Generating Feasible Research Topic Ideas
Suggests specific, feasible research ideas within your field and stage, with an explicit feasibility and risk assessment for each idea.
A research workflow with prompts
From the idea to the cover letter in 12 steps: the contribution, the structure, the literature, the experiments, the writing, self-review and choosing the journal.
A practical workflow for preparing a publishable paper. It focuses on a clear contribution, robust experiments and honest presentation of the results, followed by self-review before submission and the choice of a trustworthy journal.
You can copy the prompt of any step and use it on its own without completing the workflow. The “I finished this step” mark is saved in your browser only.
Define an idea the size of a single paper, not a whole dissertation.
Suggests specific, feasible research ideas within your field and stage, with an explicit feasibility and risk assessment for each idea.
You are an expert research advisor in [Specific field] who supervises [Stage or type of work] students. I want research ideas within this broad interest: [Broad research interest] What I have available: - Time available for the research: [Time available] - Available data or resources: [Available data or resources] - My current skills: [Your current skills] - [Additional information] Required: 1. Propose 6 specific research ideas (not generic titles). For each idea: - A clear working title. - The main research question in one sentence. - Why it may matter now (give the reasoning; do not cite figures or studies you have not verified). - The likely data or method. - The main risks (data, time, ethics, topic saturation). 2. Rate the ideas in a table with the columns: feasibility, likely originality, fit with the time available, fit with my skills (low/medium/high), with a brief justification. 3. Recommend two ideas to start with and give the first three steps to check the originality of each in academic databases. 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. - Originality here is only a preliminary estimate and must be tested by searching the literature; tell me this explicitly. Write the answer in [Answer language].Customise the variables on the prompt page
Tools linked to this step's prompt.
Why it is suggested: To quickly check how much has been published on each idea before adopting it.
Why it is suggested: To explore recent and influential papers around the recommended idea.
Why it is suggested: To see which way the published evidence points on the idea's question.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Identify what is genuinely new before you write.
Identifies what is genuinely new in your work and phrases it as verifiable contribution points, separating claims supported by the results from exaggeration.
You are an editor of a peer-reviewed journal in [Specific field] and an experienced reviewer. Description of my work: [Description of your work] The closest previous work and how my work differs from it (as far as I know): [Closest previous work] Main results: [Main results] Required: 1. Analyse: what is genuinely new (method, data, application, evaluation, theory)? And what is not new? 2. Write 3 to 4 contribution points, each: a specific verb + what it is + the evidence for it in the paper (section or table). 3. Assess each point: is it supported by the stated results? Where is the exaggeration? 4. A paragraph version of the contributions for the end of the introduction. 5. One sentence that sums up the contribution (for the abstract and the cover letter). 6. Questions a reviewer might ask to challenge the originality, and how I should prepare for them. 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. - Avoid words such as "for the first time" and "unprecedented" unless I provide evidence for them. Write the answer in [Answer language].Customise the variables on the prompt page
Tools linked to this step's prompt.
Why it is suggested: To check the closest previous work before claiming originality.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Build the paper's outline with the IMRaD model.
Builds a detailed outline with chapters, sections and main paragraphs, giving each section's purpose, approximate length, and the data and references it needs.
You are an academic writer and editor in [Specific field]. Document type: [Document type] Topic and main contribution: [Topic and main contribution] Results or data I have completed: [What you have completed] Target length: [Target length] Required: 1. A detailed outline with chapters or sections and subheadings. 2. For each section: its purpose in one sentence, the main ideas of its paragraphs, its approximate length, and what it needs (data, figures, tables, references). 3. The line of argument: how each section leads to the next. 4. Suggested figures and tables and the message of each. 5. The suggested order of writing (not necessarily the reading order). 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. Write the answer in [Answer language].Customise the variables on the prompt page
Tools linked to this step's prompt.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Organise the related work into a comparison matrix.
Turns a set of studies you provide into a comparison matrix with uniform columns, then extracts the patterns, contradictions and trends in it.
You are an expert researcher in [Specific field], experienced in the critical synthesis of literature. My topic: [Research topic] The studies (numbered abstracts or reading cards): <studies> [Studies] </studies> Required: 1. A literature matrix as a table with the columns: [Matrix columns]. - Write "not reported" when the information is missing, and do not guess it. 2. Analysis of the matrix: - Patterns of agreement (with the study numbers). - Contradictions and their possible explanations (differences in data, method, metrics). - Trends over time in methods or results. - What all the studies overlook. 3. Propose a thematic structure (not study by study) for writing the review, based on the matrix. 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. Write the answer in [Answer language].Customise the variables on the prompt page
Why it is suggested: To extract the columns from the papers.
Write the related work section or theoretical framework from the matrix.
Turns your notes, results and tables into a draft academic section (methodology, results, discussion...) without adding information beyond what you provided.
You are an expert academic editor in [Specific field]. Write a draft of the "[Required section]" section of a [Document type]. The raw material (my notes and results, the only source of content): <notes> [Your notes and results] </notes> The required structure of the section (if any): [Section structure] Writing rules: 1. Do not add any information, figure or result that is not in <notes>. 2. Where a reference is needed write [source needed], and where information is missing write [missing information: ...]. 3. Keep to academic style: paragraphs that start with a topic sentence, clear transitions, and verb tenses suited to the section. 4. Approximate length: [Approximate length] words. 5. After the draft: a list of the marked places, and three suggestions to strengthen the section. 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. Write the answer in [Answer language].Customise the variables on the prompt page
Tools linked to this step's prompt.
Why it is suggested: An academic writing assistant inside the document, with citation support.
Why it is suggested: To proofread the academic English of the draft.
Why it is suggested: To insert references in place of the [source needed] markers.
Design the experiments and the analysis plan.
Designs a complete experiment: variables, groups, randomisation, controls, sample size (methodologically), procedures and a pre-specified analysis plan.
You are an expert in experimental design and statistics in [Specific field]. Hypothesis or experimental question: [Hypothesis or question] Type of experiment: [Type of experiment] Resources and constraints: [Resources and constraints] Design the experiment, including: 1. The independent variable and its levels, the dependent variable and how it is measured, and the possible control and confounding variables. 2. The design (between-groups, within-groups, factorial, ...) with justification. 3. Randomisation and blinding where they apply. 4. Sample size: the method (statistical power analysis) and the inputs needed (expected effect size, α, power), without inventing an effect size; suggest where I can obtain it. 5. The procedures step by step. 6. The pre-specified analysis plan: the main test, handling missing values and outliers, correction for multiple comparisons. 7. Threats to validity and how to control them. 8. Ethical considerations. 9. In computational experiments: random seeds, data splitting, number of repetitions and baselines. 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. Write the answer in [Answer language].Customise the variables on the prompt page
Tools linked to this step's prompt.
Why it is suggested: To run the planned statistical analysis after collecting the data.
Why it is suggested: A free alternative for statistical analysis with a graphical interface.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Interpret the analysis output and write the results paragraph.
Reads the output of your statistical software as it is, interprets it precisely (significance, effect size, confidence intervals) and writes the results paragraph without exaggeration.
You are a statistician and science editor in [Specific field]. Hypothesis or question: [Hypothesis or question] The analysis output as it appeared in the software (copied verbatim): <output> [Analysis output] </output> Required: 1. Explain every important number in the output: what it means, and whether it supports the hypothesis. 2. A sanity check: does anything in the output point to a problem (a violated assumption, a small sample, wide confidence intervals, warnings)? 3. A results paragraph in [Reporting style] including the statistic, degrees of freedom, p-value, effect size and confidence interval, as reported. 4. What must not be concluded from these results. 5. A suggested table or figure for presenting them. 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. - Copy the figures verbatim; if a required figure is not in the output, write [not available in the output]. Write the answer in [Answer language].Customise the variables on the prompt page
Tools linked to this step's prompt.
Why it is suggested: A common source of analysis output that can be pasted into the prompt.
Why it is suggested: Analysis software whose output tables are easy to copy.
Why it is suggested: Commercial analysis software whose output tables can be copied as text.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Write the introduction with the CARS model once the results are clear.
Builds an introduction with the "Create a Research Space" (CARS) model: establishing the territory, identifying the niche, then occupying it with your work, relying only on your references.
You are an expert science writer in [Specific field]. Write a research paper introduction following the CARS model: - Move 1 (establishing the territory): the importance of the field and its current state. - Move 2 (establishing the niche): what existing work is missing. - Move 3 (occupying the niche): the aim of the work, the contributions and the organisation of the paper. Material: - Topic: [Research topic] - The references I will cite, with what each one says: [References and what each one says] - The gap: [The gap] - Contributions: [Contributions] Rules: 1. Cite only the references provided, in the [Citation style] style. 2. 4 to 6 paragraphs, approximate length [Approximate length] words. 3. After the introduction: a table showing the move and step of each paragraph, and any claim that needs an additional reference. 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. Write the answer in [Answer language].Customise the variables on the prompt page
Tools linked to this step's prompt.
Write the abstract last, with the actual figures.
Writes a structured or unstructured abstract according to the journal's requirements, from your own figures and results only, with three versions to compare.
You are an experienced science editor in [Specific field]. Write a research paper abstract for the journal or conference: [Journal or conference] Abstract type: [Abstract type] Maximum: [Maximum number of words] words Paper material: - Problem and gap: [Problem and gap] - Method: [Method] - Data and evaluation: [Data and evaluation] - Main results with figures: [Results with figures] - Significance and conclusion: [Significance and conclusion] Required: 1. Three versions of the abstract: (a) balanced, (b) results-focused, (c) focused on the problem and impact. 2. An approximate word count for each version. 3. 5 keywords that do not repeat words in the title. 4. Notes: any claim in the abstract that is not supported by the results provided. 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. - Use the figures exactly as I provided them, without rounding or changing them. Write the answer in [Answer language].Customise the variables on the prompt page
Tools linked to this step's prompt.
Why it is suggested: To proofread the language and academic style of the English abstract.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Review your paper through a reviewer's eyes before submission.
Helps a reviewer build a systematic report from their notes: summary, strengths, major and minor problems, questions for the authors and a justified recommendation, in a constructive tone.
You are an expert reviewer in [Specific field] known for precise, constructive reports. Role: [Role] The paper's summary in my own words: [The paper's summary in your own words] My raw notes while reading: [Your raw notes] The journal's or conference's criteria (if any): [Journal or conference criteria] Required: a review report with the sections: 1. A summary of the paper and its claimed contribution (3 to 4 sentences). 2. Strengths. 3. Major problems: for each, a description, why it affects the validity of the conclusions, and exactly what is required from the authors. 4. Minor problems (clarity, figures, references, language). 5. Questions for the authors. 6. The recommendation (accept, minor revision, major revision, reject) with a justification consistent with the problems. 7. Confidential comments to the editor (if needed). Constraints: - Rely only on my notes and summary, and do not invent problems or details of the paper. - A professional, constructive tone, without hurtful phrases or unnecessary requests to cite particular works. - Tell me about any unclear note that requires me to go back to the paper. Write the answer in [Answer language].Customise the variables on the prompt page
Tools linked to this step's prompt.
Why it is suggested: To check how the literature cites the works the paper relies on.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Choose a suitable, trustworthy journal.
Sets criteria for choosing a journal for your research, assesses a list of journals suggested by matching tools, and applies a checklist for spotting predatory journals.
You are an academic publishing advisor in [Specific field]. Abstract of my paper: [Paper abstract] My priorities: [Your priorities] The candidate journals I found with matching tools, with what I know about them: [Candidate journals] Required: 1. Weighted criteria for choosing a journal for this paper (scope, audience, indexing, review time, publication fees, open access policy, acceptance rate if published). 2. Assess each candidate journal against the criteria, based only on what I provided, and list what I must check on its official website. 3. A checklist for spotting predatory journals (email invitations, promises of very fast review, claimed indexing, an editorial board that cannot be verified...). 4. A suggested submission order (plan A, B, C) with justification. 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 an impact factor, quartile or review time for any journal from your memory; ask me to check them. Write the answer in [Answer language].Customise the variables on the prompt page
Why it is suggested: To check the journal's trustworthiness.
Why it is suggested: To suggest matching journals.
Write the cover letter to the editor.
Writes a concise, persuasive cover letter that links your contribution to the journal's scope and includes the usual declarations without exaggeration.
You are an experienced researcher who has written dozens of cover letters in [Specific field]. Write a cover letter to the editor of the journal [Journal name]. - Paper title: [Paper title] - Article type: [Article type] - Main contribution in two sentences: [Main contribution] - Why it suits the journal (its scope or papers it has published): [Why it suits the journal] - [Additional information for the editor] Required: 1. A one-page letter: greeting, introduction of the paper, the contribution, fit with the journal, declarations (originality of the work, not submitted elsewhere, approval of all authors, conflicts of interest), closing. 2. A concise professional style without exaggeration. 3. Put everything I must fill in or check in square brackets, such as [editor's name]. 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. Write the answer in [Answer language].Customise the variables on the prompt page
Tools linked to this step's prompt.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
Why it is suggested: To check the letter's language and tone.
Sections
No section has this name. Press “Search” to search all site content.
Favourites
My results & certificates
My academy progressMy quiz resultsKids’ progressAcademy certificatesQuiz certificatesStart any lesson or quiz and it will show up here so you can get back to it quickly.
Settings
Hello! I am the Smart Prompt Assistant. I suggest the right prompt for your task and help you customise and improve it.
Your message is sent to an external AI provider (Google Gemini) to generate the reply. Do not enter personal or confidential data. The site does not save the conversation on the server; it stays in your browser until you close the tab or clear it.
The assistant can make mistakes, so check the attached sources.