Claude prompts I keep reusing
Personal pack. Not authoritative, just what's working for me as of 2026-05.
Re-read mode
"Read this URL as context. Summarise the key claims in 3 bullets. Then ask me one question that exposes the weakest claim in the summary."
Why it works: the summary forces compression; the one question forces critical engagement. The combination prevents the "Claude says yes to everything" failure mode.
Decision mode
"You're an opinionated engineering manager. The context is at
. I'm trying to decide whether to . Recommend an action, then explain the single biggest tradeoff. No hedging."
Why it works: "opinionated EM" anchors the voice. "Single biggest tradeoff" forces ranking. "No hedging" closes the escape hatch.
Audit mode
"List every assumption in this doc that isn't backed by evidence elsewhere in the hub. For each, suggest what evidence would make the assumption checkable."
Why it works: the second clause keeps it from being a list of nitpicks. Each item ends with a concrete way to validate.
Reading list mode
"From
, what's the ideal reading order if I have only 15 minutes? Order them by 'most value gained from reading first'."
Why it works: bundles have reading orders built in (the analyser produces one) but they optimise for "complete understanding," not "best 15-min." Asking for the time-boxed order is different.
Counterpart mode
"You're the smartest person who disagrees with this thesis:
. The context is at . Write the strongest version of their argument."
Why it works: forcing the opposite framing reveals which parts of my thesis are durable and which parts only hold because I haven't seen the counter-argument.
Pre-write mode
"I'm about to write a doc with the working title
. The audience is <person>. The context is at <URL>. Before I write, what are three questions you'd want me to answer in the doc, in priority order?"</p> </blockquote> <p>Why it works: writing-question-driven docs land harder than writing-topic-driven docs. The pre-write prompt produces the questions.</p> <h2>What I'm not using</h2> <ul> <li>"Be concise." Useless — Claude is already calibrated for length to context. Better to say "Answer in <X> sentences" with a specific number.</li> <li>"Be honest." Implies otherwise. The model is mostly honest; ask better questions instead.</li> <li>Roleplay prompts that anchor to a famous person. They make the answer feel persona-shaped instead of evidence-shaped.</li> </ul> </article><meta itemProp="headline" content="Claude prompts I keep reusing"/></main><!--$!--><template data-dgst="BAILOUT_TO_CLIENT_SIDE_RENDERING"></template><!--/$--></div><!--$--><!--/$--><!--$--><!--/$--><!--$--><!--/$--><script src="/_next/static/chunks/webpack-437dde2cb4dc4bb9.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3" id="_R_" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0])</script><script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\nc:I[34431,[],\"\"]\nd:I[85341,[],\"\"]\ne:I[2510,[\"8039\",\"static/chunks/app/error-76a55773dd7b31cf.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\"],\"default\"]\nf:I[90025,[],\"\"]\n10:I[1339,[\"9664\",\"static/chunks/9664-bbf55e28a0306eec.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"2034\",\"static/chunks/2034-d12f9e4ee74547a4.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"6800\",\"static/chunks/6800-ae28f5cc4e09073d.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"3804\",\"static/chunks/3804-7c0505ea4e717f5b.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"4345\",\"static/chunks/app/not-found-8343e3d502a5dae4.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\"],\"default\"]\n11:I[63611,[\"7177\",\"static/chunks/app/layout-bb15159c7bdcaba6.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\"],\"default\"]\n12:I[88054,[\"7177\",\"static/chunks/app/layout-bb15159c7bdcaba6.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\"],\"Analytics\"]\n13:I[23193,[\"7177\",\"static/chunks/app/layout-bb15159c7bdcaba6.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\"],\"SpeedInsights\"]\n14:I[92174,[\"9664\",\"static/chunks/9664-bbf55e28a0306eec.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"8964\",\"static/chunks/app/d/%5Bid%5D/not-found-08e7e233de3c6234.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\"],\"default\"]\n15:I[19664,[\"9664\",\"static/chunks/9664-bbf55e28a0306eec.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"8964\",\"static/chunks/app/d/%5Bid%5D/not-found-08e7e233de3c6234.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\"],\"\"]\n17:I[15104,[],\"OutletBoundary\"]\n19:I[94777,[],\"AsyncMetadataOutlet\"]\n1b:I[15104,[],\"ViewportBoundary\"]\n1d:I[15104,[],\"MetadataBoundary\"]\n1e:\"$Sreact.suspense\"\n:HL[\"/_next/static/media/1755441e3a2fa970-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n:HL[\"/_next/static/media/22a5144ee8d83bca-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n:HL[\"/_next/static/media/558ca1a6aa3cb55e-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n:HL[\"/_next/static/media/ac292125708f83fb-s.p.ttf\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/ttf\"}]\n:HL[\"/_next/static/media/d2c1ffb734f61872-s.p.woff2\",\"font\",{\"crossOrigin\":\"\","])</script><script>self.__next_f.push([1,"\"type\":\"font/woff2\"}]\n:HL[\"/_next/static/css/aaa0e2604c6b392b.css?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"style\"]\n:HL[\"/_next/static/css/21ae165836349ef7.css?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"style\"]\n:HL[\"/_next/static/css/b6ae782678a510ed.css?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"style\"]\n"])</script><script>self.__next_f.push([1,"0:{\"P\":null,\"b\":\"F7tQwh8P1zlwXGBmdHNs5\",\"p\":\"\",\"c\":[\"\",\"d\",\"wzixoDcN\"],\"i\":false,\"f\":[[[\"\",{\"children\":[\"d\",{\"children\":[[\"id\",\"wzixoDcN\",\"d\"],{\"children\":[\"__PAGE__\",{}]}]}]},\"$undefined\",\"$undefined\",true],[\"\",[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/aaa0e2604c6b392b.css?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"link\",\"1\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/21ae165836349ef7.css?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"link\",\"2\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/b6ae782678a510ed.css?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"lang\":\"en\",\"data-theme\":\"dark\",\"suppressHydrationWarning\":true,\"className\":\"__variable_246ccd __variable_e896d9 __variable_8f5acc __variable_fac03f __variable_96c546\",\"style\":{\"background\":\"#09090b\"},\"children\":[[\"$\",\"head\",null,{\"children\":[[\"$\",\"meta\",null,{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"link\",null,{\"rel\":\"icon\",\"href\":\"/icon.svg\",\"type\":\"image/svg+xml\"}],[\"$\",\"link\",null,{\"rel\":\"manifest\",\"href\":\"/manifest.json\"}],[\"$\",\"link\",null,{\"rel\":\"apple-touch-icon\",\"href\":\"/icons/apple-touch-icon.png\"}],[\"$\",\"meta\",null,{\"name\":\"mobile-web-app-capable\",\"content\":\"yes\"}],[\"$\",\"meta\",null,{\"name\":\"apple-mobile-web-app-capable\",\"content\":\"yes\"}],[\"$\",\"meta\",null,{\"name\":\"apple-mobile-web-app-status-bar-style\",\"content\":\"black-translucent\"}],[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"html[data-mw-auth-pending=\\\"1\\\"]{background:#15151a !important}html[data-mw-auth-pending=\\\"1\\\"][data-theme=\\\"light\\\"]{background:#ffffff !important}html[data-mw-auth-pending=\\\"1\\\"] body{background:#15151a !important;overflow:hidden !important;visibility:hidden !important}html[data-mw-auth-pending=\\\"1\\\"][data-theme=\\\"light\\\"] body{background:#ffffff !important}html[data-mw-auth-pending=\\\"1\\\"] body\u003e*:not(#mw-auth-pending-loader){display:none !important}html[data-mw-auth-pending=\\\"1\\\"] #mw-auth-pending-loader{visibility:visible !important;position:fixed;inset:0;z-index:2147483647;display:flex !important;flex-direction:column;align-items:center;justify-content:center;gap:12px;background:#15151a}html[data-mw-auth-pending=\\\"1\\\"][data-theme=\\\"light\\\"] #mw-auth-pending-loader{background:#ffffff}#mw-auth-pending-loader{display:none}\"}}],[\"$\",\"script\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"try{var t=localStorage.getItem('mw-theme');if(t==='light'){document.documentElement.setAttribute('data-theme','light');document.documentElement.style.background='#faf9f7'}var a=localStorage.getItem('mw-accent');if(a\u0026\u0026a!=='lime'){document.documentElement.setAttribute('data-accent',a)}var s=localStorage.getItem('mw-scheme');if(s\u0026\u0026s!=='default'){document.documentElement.setAttribute('data-scheme',s)}if(localStorage.getItem('mw-was-logged-in')==='1'){document.documentElement.setAttribute('data-mw-auth-pending','1');setTimeout(function(){document.documentElement.removeAttribute('data-mw-auth-pending')},3500)}}catch(e){}\"}}],[\"$\",\"script\",null,{\"type\":\"application/ld+json\",\"dangerouslySetInnerHTML\":{\"__html\":\"{\\\"@context\\\":\\\"https://schema.org\\\",\\\"@type\\\":\\\"WebSite\\\",\\\"name\\\":\\\"memory.wiki\\\",\\\"url\\\":\\\"https://memory.wiki\\\",\\\"description\\\":\\\"Stop re-explaining your context to every AI. Put your knowledge in one URL Claude, ChatGPT, Cursor and Codex all read the same way. WYSIWYG editor, AI capture from chat surfaces, cross-platform sync, developer API. No login required.\\\",\\\"publisher\\\":{\\\"@type\\\":\\\"Organization\\\",\\\"name\\\":\\\"Raymind AI\\\",\\\"url\\\":\\\"https://raymind.ai\\\"},\\\"potentialAction\\\":{\\\"@type\\\":\\\"SearchAction\\\",\\\"target\\\":\\\"https://memory.wiki/?q={search_term_string}\\\",\\\"query-input\\\":\\\"required name=search_term_string\\\"}}\"}}],\"$L2\",\"$L3\",\"$L4\",\"$L5\",\"$L6\"]}],\"$L7\"]}]]}],{\"children\":[\"d\",\"$L8\",{\"children\":[[\"id\",\"wzixoDcN\",\"d\"],\"$L9\",{\"children\":[\"__PAGE__\",\"$La\",{},null,false]},null,false]},null,false]},null,false],\"$Lb\",false]],\"m\":\"$undefined\",\"G\":[\"$c\",[]],\"s\":false,\"S\":false}\n"])</script><script>self.__next_f.push([1,"2:[\"$\",\"script\",null,{\"type\":\"application/ld+json\",\"dangerouslySetInnerHTML\":{\"__html\":\"{\\\"@context\\\":\\\"https://schema.org\\\",\\\"@type\\\":\\\"SoftwareApplication\\\",\\\"name\\\":\\\"memory.wiki\\\",\\\"applicationCategory\\\":\\\"Productivity\\\",\\\"operatingSystem\\\":\\\"Web, macOS, VS Code, Chrome\\\",\\\"url\\\":\\\"https://memory.wiki\\\",\\\"offers\\\":{\\\"@type\\\":\\\"Offer\\\",\\\"price\\\":\\\"0\\\",\\\"priceCurrency\\\":\\\"USD\\\"},\\\"description\\\":\\\"Cross-AI knowledge URLs. WYSIWYG editing, AI conversation capture, permanent shareable URLs that every AI reads as markdown.\\\"}\"}}]\n3:[\"$\",\"script\",null,{\"async\":true,\"src\":\"https://www.googletagmanager.com/gtag/js?id=G-V3LTDKKHTS\"}]\n4:[\"$\",\"script\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"window.dataLayer=window.dataLayer||[];function gtag(){dataLayer.push(arguments)}gtag('js',new Date());gtag('config','G-V3LTDKKHTS');\"}}]\n5:[\"$\",\"script\",null,{\"src\":\"https://cdn.jsdelivr.net/npm/mermaid@11.13.0/dist/mermaid.min.js\",\"defer\":true}]\n6:[\"$\",\"script\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"if('serviceWorker' in navigator){window.addEventListener('load',function(){navigator.serviceWorker.register('/sw.js')})}\"}}]\n"])</script><script>self.__next_f.push([1,"7:[\"$\",\"body\",null,{\"className\":\"antialiased\",\"children\":[[\"$\",\"div\",null,{\"id\":\"mw-auth-pending-loader\",\"aria-hidden\":true,\"children\":[[\"$\",\"img\",null,{\"src\":\"/brand/mwblob_morph.svg\",\"alt\":\"\",\"className\":\"mw-logo-darktheme\",\"draggable\":false}],[\"$\",\"img\",null,{\"src\":\"/brand/mwblob_morph_dark.svg\",\"alt\":\"\",\"className\":\"mw-logo-lighttheme\",\"draggable\":false}],[\"$\",\"span\",null,{\"children\":\"Loading\"}]]}],[\"$\",\"$Ld\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$e\",\"errorStyles\":[],\"errorScripts\":[],\"template\":[\"$\",\"$Lf\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"$L10\",null,{}],[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/49e4b1641c7cb276.css?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"link\",\"1\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/c4f88cd8c26aa4f2.css?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"link\",\"2\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/83dd9254974167bc.css?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}],[\"$\",\"$L11\",null,{}],[\"$\",\"$L12\",null,{}],[\"$\",\"$L13\",null,{}]]}]\n"])</script><script>self.__next_f.push([1,"8:[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$Ld\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$Lf\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}]\n"])</script><script>self.__next_f.push([1,"9:[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$Ld\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$Lf\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"div\",null,{\"className\":\"min-h-screen flex flex-col\",\"style\":{\"background\":\"var(--canvas)\",\"color\":\"var(--text-primary)\"},\"children\":[[\"$\",\"$L14\",null,{\"title\":\"Document not found\"}],[\"$\",\"main\",null,{\"className\":\"flex-1 flex items-center justify-center px-6\",\"children\":[\"$\",\"div\",null,{\"className\":\"max-w-md text-center\",\"children\":[[\"$\",\"div\",null,{\"className\":\"font-mono mb-3\",\"style\":{\"color\":\"var(--text-faint)\",\"fontSize\":11,\"letterSpacing\":\"0.06em\",\"textTransform\":\"uppercase\"},\"children\":\"404, document\"}],[\"$\",\"h1\",null,{\"style\":{\"color\":\"var(--text-primary)\",\"fontFamily\":\"var(--font-display)\",\"fontSize\":32,\"fontWeight\":500,\"letterSpacing\":0,\"lineHeight\":1.2,\"margin\":0},\"children\":\"Document not found\"}],[\"$\",\"p\",null,{\"className\":\"mt-3 leading-relaxed\",\"style\":{\"color\":\"var(--text-secondary)\",\"fontSize\":13,\"lineHeight\":1.6},\"children\":\"This document doesn't exist, was moved, or its owner made it private.\"}],[\"$\",\"p\",null,{\"className\":\"mt-2 mb-6 leading-relaxed\",\"style\":{\"color\":\"var(--text-faint)\",\"fontSize\":12,\"lineHeight\":1.55},\"children\":\"memory.wiki documents are permanent. If you saved one earlier and it's gone, the owner likely deleted or restricted it.\"}],[\"$\",\"div\",null,{\"className\":\"flex flex-col items-center gap-3\",\"children\":[[\"$\",\"$L15\",null,{\"href\":\"/\",\"className\":\"inline-flex items-center px-4 py-2 rounded-lg transition-opacity hover:opacity-90\",\"style\":{\"background\":\"var(--text-primary)\",\"color\":\"var(--background)\",\"fontSize\":13,\"fontWeight\":500,\"textDecoration\":\"none\"},\"children\":\"Start something new\"}],[\"$\",\"$L15\",null,{\"href\":\"/about\",\"className\":\"inline-flex items-center transition-colors hover:underline\",\"style\":{\"color\":\"var(--text-muted)\",\"fontSize\":12,\"textDecoration\":\"none\"},\"children\":\"What is memory.wiki?\"}]]}]]}]}]]}],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}]\n"])</script><script>self.__next_f.push([1,"a:[\"$\",\"$1\",\"c\",{\"children\":[\"$L16\",null,[\"$\",\"$L17\",null,{\"children\":[\"$L18\",[\"$\",\"$L19\",null,{\"promise\":\"$@1a\"}]]}]]}]\nb:[\"$\",\"$1\",\"h\",{\"children\":[null,[[\"$\",\"$L1b\",null,{\"children\":\"$L1c\"}],[\"$\",\"meta\",null,{\"name\":\"next-size-adjust\",\"content\":\"\"}]],[\"$\",\"$L1d\",null,{\"children\":[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$1e\",null,{\"fallback\":null,\"children\":\"$L1f\"}]}]}]]}]\n1c:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}]]\n18:null\n"])</script><script>self.__next_f.push([1,"1a:{\"metadata\":[[\"$\",\"title\",\"0\",{\"children\":\"Claude prompts I keep reusing — memory.wiki\"}],[\"$\",\"meta\",\"1\",{\"name\":\"description\",\"content\":\"Claude prompts I keep reusing \u003e Personal pack. Not authoritative, just what's working for me as of 2026-05. Re-read mode \u003e \\\"Read this URL as context. Summarise the key claims in 3 bullets. The\"}],[\"$\",\"link\",\"2\",{\"rel\":\"author\",\"href\":\"https://memory.wiki\"}],[\"$\",\"meta\",\"3\",{\"name\":\"author\",\"content\":\"memory.wiki\"}],[\"$\",\"meta\",\"4\",{\"name\":\"keywords\",\"content\":\"personal knowledge hub,AI memory,AI context,markdown wiki,LLM wiki,knowledge graph,URL,MCP,Claude,ChatGPT,Cursor,Codex,knowledge management\"}],[\"$\",\"meta\",\"5\",{\"name\":\"robots\",\"content\":\"index, follow\"}],[\"$\",\"meta\",\"6\",{\"name\":\"theme-color\",\"content\":\"#09090b\"}],[\"$\",\"link\",\"7\",{\"rel\":\"canonical\",\"href\":\"https://memory.wiki/wzixoDcN\"}],[\"$\",\"link\",\"8\",{\"rel\":\"alternate\",\"type\":\"text/markdown\",\"href\":\"https://memory.wiki/wzixoDcN.md\"}],[\"$\",\"meta\",\"9\",{\"property\":\"og:title\",\"content\":\"Claude prompts I keep reusing — memory.wiki\"}],[\"$\",\"meta\",\"10\",{\"property\":\"og:description\",\"content\":\"Claude prompts I keep reusing \u003e Personal pack. Not authoritative, just what's working for me as of 2026-05. Re-read mode \u003e \\\"Read this URL as context. Summarise the key claims in 3 bullets. The\"}],[\"$\",\"meta\",\"11\",{\"property\":\"og:url\",\"content\":\"https://memory.wiki/wzixoDcN\"}],[\"$\",\"meta\",\"12\",{\"property\":\"og:site_name\",\"content\":\"memory.wiki\"}],[\"$\",\"meta\",\"13\",{\"property\":\"og:image\",\"content\":\"https://memory.wiki/api/og?title=Claude%20prompts%20I%20keep%20reusing\u0026features=GFM\u0026author=mdfy%20Demo\"}],[\"$\",\"meta\",\"14\",{\"property\":\"og:image:width\",\"content\":\"1200\"}],[\"$\",\"meta\",\"15\",{\"property\":\"og:image:height\",\"content\":\"630\"}],[\"$\",\"meta\",\"16\",{\"property\":\"og:type\",\"content\":\"article\"}],[\"$\",\"meta\",\"17\",{\"name\":\"twitter:card\",\"content\":\"summary_large_image\"}],[\"$\",\"meta\",\"18\",{\"name\":\"twitter:title\",\"content\":\"Claude prompts I keep reusing — memory.wiki\"}],[\"$\",\"meta\",\"19\",{\"name\":\"twitter:description\",\"content\":\"Claude prompts I keep reusing \u003e Personal pack. Not authoritative, just what's working for me as of 2026-05. Re-read mode \u003e \\\"Read this URL as context. Summarise the key claims in 3 bullets. The\"}],[\"$\",\"meta\",\"20\",{\"name\":\"twitter:image\",\"content\":\"https://memory.wiki/api/og?title=Claude%20prompts%20I%20keep%20reusing\u0026features=GFM\u0026author=mdfy%20Demo\"}]],\"error\":null,\"digest\":\"$undefined\"}\n"])</script><script>self.__next_f.push([1,"1f:\"$1a:metadata\"\n"])</script><script>self.__next_f.push([1,"20:Tb99,"])</script><script>self.__next_f.push([1,"\u003ch1\u003eClaude prompts I keep reusing\u003c/h1\u003e\n\u003cblockquote\u003e\n\u003cp\u003ePersonal pack. Not authoritative, just what's working for me as of 2026-05.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003ch2\u003eRe-read mode\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e\u0026quot;Read this URL as context. Summarise the key claims in 3 bullets. Then ask me one question that exposes the weakest claim in the summary.\u0026quot;\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003eWhy it works: the summary forces compression; the one question forces critical engagement. The combination prevents the \u0026quot;Claude says yes to everything\u0026quot; failure mode.\u003c/p\u003e\n\u003ch2\u003eDecision mode\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e\u0026quot;You're an opinionated engineering manager. The context is at \u003cURL\u003e. I'm trying to decide whether to \u003cdecision\u003e. Recommend an action, then explain the single biggest tradeoff. No hedging.\u0026quot;\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003eWhy it works: \u0026quot;opinionated EM\u0026quot; anchors the voice. \u0026quot;Single biggest tradeoff\u0026quot; forces ranking. \u0026quot;No hedging\u0026quot; closes the escape hatch.\u003c/p\u003e\n\u003ch2\u003eAudit mode\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e\u0026quot;List every assumption in this doc that isn't backed by evidence elsewhere in the hub. For each, suggest what evidence would make the assumption checkable.\u0026quot;\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003eWhy it works: the second clause keeps it from being a list of nitpicks. Each item ends with a concrete way to validate.\u003c/p\u003e\n\u003ch2\u003eReading list mode\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e\u0026quot;From \u003cbundle URL\u003e, what's the ideal reading order if I have only 15 minutes? Order them by 'most value gained from reading first'.\u0026quot;\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003eWhy it works: bundles have reading orders built in (the analyser produces one) but they optimise for \u0026quot;complete understanding,\u0026quot; not \u0026quot;best 15-min.\u0026quot; Asking for the time-boxed order is different.\u003c/p\u003e\n\u003ch2\u003eCounterpart mode\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e\u0026quot;You're the smartest person who disagrees with this thesis: \u003cthesis\u003e. The context is at \u003cURL\u003e. Write the strongest version of their argument.\u0026quot;\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003eWhy it works: forcing the opposite framing reveals which parts of my thesis are durable and which parts only hold because I haven't seen the counter-argument.\u003c/p\u003e\n\u003ch2\u003ePre-write mode\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e\u0026quot;I'm about to write a doc with the working title \u003ctitle\u003e. The audience is \u003cperson\u003e. The context is at \u003cURL\u003e. Before I write, what are three questions you'd want me to answer in the doc, in priority order?\u0026quot;\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003eWhy it works: writing-question-driven docs land harder than writing-topic-driven docs. The pre-write prompt produces the questions.\u003c/p\u003e\n\u003ch2\u003eWhat I'm not using\u003c/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\u0026quot;Be concise.\u0026quot; Useless — Claude is already calibrated for length to context. Better to say \u0026quot;Answer in \u003cX\u003e sentences\u0026quot; with a specific number.\u003c/li\u003e\n\u003cli\u003e\u0026quot;Be honest.\u0026quot; Implies otherwise. The model is mostly honest; ask better questions instead.\u003c/li\u003e\n\u003cli\u003eRoleplay prompts that anchor to a famous person. They make the answer feel persona-shaped instead of evidence-shaped.\u003c/li\u003e\n\u003c/ul\u003e\n"])</script><script>self.__next_f.push([1,"16:[\"$\",\"div\",null,{\"children\":[[\"$\",\"script\",null,{\"type\":\"application/ld+json\",\"dangerouslySetInnerHTML\":{\"__html\":\"{\\\"@context\\\":\\\"https://schema.org\\\",\\\"@type\\\":\\\"Article\\\",\\\"headline\\\":\\\"Claude prompts I keep reusing\\\",\\\"url\\\":\\\"https://memory.wiki/wzixoDcN\\\",\\\"datePublished\\\":\\\"2026-05-14T18:15:49.480924+00:00\\\",\\\"dateModified\\\":\\\"2026-05-15T03:37:20.915+00:00\\\",\\\"author\\\":{\\\"@type\\\":\\\"Person\\\",\\\"name\\\":\\\"mdfy Demo\\\"},\\\"publisher\\\":{\\\"@type\\\":\\\"Organization\\\",\\\"name\\\":\\\"memory.wiki\\\",\\\"url\\\":\\\"https://memory.wiki\\\"},\\\"mainEntityOfPage\\\":\\\"https://memory.wiki/wzixoDcN\\\"}\"}}],[\"$\",\"main\",null,{\"id\":\"memory-wiki-ssr-body\",\"role\":\"main\",\"itemScope\":true,\"itemType\":\"https://schema.org/Article\",\"children\":[[\"$\",\"article\",null,{\"className\":\"article-body post-content mdcore-rendered max-w-3xl mx-auto px-4 sm:px-6 py-8\",\"itemProp\":\"articleBody\",\"dangerouslySetInnerHTML\":{\"__html\":\"$20\"}}],\"$L21\"]}],\"$L22\"]}]\n"])</script><script>self.__next_f.push([1,"23:I[23570,[\"4109\",\"static/chunks/app/d/%5Bid%5D/page-648e6123b6c962a7.js?dpl=dpl_47xkhJT9Hmc2wq6EJanaMkgjRFM3\"],\"default\"]\n21:[\"$\",\"meta\",null,{\"itemProp\":\"headline\",\"content\":\"Claude prompts I keep reusing\"}]\n24:T9bd,"])</script><script>self.__next_f.push([1,"# Claude prompts I keep reusing\n\n\u003e Personal pack. Not authoritative, just what's working for me as of 2026-05.\n\n## Re-read mode\n\n\u003e \"Read this URL as context. Summarise the key claims in 3 bullets. Then ask me one question that exposes the weakest claim in the summary.\"\n\nWhy it works: the summary forces compression; the one question forces critical engagement. The combination prevents the \"Claude says yes to everything\" failure mode.\n\n## Decision mode\n\n\u003e \"You're an opinionated engineering manager. The context is at \u003cURL\u003e. I'm trying to decide whether to \u003cdecision\u003e. Recommend an action, then explain the single biggest tradeoff. No hedging.\"\n\nWhy it works: \"opinionated EM\" anchors the voice. \"Single biggest tradeoff\" forces ranking. \"No hedging\" closes the escape hatch.\n\n## Audit mode\n\n\u003e \"List every assumption in this doc that isn't backed by evidence elsewhere in the hub. For each, suggest what evidence would make the assumption checkable.\"\n\nWhy it works: the second clause keeps it from being a list of nitpicks. Each item ends with a concrete way to validate.\n\n## Reading list mode\n\n\u003e \"From \u003cbundle URL\u003e, what's the ideal reading order if I have only 15 minutes? Order them by 'most value gained from reading first'.\"\n\nWhy it works: bundles have reading orders built in (the analyser produces one) but they optimise for \"complete understanding,\" not \"best 15-min.\" Asking for the time-boxed order is different.\n\n## Counterpart mode\n\n\u003e \"You're the smartest person who disagrees with this thesis: \u003cthesis\u003e. The context is at \u003cURL\u003e. Write the strongest version of their argument.\"\n\nWhy it works: forcing the opposite framing reveals which parts of my thesis are durable and which parts only hold because I haven't seen the counter-argument.\n\n## Pre-write mode\n\n\u003e \"I'm about to write a doc with the working title \u003ctitle\u003e. The audience is \u003cperson\u003e. The context is at \u003cURL\u003e. Before I write, what are three questions you'd want me to answer in the doc, in priority order?\"\n\nWhy it works: writing-question-driven docs land harder than writing-topic-driven docs. The pre-write prompt produces the questions.\n\n## What I'm not using\n\n- \"Be concise.\" Useless — Claude is already calibrated for length to context. Better to say \"Answer in \u003cX\u003e sentences\" with a specific number.\n- \"Be honest.\" Implies otherwise. The model is mostly honest; ask better questions instead.\n- Roleplay prompts that anchor to a famous person. They make the answer feel persona-shaped instead of evidence-shaped.\n"])</script><script>self.__next_f.push([1,"22:[\"$\",\"$L23\",null,{\"id\":\"wzixoDcN\",\"markdown\":\"$24\",\"title\":\"Claude prompts I keep reusing\",\"isExpired\":false,\"isRestricted\":false,\"showBadge\":true,\"editMode\":\"account\",\"referencedBy\":{\"documents\":[],\"bundles\":[],\"hubs\":[],\"total\":0}}]\n"])</script></body></html>