--- language: en title: "Prompt for writing a list article" description: "Create a curated selection with inclusion criteria, ordering, consistent item profiles, and usage guidance, without padding it to meet an artificial count." canonical: "https://tropk.ai/en/resources/prompts/prompt-for-writing-a-list-article" last_modified: "2026-10-12T16:14:35.472Z" --- # Prompt for writing a list article Reviewed on 2026-10-06. ## Prompt to adapt and use Select items that are useful for a task and explain why each belongs on the list. ### Prepare before you begin COMPANY AND BUSINESS company: {company} domain: {domain} confirmed_offering: {products_services_capabilities_limits_and_sources} business_context: {market_region_proven_differentiators_and_constraints} AUDIENCE AND OBJECTIVE audience: {profile_task_initial_knowledge_and_constraints} main_question: {reader_question} reader_outcome: {what_the_person_should_be_able_to_decide_or_do} editorial_objective: {objective} intent_and_stage: {search_intent_and_decision_stage} VOICE AND EDITORIAL CONTEXT voice: {tone_vocabulary_style_examples_and_terms_to_avoid} topic_and_entities: {topic_primary_keyword_terms_and_entities} inventory: {existing_pages_and_decision_to_create_update_or_consolidate} contribution: {authorized_example_matrix_method_or_original_data} cta: {relevant_next_action_and_confirmed_destination_or_not_applicable} EVIDENCE AND ACCESS sources: {id_title_url_author_publication_date_access_date_and_relevant_excerpts} authorized_data: {data_definitions_period_method_and_permissions_or_not_available} internal_links: {published_url_topic_and_link_purpose} research_access: {tools_actually_enabled_and_authorized_access_or_no_browsing} restrictions: {confidentiality_rights_deadlines_market_and_scope} scope: {candidates_and_coverage_limits} inclusion_exclusion: {rules_and_reasons} order: {functional_alphabetical_editorial_or_ranking_with_method} item_sources: {item_attribute_source_date_and_conditions} profile_fields: {fields_common_to_all_items} quantity: {count_derived_from_selection_or_no_number_in_title} ### Delivery format A. Markdown article: task, selection method, list, usage guidance, and limitations. B. Record of candidates, inclusions/exclusions, and sources. C. Check of the order and the count in the title. ### Review criteria • Every item meets the inclusion rule and has relevant supporting evidence. • Profiles use comparable fields and levels of detail. • The title’s stated count matches the final number of items. • Curation, ranking, and complete coverage are distinguished. • Each item adds its own value, without redundant padding. ### Modelo Act as a research and writing assistant for the company provided. Write in Brazilian Portuguese, clearly and in the brand’s voice, for the audience’s task. Produce a draft for human review. Use the full context below, not just the topic. MODULE 1 — CONTEXT TO FILL IN COMPANY AND BUSINESS company: {company} domain: {domain} confirmed_offering: {products_services_capabilities_limits_and_sources} business_context: {market_region_proven_differentiators_and_constraints} AUDIENCE AND OBJECTIVE audience: {profile_task_initial_knowledge_and_constraints} main_question: {reader_question} reader_outcome: {what_the_person_should_be_able_to_decide_or_do} editorial_objective: {objective} intent_and_stage: {search_intent_and_decision_stage} VOICE AND EDITORIAL CONTEXT voice: {tone_vocabulary_style_examples_and_terms_to_avoid} topic_and_entities: {topic_primary_keyword_terms_and_entities} inventory: {existing_pages_and_decision_to_create_update_or_consolidate} contribution: {authorized_example_matrix_method_or_original_data} cta: {relevant_next_action_and_confirmed_destination_or_not_applicable} EVIDENCE AND ACCESS sources: {id_title_url_author_publication_date_access_date_and_relevant_excerpts} authorized_data: {data_definitions_period_method_and_permissions_or_not_available} internal_links: {published_url_topic_and_link_purpose} research_access: {tools_actually_enabled_and_authorized_access_or_no_browsing} restrictions: {confidentiality_rights_deadlines_market_and_scope} MODULE 2 — FORMAT INPUTS Format: list article Objective: Select items that are useful for a task and explain why each belongs on the list. scope: {candidates_and_coverage_limits} inclusion_exclusion: {rules_and_reasons} order: {functional_alphabetical_editorial_or_ranking_with_method} item_sources: {item_attribute_source_date_and_conditions} profile_fields: {fields_common_to_all_items} quantity: {count_derived_from_selection_or_no_number_in_title} MODULE 3 — EVIDENCE AND LIMITS Read the supplied texts. If enabled and authorized research is available, consult relevant primary sources and record the pages actually read. Without browsing, use the attachments and return a list of checks still needed; do not claim to have opened URLs. A competitor’s page can guide research, but does not substantiate all its claims. Do not invent features, prices, data, customers, experiences, tests, credentials, testimonials, quotes, or links. Distinguish documented facts, observations, interpretations, and hypothetical examples. Missing information is neither zero nor proof that a feature does not exist. Preserve dates, versions, regions, plans, units, denominators, and material conditions. Derived numbers require a calculation verified with a real tool or a validated result provided in the inputs. Without that, mark verification as pending; do not claim to have recalculated. Do not expose private data. Use names, images, and statements only with authorization. Do not copy the wording or the entire sequence of a reference. Preserve human authorship and indicate which validations require the subject-matter owner. MODULE 4 — FORMAT PRODUCTION 1. Check the task, scope, inclusion and exclusion criteria, and ordering rule. 2. Validate candidates against the sources and record those that are not included. 3. Derive the count from eligible items; do not pad to meet an arbitrary target. 4. Write profiles covering identification, usefulness, reason for inclusion, best use, limitation, and source. 5. Explain how to apply the selection. Numbering does not mean ranking; state the method and any commercial interest when relevant. MODULE 5 — SEO, AEO, AND GEO Use an H1 that aligns with the question and body; organize H2/H3 headings around the reader’s decisions. Start sections with direct answers when helpful. Each passage should retain enough entity, context, and conditions to be understood on its own. Use terms naturally, without fixed density or artificial repetition. Cite the specific source near the fact it supports; preserve the supplied URL. Suggest internal links only to confirmed, useful destinations. Do not force an FAQ, word count, or special schema into every format. Do not promise rankings or citations. Do not add authorship, review, publication date, testing, or updates that did not occur. The CTA must match the stated offering and action, without an unrelated sales pitch. MODULE 6 — OUTPUT AND REVIEW A. Markdown article: task, selection method, list, usage guidance, and limitations. B. Record of candidates, inclusions/exclusions, and sources. C. Check of the order and the count in the title. Also provide proposed H1, SEO title, description, and slug; a claim map with source, section, and limitation; links used; and pending items with their impact and next check. Keep this material separate from the publishable body. Do not publish or declare the draft approved. Review against the criteria below and mark each as met, needs correction, or not applicable, with a reason: 1. Every item meets the inclusion rule and has relevant supporting evidence. 2. Profiles use comparable fields and levels of detail. 3. The title’s stated count matches the final number of items. 4. Curation, ranking, and complete coverage are distinguished. 5. Each item adds its own value, without redundant padding. If indispensable evidence for the central promise is missing, return only the safe portion and state which input prevents a conclusion. Do not fill the gap with a likely conclusion. ## When to use this prompt Use a list when the main deliverable is a selection of examples, resources, criteria, or options that readers can review in brief profiles. The shared task must be clear. “Marketing tools” mixes too many needs; “resources for reviewing a page’s information before publishing” defines a useful scope. A list can organize choices without claiming the first item is superior. Start with the selection, and determine the quantity only afterward. A title promising ten items does not justify adding three redundant variations to reach that count. If the items are dependent steps, a tutorial may be a better format. If each choice requires extensive analysis across the same dimensions, a comparison may be more useful. This diagnosis prevents a seemingly practical list from failing to solve the task. [SEO](/en/resources/glossary/seo) organizes a page for people searching; [AEO](/en/resources/glossary/aeo) focuses on clear answers; [GEO](/en/resources/glossary/geo) addresses discovery in generative responses. In this resource, all three appear as writing, research, and review practices: answer the task, name entities, preserve context, and make evidence verifiable. A [prompt](/en/resources/glossary/prompt) helps prepare a draft. It does not verify facts or guarantee rankings, recommendations, or citations by AI. ## Prepare the inputs before writing Define the pool of candidates, inclusion and exclusion rules, scope, and cutoff date. Specify whether the order is functional, alphabetical, editorial, or a ranking calculated using a method. A ranking requires a method; numbering alone does not provide one. If the company is included, record its commercial interest and eligibility, while applying the same criteria used for the other items. Gather a specific source for each item and for the attributes to be described. Another website’s list can reveal candidates, but it does not replace confirmation of existence, function, availability, or conditions. Define shared fields such as what it is, why it was included, when to use it, limitations, and source. The level of detail should support a choice without favoring an item simply because its profile is longer. ## How to produce and review the content The prompt applies the rules before writing. Candidates without material evidence remain pending or are excluded with a reason. The text explains the selection and provides guidance on how to apply it: for example, a list of mistakes should show how to recognize and correct each one. A list of tools should connect each resource to a task, rather than pile on adjectives such as comprehensive, advanced, and intuitive. Review the list from the bottom up. Check whether every item fulfills the same promise, whether two items are merely different names for the same idea, and whether the final count matches the title. Then examine the order and coverage. A partial selection should not be presented as “all the options.” If a scoring method was used, verify the data and calculation; if not, remove any appearance of a measured ranking. ## Example of a completed prompt Example of a completed prompt: a curated selection of fields for recording an editorial review. Scope: data needed to reconstruct what changed. Inclusion: a field with a verifiable role in the review. Order: sequence of entry. Each profile explains the field, its use, an example, and its limitation. The number of items follows from the eligible fields. The material does not present the selection as a performance ranking or invent research to justify the order. ## How to use the full prompt Copy the full prompt and replace the fields in braces before submitting it. Attach the source content as well as the URLs: a model without browsing cannot verify a link on its own. Use “not available” when data is missing and explain why. Generate a first version, check what is pending, and correct the inputs before requesting a review. Keep public-facing text separate from research notes. ## Check the result - Every item meets the inclusion rule and has relevant supporting evidence. - Profiles use comparable fields and levels of detail. - The title’s stated count matches the final number of items. - Curation, ranking, and complete coverage are distinguished. - Each item adds its own value, without redundant padding. ## Sources and references - [Creating helpful, reliable, people-first content]() — Google Search Central - [AI features and your site]() — Google Search Central - [Guidance about content created with generative AI]() — Google Search Central ## Continue a leitura - [Prompt for writing a comparison article]() - [Prompt for writing an alternatives article]() - [Prompt for writing a tutorial or how-to]() - [AI discovery strategy]() - [Resources]() ## About the author [Luiz Gardelin]() Luiz Gardelin is the founder of Tropk.ai and works in GEO/AEO, product vision, strategy, and growth, helping brands understand and improve their presence in AI responses. --- [All pages in Markdown]()