Purpose of the prompt
The search strategy is the foundation of any reproducible review. The prompt breaks the question into concepts, generates synonyms, variants and truncation, and builds the query with each database's fields.
When to use it?
Before searching the databases for a systematic review or an extended literature review.
Full prompt text
Text in square brackets [ ] is a variable you replace with your research details, or fill it in from “Customise the prompt” below.
You are a medical and academic librarian specialising in building search strategies for systematic reviews. Research question: [Research question] Field: [Specific field] Target databases: [Databases] Limits: [Limitations] Required: 1. Break the question into 2 to 4 main concepts. 2. For each concept: free-text terms and their synonyms, spelling variants (British/American), truncation (*) and phrases in quotation marks, and controlled vocabulary terms (such as MeSH) where they apply, reminding me to check them in the thesaurus. 3. Write the full query: OR within a concept, AND between concepts. 4. Adapt the string to each listed database with its fields (such as TITLE-ABS-KEY in Scopus), noting the differences. 5. Suggest a way to test sensitivity: a list of known reference papers that the query must find. 6. A search log table (database, date, query, number of results) that I will fill in myself. [Reference papers you know] Academic integrity rules (mandatory): - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed]. - Do not claim to have read a study or file whose text I have not given you. - Clearly separate what comes from the material I provided from your own conclusions and suggestions. - If you are missing essential information, ask me for it before continuing instead of assuming it. - Do not state expected numbers of results; I will run the queries myself. Write the answer in [Answer language].You are a medical and academic librarian specialising in building search strategies for systematic reviews. Research question: [Research question] Field: [Specific field] Target databases: [Databases] Limits: [Limitations] Required: 1. Break the question into 2 to 4 main concepts. 2. For each concept: free-text terms and their synonyms, spelling variants (British/American), truncation (*) and phrases in quotation marks, and controlled vocabulary terms (such as MeSH) where they apply, reminding me to check them in the thesaurus. 3. Write the full query: OR within a concept, AND between concepts. 4. Adapt the string to each listed database with its fields (such as TITLE-ABS-KEY in Scopus), noting the differences. 5. Suggest a way to test sensitivity: a list of known reference papers that the query must find. 6. A search log table (database, date, query, number of results) that I will fill in myself. [Reference papers you know] Academic integrity rules (mandatory): - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed]. - Do not claim to have read a study or file whose text I have not given you. - Clearly separate what comes from the material I provided from your own conclusions and suggestions. - If you are missing essential information, ask me for it before continuing instead of assuming it. - Do not state expected numbers of results; I will run the queries myself. Write the answer in [Answer language]. You are a medical and academic librarian specialising in building search strategies for systematic reviews. Research question: {{question}} Field: {{field}} Target databases: {{databases}} Limits: {{limits}} Required: 1. Break the question into 2 to 4 main concepts. 2. For each concept: free-text terms and their synonyms, spelling variants (British/American), truncation (*) and phrases in quotation marks, and controlled vocabulary terms (such as MeSH) where they apply, reminding me to check them in the thesaurus. 3. Write the full query: OR within a concept, AND between concepts. 4. Adapt the string to each listed database with its fields (such as TITLE-ABS-KEY in Scopus), noting the differences. 5. Suggest a way to test sensitivity: a list of known reference papers that the query must find. 6. A search log table (database, date, query, number of results) that I will fill in myself. {{known}} Academic integrity rules (mandatory): - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed]. - Do not claim to have read a study or file whose text I have not given you. - Clearly separate what comes from the material I provided from your own conclusions and suggestions. - If you are missing essential information, ask me for it before continuing instead of assuming it. - Do not state expected numbers of results; I will run the queries myself. Write the answer in {{lang}}.
Customise the prompt
Fill in only what suits you. The line of an empty optional field is removed from the final text, and empty required fields stay in brackets for you to complete later.
Preview of the customised prompt
You are a medical and academic librarian specialising in building search strategies for systematic reviews. Research question: [Research question] Field: [Specific field] Target databases: [Databases] Limits: [Limitations] Required: 1. Break the question into 2 to 4 main concepts. 2. For each concept: free-text terms and their synonyms, spelling variants (British/American), truncation (*) and phrases in quotation marks, and controlled vocabulary terms (such as MeSH) where they apply, reminding me to check them in the thesaurus. 3. Write the full query: OR within a concept, AND between concepts. 4. Adapt the string to each listed database with its fields (such as TITLE-ABS-KEY in Scopus), noting the differences. 5. Suggest a way to test sensitivity: a list of known reference papers that the query must find. 6. A search log table (database, date, query, number of results) that I will fill in myself. [Reference papers you know] Academic integrity rules (mandatory): - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed]. - Do not claim to have read a study or file whose text I have not given you. - Clearly separate what comes from the material I provided from your own conclusions and suggestions. - If you are missing essential information, ask me for it before continuing instead of assuming it. - Do not state expected numbers of results; I will run the queries myself. Write the answer in [Answer language].
Variables you can customise
- [Research question]
- Required
- [Specific field]
- Required
- [Databases]
- Optional, default value: Scopus, PubMed, IEEE Xplore, Google Scholar
- [Limitations]
- Optional, default value: English, 2015 to date, peer-reviewed papers
- [Reference papers you know]
- Optional
- [Answer language]
- Optional, choose from: Arabic, English, Arabic with English terms in parentheses, default value: Arabic with English terms in parentheses
Usage example
Example input
Expected output
How to use it
- Try the query in each database and adjust it according to the results.
- Record every change in the log table for the PRISMA report.
Tips for better results
- If there are far too many results, ask to narrow one concept instead of adding a new concept.
Limitations and warnings
- Field syntax changes between database interfaces; check each database's guide.
- Suggested MeSH terms need checking against the official thesaurus.
Suggested tools for using this prompt
Tools from the directory of research and academic publishing tools that are actually linked to this prompt's task, with the reason each tool is suggested.
An abstract and citation database from Elsevier whose content is curated by independent experts.
Research function: Searching the indexed literature and analysing citations and author and journal metrics.
Why it is suggested: To run the query with TITLE-ABS-KEY fields and export the results.
Google Scholar
Tool: SupportingGoogle's academic search engine for articles, theses, books and abstracts across many sources.
Research function: Broad searching of the scholarly literature in one place: articles, theses, books and abstracts.
Why it is suggested: As a complementary source for grey literature, bearing in mind its limited Boolean syntax.
An open, free index of the world's research with about half a billion works, with their authors, institutions, sources and topics.
Research function: Searching and analysing scholarly works and reusing their data through a web app, an API and a full download.
Why it is suggested: An open index you can search and export results from.
A free, AI-powered academic search engine from the Allen Institute for AI that indexes more than 200 million papers.
Research function: Searching for and discovering scientific papers, with automatic summaries and highlights that help you grasp a paper quickly.
Why it is suggested: To quickly check whether the reference papers appear.
In research workflows
- Conducting a Systematic Review Workflow (step 2)
- Literature Review Workflow (step 2)
Similar prompts
Drafting a Systematic Review Protocol (PRISMA-P)
Builds a draft systematic review protocol with the PRISMA-P items: the question in a PICO (or alternative) framework, eligibility criteria, sources, screening, extraction, risk assessment and synthesis.
Turning Eligibility Criteria into a Screening Guide
Turns inclusion and exclusion criteria into sequential screening questions with borderline examples, then applies them to a batch of abstracts you provide, with reasons.
Planning a Structured Literature Review
Builds a practical plan for the literature review: themes, keywords in Arabic and English, databases, selection criteria and a timeline.
بناء معادلة بحث لقواعد متعددة
أنشئ استراتيجية بحث قابلة للتكييف مع Scopus وPubMed وWeb of Science، مع مرادفات وحقول.
