Chain-of-Thought Scaffold: A Fixed 5-Step "Think Before You Answer" Process
Forces the AI to think through 5 fixed steps before answering — restate → list assumptions → reason step by step → self-check → conclude. Field tests show roughly a 30% reduction in confidently wrong answers on complex reasoning tasks.
Question: {{question}}
Do NOT answer immediately. Work through these inside <reasoning> tags:
1. Restate what is being asked in your own words.
2. List the key facts and any assumptions you must make.
3. Reason step by step.
4. Self-check: what would make this answer wrong?
5. Only then write the final answer outside the tags.
If step 4 reveals a flaw, fix it before answering.Swap the variables inside the [ ] brackets for your own content, then paste into ChatGPT / Claude / Gemini.
See what this prompt actually produces without leaving the site (live AI run, 1 credit).
For problems that require reasoning (math, logic, planning), this scaffold forces the AI to think it through fully before answering, resulting in far fewer cases of "sounds confident but is actually wrong" compared to asking directly.
一段先在 <reasoning> 內走完 5 步、最後才給結論的回覆。
A description of the intended result. Check this entry's testing notes and try the prompt with your own inputs.
[question]需要推理的問題
填下面的欄位，上方 prompt 會即時替換 [方括號] 內容。填好後按「複製組好的 prompt」直接丟進工具。
Question: {{question}}
Do NOT answer immediately. Work through these inside <reasoning> tags:
1. Restate what is being asked in your own words.
2. List the key facts and any assumptions you must make.
3. Reason step by step.
4. Self-check: what would make this answer wrong?
5. Only then write the final answer outside the tags.
If step 4 reveals a flaw, fix it before answering.Suno Engineer's Mindset: 4 Steps to a Song That Doesn't Sound Like AI
A studio engineer's breakdown of Suno's fatal weaknesses (fried vocals, high-frequency artifacts), plus a 4-step DAW workflow and a Suno Studio cleanup prompt.
5 Claude Weekly Workflows That Stuck After 6 Months
Proposal generator / meeting processor / content repurposer / Friday review / shutdown reset — out of 40 I tried, only these 5 survived, each saving 30+ minutes per run.
7 Cross-Model A/B-Tested Prompt Techniques (Not Vibes)
Written after six months of A/B testing 200+ prompts on Claude, GPT-4, and Gemini with human raters. Covers persona + constraint stacking, anti-examples, role-reversal QA, cognitive scaffolds, emotional priming, uncertainty CoT, and steelman-first.
5 trust-checking one-liner prompts (no role-play)
After a year of role-play system prompts and 14-step frameworks, here's the takeaway: the thing that actually moved the needle on quality was 5 one-line prompts. No roles, no markdown, no "you are an expert."