Chain-of-Thought Scaffold
A reusable scaffold that asks the model to think step-by-step before answering — for problems where the right reasoning path matters more than the final word.
Force step-by-step reasoning before the final answer.
Prompt
Solve the problem below.
<problem>
{{PROBLEM}}
</problem>
First, work through your reasoning inside <thinking> tags. Consider edge cases, check your math, and challenge your assumptions. Then give the final answer inside <answer> tags. Be concise in the answer — keep the reasoning in <thinking>.
Variables
{{PROBLEM}}— the problem to solve
When to Use
- Math and logic problems
- Complex reasoning tasks
- Debugging scenarios
- Anywhere you want to inspect the model's reasoning