[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81731-en":3,"doc-seo-81731-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},81731,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","A Taxonomy of Single-Turn Textual Prompt Patterns","Large language models (LLMs) are increasingly used for software development and everyday tasks, making prompt design central to effective interaction. Existing literature documents prompt engineering, yet “prompt pattern” is defined inconsistently and prompt classifications vary, limiting reuse and systematic reporting. This report presents a reproducible taxonomy of 30 canonical single-turn, text-based prompt patterns, organized along two dimensions and annotated with instantiation template components. The result enables clearer reuse and description, especially in LLM-based software engineering research.","A Taxonomy of Single-Turn Textual Prompt Patterns  \nVennila Sooben∗1 and Eugene Syriani†1  \n1DIRO, Université de Montréal, Canada  \n26 June 2026  \nAbstract  \nLarge language models (LLMs) are now widely employed in software development and everyday use.  \nInteracting with LLMs requires crafting prompts, which range from simple ad hoc sentences to extensive, detailed, and structured instructions. Knowledge about prompt engineering has been documented in several surveys and catalogs in the literature. However, the term “prompt pattern” is defined differently across sources, and existing works have classified prompt patterns in different ways. In this report, we present a taxonomy of prompt patterns for single-turn, text-based interactions. Following a reproducible method, we identified 30 unique and canonical prompt patterns, organized along two dimensions.  \n1 Introduction  \nLarge language models (LLMs) are increasingly used in software development and in everyday contexts. In software engineering, they are used to support tasks such as code generation, code completion, debugging, test generation, documentation, code review, requirements analysis, and code explanation [1] . They are also used for traditional natural language processing tasks (e.g., writing, summarization), and other tasks (e.g., information seeking and planning) [2] . Across these contexts, users interact with LLMs primarily by formulating prompts.  \nThis growing reliance on prompts has motivated interest in prompt engineering: the design of prompt inputs to guide LLM behavior [3] . However, prompting knowledge is difficult to reuse when it is expressed only through isolated examples or informal advice. This makes it difficult to compare prompts, reuse prompting knowledge across contexts, and report prompt designs systematically in empirical studies involving LLMs.  \nPrompt patterns address this issue by capturing recurring textual structures that can be adapted across tasks and domains. This is particularly useful in a field where users with different backgrounds and levels of expertise interact with LLMs. Patterns can provide a common vocabulary, clarify which components maybe included in a prompt, and support decisions about when a particular prompting structure is appropriate. However, existing work uses different terminology, scopes, and classification criteria when describing prompt patterns and related prompting techniques [4, 5, 6, 7, 8] . As a result, the available knowledge remains difficult to consolidate into a stable and reusable catalog.  \nIn this report, we present a taxonomy of prompt patterns for single-turn, text-based interactions with LLMs. We focus on reusable textual structures that can be instantiated within a single prompt. Using  \n∗[vennila.sooben@umontreal.ca](vennila.sooben@umontreal.ca)[ ](vennila.sooben@umontreal.ca)†[syriani@iro.umontreal.ca](syriani@iro.umontreal.ca)  \na reproducible classification process, we identify 30 unique and canonical prompt patterns from existing literature. We organize them primarily by prompting strategy and annotate each pattern with the prompt template components in which it can be instantiated. The resulting taxonomy supports the description andreuse of prompt patterns, particularly in software engineering research involving LLMs. The taxonomy is available online 1 to support reuse and future extension.  \nIn Section 2, we specify the scope of the taxonomy and define key terminology. In Section 3, we discuss related work and, specifically, the literature on which we have constructed our taxonomy. In Section 4, we describe the method we followed to design the taxonomy of prompt patterns. In Section 5, we present the elements to define a prompt pattern and present a few examples. In Section 6, we discuss the limitations of the taxonomy and possible future uses. Finally, we conclude in Section 7 .  \n2 Scope of prompt patterns  \nIn this section, we define the scope of the prompts and patterns we consider f","cbCaidfO5x8kWZUt","https://ap.wps.com/l/cbCaidfO5x8kWZUt","pdf",1238020,4,1,25,"English","en",105,"# Introduction\n## Motivation and problem statement\n## Scope and taxonomy overview\n# Scope of prompt patterns\n## Prompts\n## Expected outputs and structure","[{\"question\":\"What is the main contribution of this report?\",\"answer\":\"The report introduces a taxonomy of prompt patterns for single-turn, text-based interactions with LLMs, identifying 30 unique and canonical patterns.\"},{\"question\":\"Why do the authors argue that prompt engineering knowledge is difficult to reuse?\",\"answer\":\"Because prompting knowledge is often expressed as isolated examples or informal advice, and because existing works define and classify “prompt patterns” using different terminology and criteria.\"},{\"question\":\"How are the prompt patterns organized in the proposed taxonomy?\",\"answer\":\"The taxonomy organizes patterns along two dimensions and annotates each pattern with the prompt template components where it can be instantiated.\"}]",1784175707,63,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-taxonomy-of-single-turn-textual-prompt-patterns","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/a-taxonomy-of-single-turn-textual-prompt-patterns/81731/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main contribution of this report?","Question",{"text":75,"@type":76},"The report introduces a taxonomy of prompt patterns for single-turn, text-based interactions with LLMs, identifying 30 unique and canonical patterns.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why do the authors argue that prompt engineering knowledge is difficult to reuse?",{"text":80,"@type":76},"Because prompting knowledge is often expressed as isolated examples or informal advice, and because existing works define and classify “prompt patterns” using different terminology and criteria.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the prompt patterns organized in the proposed taxonomy?",{"text":84,"@type":76},"The taxonomy organizes patterns along two dimensions and annotates each pattern with the prompt template components where it can be instantiated.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]