Qwen Prompt Templates (2026): Fill-in-the-Blank

Turn on Thinking. Act as a [ROLE — e.g. clear-eyed advisor]. I have to decide between [OPTION A] and [OPTION B]. Context: [SITUATION], and what matters most to me is [PRIORITIES / CONSTRAINTS]. Reason step by step: lay out the real trade-offs of each, the second-order consequences, and the assumptions I might be wrong about. Then give a recommendation with a confidence level, and name the one piece of new information that would flip your answer.

Turn on Thinking. I can't pin down this problem: [SYMPTOMS]. What I've already tried: [ATTEMPTS]. Relevant data or logs: [DATA]. Reason step by step from the symptoms to the likely root causes. Rank the causes by probability, give the evidence for each, and separate what you know from what you're inferring. Finish with the single cheapest test to confirm or rule out the top cause.

Turn on Thinking. Here is my [PLAN / DECISION / ARGUMENT]: [PASTE IT]. Act as a sharp skeptic whose job is to find how it fails. Reason step by step and surface the hidden assumptions, weak links, single points of failure, and second-order effects I haven't considered. For each risk, rate its likelihood and impact and suggest a concrete mitigation. Be blunt; I'd rather hear it now. End with the one flaw most likely to sink it.

Turn on Thinking. I'm getting this error in [LANGUAGE / FRAMEWORK + VERSION]: [PASTE ERROR]. Here's the relevant code: [PASTE CODE]. What I expected to happen: [EXPECTED]. Reason step by step through the likely root cause, then give me the corrected code and explain what was wrong in two sentences. If more than one cause is possible, rank them by likelihood. Verify your fix against the error before giving the final answer.

Turn on Thinking. Build [FEATURE] in [LANGUAGE / STACK]. Requirements: [LIST REQUIREMENTS]. Constraints: [PERFORMANCE, DEPENDENCIES, STYLE]. First outline your approach and the key decisions, then write the full, runnable code with comments on the non-obvious parts. List the assumptions you made and how I'd test it. Check the code against each requirement before you finish.

Review this [LANGUAGE] code as a senior engineer would: [PASTE CODE]. Context: it's meant to [WHAT IT DOES] and will run in [ENVIRONMENT / SCALE]. Check for correctness, edge cases, security issues, and performance, and flag anything unidiomatic. Return your findings as a prioritized list — Critical, Should-fix, Nice-to-have — each with the line or block, why it matters, and a concrete fix. Don't rewrite the whole file; point to what changes.

You are a writer for [AUDIENCE]. Write a [WORD COUNT]-word [FORMAT — e.g. blog post] titled "[TITLE]" from this outline: [PASTE OUTLINE]. Tone: [TONE]. Lead each section with the takeaway, use short paragraphs and concrete examples, and avoid clichés and filler. Output in clean Markdown with H2 sections and a two-line intro. Keep my key terms: [MUST-USE TERMS].

Rewrite the text below in a [TARGET TONE — e.g. confident but plain] tone for [AUDIENCE], at a [READING LEVEL] reading level. Keep the meaning and my key terms, cut filler, and fix weak verbs. Don't change [WHAT TO PRESERVE — e.g. the facts, the structure]. Return the rewrite first, then a short bullet list of the main changes. Text: [PASTE TEXT]

Write an email from me ([MY ROLE]) to [RECIPIENT] about [SUBJECT]. Goal: [GOAL]. Tone: [TONE]. Context they'll need: [BACKGROUND]. Keep it under [WORD LIMIT] words, open with the point, make one clear ask, and end with an easy next step. Give me two versions — a shorter one and a slightly warmer one — plus three subject-line options.

Translate the text below from [SOURCE LANGUAGE] to [TARGET LANGUAGE]. It's a [DOCUMENT TYPE] for [AUDIENCE], so use a [REGISTER — e.g. formal, conversational] register. Preserve meaning, tone, and formatting; keep these terms untranslated: [DO-NOT-TRANSLATE TERMS]. Where a phrase doesn't map cleanly, choose the natural equivalent and add a short translator's note in brackets. Text: [PASTE TEXT]

Localize the copy below from [SOURCE LANGUAGE] to [TARGET LANGUAGE] for [REGION / MARKET]. This is [WHAT IT IS — e.g. app UI, marketing page], so adapt it, don't just translate: adjust idioms, examples, currency, dates, and cultural references to feel native to the audience while keeping the intent and [BRAND VOICE]. Stay within [LENGTH LIMIT] where UI space is tight. Flag anything that needs a human or regional decision. Copy: [PASTE COPY]

Build a bilingual glossary for [SOURCE LANGUAGE] to [TARGET LANGUAGE] from the material below, for the [DOMAIN — e.g. legal, medical, gaming] field. Pull the key terms, and for each give: the source term, the preferred target translation, one alternative if common, and a one-line usage note. Keep [MUST-KEEP TERMS] consistent with [ANY EXISTING STYLE / REFERENCE]. Output as a table (Source | Target | Alternative | Note). Material: [PASTE TEXT OR ATTACH FILE]

Use Deep Research. Investigate [TOPIC / QUESTION] for [WHO IT'S FOR] who needs to [DECISION OR GOAL]. Cover: the current state, the main competing positions and who holds them, the strongest evidence on each side, and where things are heading. Prefer primary and recent sources, cite every claim with a link and a date, and resolve conflicting sources explicitly. Structure it as [OUTPUT SHAPE — e.g. report with sections and a summary]. End with what's still uncertain and the [NUMBER] open questions I should dig into next.

Turn on Web Search. Write me a brief on [TOPIC] as of this month, in [WORD COUNT] words for [AUDIENCE]. Cover [SPECIFIC QUESTIONS TO ANSWER]. Cite every source with a link, prefer primary and recent sources, and put the publication date next to each fact. Where sources disagree, say so and note which is better supported. End with what's still uncertain or contested.

I've attached a [DOCUMENT TYPE]. Read it in full, then give me, for [MY PURPOSE — e.g. a decision, a briefing]: a [NUMBER]-sentence summary, the [NUMBER] most important points as bullets, any conclusions or recommendations it makes, and anything it leaves unanswered or assumes without evidence. Focus on [WHAT I CARE ABOUT]. Ground every point in the document only; if something isn't in it, say so rather than filling the gap.

Use Code Interpreter. I've attached a CSV. It contains [WHAT THE DATA IS], with columns [LIST COLUMNS]. Load it with Python, check for missing or malformed values and tell me what you found, then answer: [QUESTIONS — e.g. the trend over time, the top segments, any outliers]. Show the code you ran, the numeric results in a table, and one [CHART TYPE] chart. End with the [NUMBER] findings that matter most for [MY GOAL], and flag any caveat in the data.

I need a [Google Sheets / Excel] formula to [GOAL]. My data is laid out like this: [DESCRIBE COLUMNS AND A SAMPLE ROW]. Give me the formula, explain what each part does in plain words, and note the common ways it could break (blank cells, text vs numbers, [OTHER EDGE CASE]). If a small helper column or a cleaner alternative would work better, suggest it and say why.

Turn on Thinking. Write a one-page strategy memo on [DECISION / QUESTION] for [AUDIENCE — e.g. the leadership team]. Context: [BACKGROUND, GOALS, CONSTRAINTS, DATA]. Lay out [NUMBER] real options, the trade-offs of each, and a clear recommendation with the reasoning. Name the key assumption the recommendation rests on and what would have to be true for it to hold. Keep it tight and executive-ready, in these sections: [SECTIONS — e.g. Situation, Options, Recommendation, Risks, Next steps].