ✦ 'Edit' already sent prompt instead of correcting a mistake by sending another follow-up prompt. To get the entire list of 160 Claude tips, go to: It's literally the entire knowledge I have of using Claude.

Don't upgrade to the $100 Claude plan if you keep hitting token limits. Instead, use these 21 hacks to make the $20/month subscription enough: Hack 1. Do not upload PDFs in Claude. It costs a huge amount of tokens. Paste the text into a Google Doc & download it as .md. it is not the same. Hack 2. Figure out the solution in Chat on Fable 5 High & then move to Opus 5 on High effort to execute the task. Hack 3. Start any new Claude chat with this prompt: “I need [task] for [goal]. I will know it worked when [target]. Ask me questions first, using the AskUserQuestion tool.” Hack 4. When one specific thing is wrong, fix that section, not the entire thing. Prompt: "Only redo section 3. Keep everything else. Just the output." Hack 5. Give the entire task at one go, not one problem after another in different prompts. Like: "Summarize this, list the points, suggest a headline" Hack 6. Stop sending follow-up prompts like "no, I meant...". Click 'Edit' on your original message to fix a specific problem. Hack 7. Turn your repeated prompts into Claude Skills. It saves you time & tokens. Hack 8. Use Sonnet only for grammar checks. I'd use ChatGPT, not even Sonnet. Use Fable for complex tasks. Use Opus to execute the tasks. Hack 9. Do not create .md files as a part of workflow. It's too much work for less outcome. Instead turn them into Claude Skills. Hack 10. When Claude starts to hallucinate, click "edit" on an earlier message. Hack 11. Once you send 15-20 prompts in a chat. Do not continue with that chat; instead, ask for a summary. Copy the brief. Open a fresh chat. Hack 12. Put files in a Project. Now every chat inside that project has the same context overall. Hack 13. Upload only the files a single task needs. Do not unnecessarily give context; it makes it less creative. Hack 14. One chat for one problem. It doesn't need more explanation. Hack 15. Turn off search & connectors. Switch them on if you need them for a task. Hack 16. Use Claude Schedule for mundane tasks over weeks. Type /schedule: "Every Monday at 7 am, create my weekly briefing." Hack 17. This is for people who use Claude Code. Point Claude Code at the file, not the whole repo. "Build a bar chart from this CSV. Save as chart.png." Hack 18. Go to Claude settings > Personal Preferences. Set your tone. Hack 19. "Make it better" doesn't mean anything in Claude's language. Give more context. I speak my prompts with wispr .ai to give the full context at one go. Hack 20. Claude uses a rolling 5-hour window. So I usually send something right when I arrive at the office and then early + late afternoon. So about 3 sessions. Hack 21. Claude is not an all-rounder model. It can't generate good images. Use ChatGPT for image generation. I have been using these hacks, not only to save tokens but also to get more creativity out of Claude. I'm a psycho when it comes to using Claude (better). And I squeezed every personal tip into this one PDF. Get it here:

You follow prompting tips from 2023. That's why you're WORST at prompting (without knowing). So here are 21 rules you should use while prompting Claude: ✦ More here: ✦ Taken from: Prompt Tip 1. Never end questions with "right?" ☑ Not even with "maybe?" It's worse. ☑ Do not ask yes/no questions. ☑ "Compare X vs Y for this [context]" is far better. ☑ Otherwise, AI is very good at following the signals ☑ It won't argue against, to please you. Prompt Tip 2. "Think step by step" doesn't work. ☑ No "Think step-by-step." ☑ No "get information, and then work on a plan." ☑ Instead, add a role in just a few words ("…as a reliability engineer"). Prompt Tip 3. Never trust AI's cited sources. ☑ AI is very good at sounding confident. ☑ Open every single link. ☑ Mentioned links may not exist. Prompt Tip 4. Only give 3 rules in a prompt. ☑ If you have more rules, give them in the follow-up prompts. ☑ 2nd follow-up prompt: "Check your draft against these ONE AT A TIME, then revise." ☑ It doesn't read beyond 3 rules. Prompt Tip 5. Do not give examples anymore. ☑ NO "Example 1: [solved case]." ☑ Give a goal instead. ☑ Paste any necessary real numbers & context. ☑ Mention what you ruled out ("I didn't change format, send time, or subject"). ☑ End the prompt with: "Ask me for the data you need before you answer." Prompt Tip 6. No prompting rule is ever green. ☑ Test hacks that were tested on 2023 models. ☑ When you have any new model, re-test your favorite tricks before trusting them. Save the new rules & delete the 2023 ones.

Most advice on LinkedIn is making you worse at Claude. These are the 7 things I'd tell anyone starting with Claude: 1. Always start a chat with Fable-5, on High. After 2 prompts, switch to the Opus-5 model mid-chat. Find the solution to problems with Fable-5 but let Opus-5 do the job. 2. Never give Claude a long list of rules to stick to. Keep it to a maximum of 3 rules. Let it think, instead of thinking of following the rules. 3. Open a chat with this prompt: "I need [task] for [goal]. I'll know it worked when [target]. Ask me questions first, using the AskUserQuestion tool." Answer the form by giving more context in the "Something else" box, in your own words. 4. Always remember: New task, new chat. Otherwise Claude re-reads the entire chat with every prompt you send and starts hallucinating after 40 prompts. 5. Turn on Research mode for deep and complex questions. It reads 40 sources so you don't. But do not blindly trust the links. Always open the source link to double-check. 6. If you want to create an image, use ChatGPT. Or ask Claude for an HTML image, so doesn't mess up the accuracy of the text. 7. Click the citations links any AI model gives you. Claude thinks of an answer first, then finds a source that agrees (sometimes the citation is written by AI itself). If you do one thing from this, do # 3. Download my entire Claude Tips guide at This is as simple as it can get. Stop unnecessarily wasting 6 months figuring out which ones matter.

My mom asked me, "What the hell is Claude?" This image did the job, not me: Then she called. 6 more questions in 20 minutes. Her questions will teach you, better than I ever did: → "What do I type in the prompt box?" Copy this template and fill it with your context: "I want to [TASK] for [RESULT]. AskUserQuestion." Claude asks 3-5 questions. You tap the answers. Prompting, solved. She never asked about it again. → "You expect me to type all that?" No. Talk to your Claude. Download Wispr .ai (free). You speak 4x faster than you type. (She speaks 400x. Sorry mom.) → "Where did my file go?" Go to Claude desktop app. Locate "cowork." Open "Projects" and upload all the files there. She dropped in a messy PDF. She got an Excel. Saved on her computer. Found it herself. → "What the hell is a Claude skill?" Fair question. A long prompt turned into a Claude command that runs on its own, every single time. Building your own takes weeks. So I handed mine. Download my entire Skill library: Open the email received in your inbox. Go to the given link and download the skills. Claude Customize → Skills → Upload. 2 minutes. Her Claude now works like mine. Yours can too. → "It's reading my emails??" Only if you let it. Gmail, calendar, meeting notes. Her first test: "prep me for tomorrow's meeting" She called back just to say "witchcraft." → "Why did nobody tell me this?" Because 98.75% of people have never tried Claude. Everyone's waiting to feel ready. She skipped the waiting. So can you. Save this for your own mom. Or dad, boss, friend. The one who keeps saying "I'm so behind." 10 minutes. 1 image. That's the whole entry fee. Get all 27 Claude Skills, free:

I asked ChatGPT, Gemini & Claude the same question. All 3 gave me the exact same answer: "Which LLM is the best if I'm on a free plan?" ChatGPT ranked at the top. Every time. Even Claude and Gemini put themselves in 2nd and 3rd. I tested this answer personally by creating a new (free) account on all of these AI tools. I spend $1,000+/month on AI. But I tested the free tier of almost all the AI tool models to answer one question: what would I use with $0? Here's my free AI Tool stack: 1. ChatGPT (99% of your needs) Claude's free model is Sonnet 5. Gemini's is 3.6-Flash. Both are far from the top of the Intelligence Index. ChatGPT gives you a frontier model for $0. But only if you set it up right: → Download the app. Every LLM is better on its app. → Go to "ChatGPT Work" → pick 5.6-Terra-High → If you run out of Terra, switch to Luna-High (free). → Click Plugins → Spreadsheets (or Gamma). Free. 2. The rest of the stack: → Gamma for slides (400 starter credits) → Wispr Flow for dictation (2,000 words/week) → Seedance via Dreamina for video (225 credits/day) → NotebookLM for research on your own sources → Cursor for coding (free hobby plan, no card) → ElevenLabs for text-to-speech → Granola for meeting notes → Canva for design 3. The free vibecoding combo: → GitHub stores your code → Vercel puts your site online → Supabase handles logins → Resend sends 3,000 emails/month Then start every build with this prompt: "You are already connected to my GitHub, Vercel, Supabase & Resend. I want to build [project] for [goal + success criteria]. Make sure that [rules, max 3]. Ask me clarifying questions first." To read the full breakdown (with my exact prompts, screenshots, and what I actually pay $1,000/month for), go here:

Fable 5. Opus 5. Sonnet 5. Haiku 4.5. How to pick the right Claude model (every time): Step 1: Does your task require a complex answer? ☑️ No: use Haiku 4.5 or Sonnet 5. ☑️ Yes: use Opus 5 or Fable 5. Step 2: If your task is quick: → Need maximum speed & minimal tokens? ☑️ Yes: Haiku 4.5 (lightweight, token-saver). Chat without files. Turn on web search. Plan in Chat, build in Cowork. Prompt example: "I want [desired result] with [constraints]. Ask me questions using AskUserQuestion before you start." ☑️ No: Sonnet 5 (fast, everyday model). Perfect for simple tasks. Connect your apps with Connectors: Slack, Google Drive, Notion, Figma, Granola, Gamma + 50 more. Prompt example: "You are a [role]. [Task] this [input]. Keep it under [length]. Tone: [casual/formal]. No preamble - just the output." Step 3: Is this your hardest, most ambitious work? (multi-step reasoning, agents, long-thinking tasks) ☑️ No: Opus 5 (deep-work model). Use Cowork. Put Effort on High. Always. Use Skills in Projects (like /linkedin or /excel-style). Prompt example: "/[skill] topic: [topic]. DO NOT start yet. Ask me clarifying questions (use AskUserQuestion) so we can refine the approach step by step." After Cowork: → Download your file. → Or convert it into a Claude Skill. → Start a fresh session to save tokens. ☑️ Yes: Fable 5 (the smartest model by Claude). Deep research. Analytical decisions. Prompt example: "Here is my goal: [goal]. Here are my constraints: [constraints]. Think through the tradeoffs before answering, propose 2–3 approaches, and recommend one with your reasoning." Too long to write yourself? I built a skill for that: /fable-prompter. Type a messy prompt → get a Fable-worthy prompt. It's free in my Skill library, with +26 Claude Skills. 1. Sign up with your best email at 2. Find the welcome email in your inbox named "Don't lose access to your AI library." 3. Click on the library link. 4. Open the "Claude Skills" folder. Download it all. 5. Upload to Claude → Settings → Skills. ⚠️ But careful with Fable 5: ☑ It costs a lot of tokens (very fast). ☑ Only ~10% of tasks actually need it. ☑ Use it 1-2 turns for strategy, then switch to Opus. ☑ Long conversations = expensive. Claude re-reads the whole thread every turn. When Opus gets stuck, escalate to Fable. Everything else, route down the tree. ♻️ Repost this, so your team stops burning tokens.

I made a 16-page PDF to get you Claude-certified. The certificates are official by Anthropic & free... And the playbook is free too, at Here's what's inside: The Claude Certification Playbook. → 3 official certificates & the order to take them in. → Step from creating an account to downloading. → The fake detector (yes, people sell fake ones). → The LinkedIn format to showcase the certificates. → The copy-paste announcement post on LinkedIn. → What you can honestly say about it in interviews. The certificates take 6 hours. Getting the playbook takes 2 minutes: 1. Go to Subscribe for free. 2. Open the welcome email in your inbox. 3. Tap the Notion library link inside. 4. Download "The Claude Certification Playbook." 5. Start with page 4 (the fake detector). Know someone job hunting? Send them this post. It's the favor.

Before you open Netflix tonight: • Create a Claude account • Do not open a random YouTube tutorial • Go through these guides one-by-one You can learn Claude (entirely) over a weekend. Here are the 15 guides to get you started: 1. Claude for Dummies ( 2. Prompt Engineering 101 ( 3. 27 Claude Tips ( 4. How to set up Cowork ( 5. Create infographics with AI ( 6. How to not write like Claude ( 7. How to prompt Fable 5 ( 8. Claude for Linkedin ( 9. Use Claude Design ( 10. Claude for Excel ( 11. Detect AI-slop ( 12. Claude for your team ( 13. Connectors in Claude ( 14. Vibecode with Claude Code ( 15. Stop hitting Claude limits ( -- 1. Save this list for later (three dots, top right). 2. Share it with a friend by ♻️ reposting this image. 3. Subscribe to my free newsletter:

You're constantly drowning in (overtechnical) posts about Claude, many of what is written by Claude itself. So, I've made a simpler one-pager that you MUST know (without getting technical): First, the words. People use them like you're supposed to already know them. → A Project is a folder with your uploaded files, rules & categorised chats for one job. → A Style is a copy of how you write. → An Artifact is a doc that opens on the right of your screen. You can edit it there. → A Skill is a long prompt you wrote down once so you never have to explain it again. → A Connector is your tools, in Claude (your Gmail, Drive, Slack), so it reads them & gets your context. → Claude Cowork works on your files stored on your desktop while you go do something else. → A token is (literally) a word. That's all. It wasn't that scary, right? Now the part that you have to do, to set up Claude: 1. Open a Project & name it after the repetitive task. Like, "Client emails." Then upload files related to this task. Now, Claude reads everything in the folder before it answers you. 2. Write your about-me file & turn it into a Skill. It must have your job, whom you sell to, what you sell, how you talk, what you never say. Then turn it into a Claude Skill by uploading it in a chat with this prompt: "Turn this uploaded .md file into a Claude skill with the name of "about me." To write your own about me skill, download the interview prompts at 3. Put your rules in the Project instructions. Copy this, but change the names: "You help me write [what]. My readers are [who]. Use short sentences. Never use the words [x] or [y]. If you need more information, ask me one question at a time. When I paste a draft, tell me what to cut before you rewrite anything." But I don't use these Claude functions anymore: ✦ I don't have Memory turned on. It poisons the future chats and restricts Claude to being in a box. ✦ I only connect to 3 connectors. Gamma, Granola, Gmail. Never paste logins, keys, or client contracts. I wrote 27 such Claude tips after realising Anthropic was going to publish them for us. The guide is free to download:

How to prompt Claude Fable-5 (and any AI model): → Start by deleting the long examples you give. → Delete the "step-by-step" prompt technique. → Avoid biased questions. Don't finish with "right?" → Chain-of-Thought (step-by-step) only works well with maths problems. It's worth skipping it. → Don't give a long list of rules (max 3) to follow. The models got very good at simple prompts, and worse at your complicated, over-structured ones. To make a simple prompt, better: → Make your next prompt shorter. → Define the goals with extreme clarity. → Give no more than 3 rules to perform one task. → Ask open-ended questions to let it figure it out. → Always encourage it to ask clarifying questions. → Don't trust the sources blindly. It tries to prove itself by finding links that agree with what it already has written. This is the one simple prompt template I stick to: "[GOAL: What a finished answer must achieve. Write the test it has to pass.] [CONTEXT: The facts the AI would otherwise invent. Only the ones it cannot know.] [CONSTRAINTS: The hard limits. 3 max.] If anything here is missing or unclear, ask me before you answer. [Add “use AskUserQuestion tool” if you’re on Claude]." I've been teaching prompt engineering since 2022, and so much has changed since then. What was true - because science said so - isn't anymore. The models are 10x more capable now. I'm a psycho so I actually filter out and read the 100+ daily papers on prompt engineering (on arxiv. org). Read my findings at

I spent 1,800 hours figuring out Claude the hard way. Here's the only guide I wish someone had sent me earlier to read: → (it's a free guide) ChatGPT got 34.7 billion visits last year. Claude only got 3.7 billion. And you were not one of them because: 1. You don't know where to start. I made an entire PDF that compiles all of my free Claude tips at 2. You don't know why it matters. Claude is just better across the board (still). Claude Code is the best for coding. Claude Design is the best at design. Claude Cowork is the best for non-devs. You miss out every day from not playing with it. 3. You think Claude is soooo different. It's just ChatGPT with extra flavors. Actually, Claude is so good that now ChatGPT kinda copied Claude to try to catch up. Learning Claude from random YouTube videos will waste 6+ hours. Getting the guide takes 2 minutes: 1. Go to Put your email. 2. Open the email in your inbox. 3. Download "The 27 Claude Tips." No, i am not being paid by Anthropic to make you use Claude, better.

I repeat myself almost 17 times a day to my AI tools. It's so annoying until I started using this one AI tool as my Google Doc: So instead, I started using Granola .ai to open it in the background in almost every meeting I get into. > It works on Zoom, Meet & Teams (i use Meet). > It doesn't join in any of my meetings. > I hate bots in the meetings. Please don't do it. > I focus on the meeting rather than remembering context. Here's how I stopped taking notes at all: 1. Download Granola (granola .ai). 2. It's a notepad, like Apple Notes. 3. Open it in every meeting (non-negotiable). 4. It captures all the transcripts with timestamps. 5. Go to Claude Settings > Connectors > Granola 6. Now, everything you draft with Claude, it already has the context from the meetings you had. 7. Copy the following prompt (you do this ONCE): "Read my last 30 sent emails in Gmail. Write my voice profile: how I greet, how I sign off, my sentence length, my go-to phrases, the words I never use. Format it as writing instructions to follow when drafting as me." 8. To go even beyond a surface-level workflow, save the output as project instructions. 9. This is why your emails will sound like you. 10. After your next meeting, paste this in Claude: "Pull my last meeting from Granola. Draft the follow-up using my voice profile: what we decided, action items with owners, one clear next step. Keep it as short as I keep mine. Create it as a Gmail draft to the attendees." 11. Open Gmail draft. Attendees in the To field. 12. Ask Claude: "Which action items from this week's meetings are still waiting on me?" This simple workflow saves headaches because it remembers every meeting I've had. My recaps just became a mere to-do list. I am not lazy. I just hate to do small stuff that i can ask AI to help me do.

You will NOT make it to the end of this post. 3 steps, but only 0.1% of people actually try this (stupid) simple guide of Claude Code to build small tools: DO NOT continue reading if you expect: ✗ a simple doc → Claude Cowork ✗ just an image → ChatGPT on High ✗ a widget to open once → Claude Artifact ✗ a small interactive interface → Claude Chat ✗ to get rich quickly → You'll not. I can't help you Those of you who're still reading, start here: Step 1. Download the desktop app. → At claude .com/download → Pay for Pro subscription ($20/month) → Go to the Claude app & select the Code tab → Make an empty folder on the desktop. → Then go to Claude Settings > Claude Code → Turn on bypass permissions → Again, Go to Claude Settings > Connectors → Add Netlify + Supabase connectors. They're free. Step 2. Copy and paste this prompt "You're my CTO. I'm the CEO. I don't read code. Plain English only. I want [end goal]. Interview me first. One question at a time, using AskUserQuestion. Then show me the plan. Then build. Push it live with Netlify. Match the screenshot I shared." Step 3. Give Claude code, your taste. → Go to getdesign .md. It's free. → Pick Stripe. Or Notion. → Download the file. Drop it in the created folder. → Say: "Use this for all the styling." WHAT NOT TO DO: → Do not pay for the max subscription. The $20/month is enough to start. → Don't give 3-4 tasks in one chat. Start a new chat for every task. A long chat re-sends everything and eats your tokens faster. → Don't paste big text for token limit reasons. Point at your downloaded files. → Type /usage to see how many tokens you have already spent and how many are left. → Work in "plan" mode and then switch to "Auto" mode when it's time to build it. BEST OF CLAUDE-CODE PROMPTS. PROMPT 1. Build a landing page for [...]. A landing page for my [coaching business] that sells [my group program]. Big headline, a short pitch, [3] offers with prices, testimonials & a [booking] button. Make it feel [calm and premium], with lots of whitespace. PROMPT 2. Build a mockup to show my [developer or designer]. A clickable mockup of [the feature I keep failing to explain]: [a dashboard where my team sees who's doing what]. It doesn't have to work. I just need to show my [developer] the screens. PROMPT 3. Build a tool that does [a boring job] for me. A tool that takes [my export of orders] & [turns it into a clean monthly report with totals by product]. I drop the file in, it hands me the report back. PROMPT 4. Build an app where [people] log in. A simple app where [my students] sign in with Google & see [their own progress and next lesson]. Each person only sees their own stuff. Start with [one screen], we can add more. PROMPT 5. Build a dashboard for [...]. A dashboard that reads [the spreadsheet in this folder] & shows [my revenue, new clients, and refunds] as simple charts. Refresh it whenever I drop in a new file. To read the entire guide (for free), go to:

Delete every prompt template you ever saved. You only need these 3 Claude Skills: 1. /how-to SKILL ☑ Your universal guide. A → Z on any task. Type "/how-to" + what you want. Claude asks the right questions to builds the plan. ↳ Replaces every "how do I do this?" prompt. 2. /about-me ☑ Who you are. How you think. How you write: Open Claude. Run a 100-question interview. Or turn your old about-me .md into a Skill. ↳ Now Claude sounds exactly like you. 3. /skill-creator ☑ The Skill that builds your other Skills. Type /skill-creator. Answer the questions. Save. Or say "make it a skill" in any long chat. ↳ This is how you replace the next 500 prompts. 5. Dictate, don't type ☑ Use Wispr . ai (free). Voice is faster: You answer 100 questions in 90 minutes. Voice is also more honest than typing. ↳ Vagueness won't survive Claude's follow-ups. 5. Skills + Projects. Nothing else. ☑ Forget folders, files & global instructions: Skill = a capability you can teach someone. Project = a specific context (a client, a campaign). ↳ Turn everything OFF. No settings is the best one. I teach you how Claude works at Download my Skills library for free: Step 1: Subscribe for free at Step 2: Open your welcome email. Step 3: Trace the link. Open the 'Skills' folder. Step 4: Access my entire Skills library. Step 5: Claude settings → Capabilities → Skills.