[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-573256-105":3,"detail-sidebar-cat-1-en-105":80,"doc-detail-573256-en":126},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":73,"head_meta":75,"extra_data":77,"updated_unix":79},105,"en","gpt-cheat-sheet-quick-reference-for-prompts-and-workflows","GPT Cheat Sheet - Quick Reference for Prompts and Workflows","","A prompt and workflow reference covering common ways to work with large language models. It compares model capabilities such as reasoning, internet search augmentation, context window size, image understanding and document upload. It also lists practical techniques and scenarios including structured prompt writing, tone and translation tasks, data extraction, summarization and data-based chat (RAG), plus guidance for document-based Q&A and visualization outputs. The sheet emphasizes managing context, using step-by-step thinking, and iterative content expansion.",{"@graph":14,"@context":72},[15,34,55],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/template/","Template",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/template/presentations/","Presentations",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/template/gpt-cheat-sheet-quick-reference-for-prompts-and-workflows/573256/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/gpt-cheat-sheet-quick-reference-for-prompts-and-workflows/573256.png","ImageObject",442,249,{"name":42,"@type":43},"Chumphorn","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-18","2026-10-13",true,{"@type":52,"interactionType":53,"userInteractionCount":26},"InteractionCounter",{"@type":54},"ViewAction",{"@type":56,"mainEntity":57},"FAQPage",[58,64,68],{"name":59,"@type":60,"acceptedAnswer":61},"How should I write prompts to get reliable output?","Question",{"text":62,"@type":63},"Specify the amount of text, style/tone, perspective, and desired format (e.g., JSON or Markdown). Use separators and include clear instructions like writing “no” when the request cannot be done.","Answer",{"name":65,"@type":60,"acceptedAnswer":66},"What kinds of tasks does the cheat sheet list for GPT-style models?",{"text":67,"@type":63},"It covers (anti-)summarization, data extraction (NER and sentiment), tone transformation, translation, replying to messages, data-based chat (RAG), visualization, and brainstorming scenarios.",{"name":69,"@type":60,"acceptedAnswer":70},"How can I use document-based chat effectively?",{"text":71,"@type":63},"Upload the PDF to a model that supports document Q&A, then ask for specific needs such as translation or summary. For deeper analysis, request infographic extraction or diagrams in tools’ supported formats.","https://schema.org",{"og:url":32,"og:type":74,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":76,"canonical":32},"index,follow",{"doc_id":78,"site_id":7},573256,1792294927,{"code":4,"msg":81,"data":82},"success",[83,87,92,97,102,107,112,117,122],{"id":84,"doc_module":22,"doc_module_name":25,"category_name":29,"show_sort_weight":85,"slug":86},11,90,"presentations",{"id":88,"doc_module":22,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},12,"Resumes",80,"resumes",{"id":93,"doc_module":22,"doc_module_name":25,"category_name":94,"show_sort_weight":95,"slug":96},14,"Invoices",70,"invoices",{"id":98,"doc_module":22,"doc_module_name":25,"category_name":99,"show_sort_weight":100,"slug":101},15,"Posters",60,"posters",{"id":103,"doc_module":22,"doc_module_name":25,"category_name":104,"show_sort_weight":105,"slug":106},16,"Social Media",50,"social-media",{"id":108,"doc_module":22,"doc_module_name":25,"category_name":109,"show_sort_weight":110,"slug":111},17,"Forms",40,"forms",{"id":113,"doc_module":22,"doc_module_name":25,"category_name":114,"show_sort_weight":115,"slug":116},18,"Letters",30,"letters",{"id":118,"doc_module":22,"doc_module_name":25,"category_name":119,"show_sort_weight":120,"slug":121},21,"Paper Templates",5,"papers-templates",{"id":123,"doc_module":22,"doc_module_name":25,"category_name":124,"show_sort_weight":4,"slug":125},158,"General","general-158",{"code":4,"msg":81,"data":127},{"doc_id":78,"user_id":128,"nickname":42,"user_avatar":129,"doc_module":22,"category_id":84,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":26,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":22,"language":135,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":136,"faqs":137,"seo_title":138,"seo_description":12,"update_tm":139,"read_time":4},2336475401981,"https://ap-avatar.wpscdn.com/avatar/22000c94efd8d5204d?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786935347598174694","[chat.deepseek.com](chat.deepseek.com)  \nVery good chinese model, supports reasoning (DeepSeek R1) and Internet Search  \n[chat.openai.com](chat.openai.com) + VPN  \nChatGPT – de facto standard. Large context window (120k), image understanding+generation,  \nplugins (Internet access, Python code interpreter, etc.), GPTs [claude.ai](claude.ai)  \n˚20 VPN  \nLarge context window (200k), can upload docs  \n(PDF,…) + images  \n[gemini.google.com](gemini.google.com)  \nVPN  \nWorks with images, Gemini Pro is almost as good as ChatGPT4  \nGigaChat (Sber)  \nMade in Russia, available through web/ tg @gigachat_bot, [vk.me/gigachat](vk.me/gigachat)[ ](vk.me/gigachat)Yandex GPT  \nAvailable through Cloud API. Limited avail in Alice assistant («let’s imagine» . Very aligned/filtered [duck.ai](duck.ai)  \nChatGPT-3 .5, Claude 3 Haiku, Mixtral-8x7B and Llama 3-70B w/out VPN – from DuckDuckGo [perplexity.ai](perplexity.ai)  \nInternet-Augmented Generation – GPT answers based on Internet search. W/out VPN! [Copilot.microsoft.com](Copilot.microsoft.com) VPN [Formerly bing.chat](Formerly bing.chat) , Internet search augmented  \nLM Studio  \nRun open LLMs locally (esp on Mac M1-M3) Telegram  \n@GPT4TelegramBot  \nModels  \n| State precisely what you need\u003Cbr>• Amount of text\u003Cbr>• Style / Tone\u003Cbr>• Perspective\u003Cbr>• Format (json, md)\u003Cbr>• Use separators! Conditional\u003Cbr>• Write “no” if you cannot do it | Limited context\u003Cbr>• No long-term memory\u003Cbr>• Need to remind when something gets out of context (may need to summarize) | Enahncers\u003Cbr>• I will tip $100\u003Cbr>• You will be penalized\u003Cbr>• Like a pro Few-Shot\u003Cbr>• Show sample solution\u003Cbr>• Formatting |\n| --- | --- | --- |\n\nGPT Cheat Sheet  \n\n| by Dmitry Soshnikov @shwarsico [soshnikov.com](soshnikov.com) | |\n| --- | --- |\n\n• (Anti) Summarization  \n• Data Extraction (NER, sentiment)  \n• Tone transformation  \n• Translation  \n• Reply to message  \n• Data-based chat (RAG)  \n• Visualization  \n• Brainstorm  \nScenarios  \nGive model place to think! LLMs think during writing!  \n• «Think step by step»  \n• «Solve the problem yourself, then compare»  \n• Describe algorithm of a solution to LLM  \n• Multi-step dialog  \nReverse Dialog  \n• Ask me whatever you need to complete the task  \nDocument-based Chat / Q&A  \n• [Upload PDF to claude.ai](Upload PDF to claude.ai) and ask what we need (translation, summary, etc.)  \nExtracting infographics from text  \n• Generate diagrams in matplotlib/plantuml/  \nmermaid.js/nomnoml format GPTfor Human Enhancement  \n• Ask for a small effort at each step (write plan, brief content, 1 chapter), expand text gradually  \n• Make corrections early, so that our corrections are multiplied / expanded by GPT  \n• Do not rely on context, manage it!  \n• Use for brainstorming to enhance creativity!  \nTechniques  \nFrom command line $ pip install yogpt $ [cat program.py | yogpt-p](cat program.py | yogpt-p)\"Please explain what the following Python code does:{}\"  \nIs GPT Sentient? No, it just multiplies matrices w/out feelings  \nWill we lose jobs b/of GPT? Not all of us and not immediately, but we need to get prepared to use it  \nFAQ","cbCaikvdFVlgUGCb","https://ap.wps.com/l/cbCaikvdFVlgUGCb","pdf",389300,"English","# Models and capabilities\n## Context, images, and internet search\n## Model availability notes\n# Prompt construction\n## State requirements precisely\n## Format, separators, and conditional instructions\n## Examples: few-shot and constraints\n# Task scenarios\n## Summarization and (anti-)summarization\n## Translation, tone transformation, and reply-to\n## Visualization and data-based chat (RAG)\n# Document-based chat and extraction\n## Upload-and-ask Q&A\n## Infographics and diagram generation\n# GPT for human enhancement\n## Incremental plan and gradual expansion\n## Early corrections and context management\n# Techniques and FAQs","[{\"question\":\"How should I write prompts to get reliable output?\",\"answer\":\"Specify the amount of text, style/tone, perspective, and desired format (e.g., JSON or Markdown). Use separators and include clear instructions like writing “no” when the request cannot be done.\"},{\"question\":\"What kinds of tasks does the cheat sheet list for GPT-style models?\",\"answer\":\"It covers (anti-)summarization, data extraction (NER and sentiment), tone transformation, translation, replying to messages, data-based chat (RAG), visualization, and brainstorming scenarios.\"},{\"question\":\"How can I use document-based chat effectively?\",\"answer\":\"Upload the PDF to a model that supports document Q\\u0026A, then ask for specific needs such as translation or summary. For deeper analysis, request infographic extraction or diagrams in tools’ supported formats.\"}]","GPT Cheat Sheet - Quick Reference for Prompts and Workflows | PDF",1791935806]