CloudYetiFREE

Free AI resources

Commands, prompts and setups from the videos, written down and ready to copy.

AI privacy checklistWhat AI chat apps remember about you, and how to control it. A new tip is added each time a privacy video goes out. Prompt lines to copyThe lines from the videos, ready to paste into any AI chat. A new line is added with each new video. Claude Code tips from the team that builds Claude CodeThe habits and commands from the videos, each with the text to copy. A new tip is added with each new video. 7 learning swaps for AI engineers who use coding agentsKeep learning to code and debug. Then move your study time from syntax drills and tutorial copying to the skills that decide whether a coding agent's work is right. Make the AI argue against a purchase before you buyAsk "is this a good buy?" and the AI tends to say yes. Ask it to argue against the purchase first, then for it, then pick one. Tell the AI to ask before it sends anythingWhen an AI assistant is connected to your email, let it draft the replies, but make it ask you before it sends anything to another person. Ask for the exact quotes first, then the answerWhen you paste a long document into an AI chat, ask it to quote the exact lines first and answer only from those quotes. The answer comes from your document, and you can check it. Ask what it changed, in two linesWhen the AI tidies up your plan or draft, ask it to end with two lines on what it changed or removed. A clean new version does not show you what went missing. If you want more than the basics, ask for itA one-line ask gets a minimal answer. If you want extras, like a timeline, a shopping list or a backup plan, name them in the ask. Ask the AI to check its own answer against a ruleBefore the AI finishes, tell it what a right answer must satisfy and ask it to check its answer against that rule. Anthropic's prompting guide says this catches errors reliably, especially for math. Ask the AI to check two sources and say where each answer came fromAn AI can answer a fact question from memory and sound sure. Ask it to check two sources, name each one and give its date, so you can see where the answer came from. Claude Code now reads AGENTS.md: keep one instruction file for every agentSince version 2.1.277, Claude Code reads AGENTS.md when a project has no CLAUDE.md. If you also use Codex or another agent, one AGENTS.md file can hold the rules for all of them. Put /goal inside /loop, and Claude Code works through your task fileOne command makes Claude Code wake up on a timer, read tasks.md, and keep working until each pending task is done. You add tasks to the file instead of typing prompts. An old Claude Code chat can eat a big part of your limit with one messageThe prompt cache lasts one hour. After that, your next message sends the whole chat again at full price. Two commands tell you when to start fresh. When Claude goes sideways, the Claude Code team stops and re-plansWhen a Claude Code task starts going wrong, switch back to plan mode and fix the plan instead of pushing more prompts. Then have a second Claude review the plan. The Claude Code team keeps context usage on screen, all the timeOne /statusline command puts a bar at the bottom of Claude Code that shows how full the context window is. A second one adds your 5-hour and weekly plan limits. The two words the Claude Code team adds to big requestsEnd a big Claude Code request with "use subagents". Claude splits the work into helpers that each run in their own context window, so your main chat stays clean. The line the Claude Code team types after every correctionWhen Claude Code gets something wrong and you fix it, one line makes Claude write a rule so the same mistake does not come back. Put a big plan in one project, so every new chat starts with the factsTired of pasting the same paragraph into every new chat? Put the facts in a project's instructions once, and every chat in that project starts with them. Crop the photo to the part you are asking aboutA photo of a whole sign, board or menu makes the AI hunt for your line in small print. Crop to the part you are asking about, keep the column names, and the answer gets easier to check. Deleting a chat does not delete what the AI remembered from itClaude keeps memory as separate topics. Delete the chat and the topic can stay, so delete the topic itself. Give the AI a role in one sentenceAsk a plain question and you get advice that fits anyone. Start with one sentence that says who the AI is, and the answer goes to your exact case. This 10-word prompt keeps finding bugs in people's appsSteve Ruiz posted a one-line prompt on X: find all of the implicit state machines in my app. People who ran it on their own code found real bugs. Here is the prompt, a longer version that gives you a ranked report, and what to do with the results. When a long chat forgets your rules, ask for a handoff briefIn a long chat, an AI can start ignoring a rule you gave in the first message. The rule is fine; the chat is too long. Anthropic's docs say that as the token count grows, accuracy and recall degrade, and they call it context rot. Ask the AI for a short brief of your rules and decisions, then paste it into a new chat. Use an incognito chat when you don't want the AI to rememberPlanning a surprise on a shared AI account? Start an incognito chat, so the plan stays out of history and memory. Fix my grammar, keep my wordsAsk an AI to fix the grammar and it may rewrite your voice too. Say exactly what to change, and ask for a list of every change. Keep an AI bug fix small: change only what the bug needsAsk an AI coding tool to fix one bug and it may also rename functions, add files and tidy code around it. Two lines keep the fix small and still show you what else it noticed. Label each part when you paste two messages into the AIWhen you paste someone else's message and your own notes into one chat, give each part a label and put the task on its own line, so the AI does not mix them up. Give the AI the last four digits, not your whole statementWhatever you paste into an AI chat can end up in the draft it writes. For a complaint or a refund email, paste only the charges and the last four digits of the card. Flip the roles: let Claude interview you before it writes anythingWhen you don't know exactly what you want yet, ask Claude to ask you questions first. The draft then starts from your answers, not a guess. Tell the AI who is readingWhen the AI writes for nobody, "simpler" and "shorter" do not fix it. One line that names the reader does. When you give the AI more than one job, number the stepsWrite each ask as its own numbered line, so the AI works down the list and you can check every number against the answer. For a big piece of work, ask the AI for the outline firstAsk for the outline, read it, fix it, and only then let the AI write each part, so one wrong line at the top does not spread through the whole result. Ask by the page number your PDF viewer showsWhen you ask an AI about one page of a PDF, use the page number in your PDF viewer, not the number printed on the page. Covers and contents pages often have no printed number, so the two can differ. Paste the long document first and ask your question lastWhen you paste a long document into an AI chat, put the document at the top and your question at the very bottom, then check the page the answer quotes. Run Qwen 3.8 Flash Next on your own Mac, with a lean coding agentOn my 128 GB M3 Max, Qwen 3.8 Flash Next built a working app from one prompt in about 13 minutes. The biggest speedup was the agent setup, not the model. The AI explained a loop that does not exist. One line stops thatAn AI coding assistant can describe code in a file it never opened, and the guess sounds as sure as a real answer. Anthropic's prompting docs give a line that makes it read the files first. Read your message like a stranger before you send itThe AI only knows what is in your message. Read it as someone with no context would, and add the facts they would ask for. Say "edit", not "suggest"If you want the AI to change your text, ask it to edit and make the changes. "Can you suggest some changes?" can get you a list of ideas instead of a fixed draft. Say it plainly, not in capital lettersWriting IMPORTANT or NEVER in capital letters can push the AI too far. Ask the normal way and say what you want. Give the AI numbers and a list, not "easy"Words like easy, quick or cheap are a guess for the AI. Say the time, the budget and the list of what you have, and the answer fits your real limits. Claude follows a rule better when you say whyA rule in capital letters with no reason is the weak version. Add the reason after "so" or "because", and Claude can handle the cases you did not list. Show the AI what you want instead of describing itWords like nice, modern and premium give an AI almost nothing to go on, so it guesses the average. Paste a screenshot, a link or a few examples you like, and say "like this, but for my product." Anthropic's prompting guide calls examples one of the most reliable ways to steer the output's format, tone and structure. Make the AI show which parts of its answer are guessesAn AI sounds just as sure when it is guessing. Ask it to tag each claim by where it came from, then list the claims you should check. Anthropic's guide on reducing hallucinations recommends letting the model say it does not know and checking each claim against a source. Write your rules once in the settings, not in every chatIf you type the same rules at the start of every new chat, put them in Claude's Instructions setting once. They apply to all your chats.
Get new videos and tips by emailOne short email when there is something new. Unsubscribe any time.