Use this skill when the user invokes /iteration-of-thought-trace or asks for a default public reasoning trace using Iteration of Thought. The skill writes a durable scratchpad to root memory/{question_name}.md and uses Iteration of Thought as the actual structure of the analysis. Treat the scale as a rough effort target rather than a fixed quota: around 100 numbered lines or roughly 2,000 to 3,500 tokens of public scratchpad detail. Use this skill when the user wants the answer shaped by multi-round reasoning with intermediate summarization extending context indefinitely instead of a generic response.
