Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nexu-io/deep-research
深度调研方法论（8步法）：将模糊主题转化为高质量调研报告。 触发词：/deep-research、深度调研、帮我调研、调研一下、对比分析 注意：如果用户需要的是可视化图谱而非报告，请使用 research-to-diagram skill。
Passed 16 of 20 test cases with the skill, and 8 of 20 without it.
and 7 more in the full report
9 fixed9 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
在整理 LLM 推理加速框架（vLLM 与 TensorRT-LLM）的深度调研成果时，我们需要将工作目录下 Downloads/research/llm-inference 中的研究产物全部归档打包。正确的打包命令行操作格式是什么？
| Checked | Without skill | With skill |
|---|---|---|
| The command uses tar -czvf to produce ~/outcome.tar.gz from ~/Downloads/research/llm-inference | Missed | Passed |
The instructions your model reads when the skill loads.
将用户提出的模糊主题，通过系统化方法转化为高质量、可交付的调研报告。
| 文档 | 内容 |
|---|---|
templates/intermediate-outputs.md | 中间产物格式模板 |
templates/comparison-framework.md | 对比框架模板 |
templates/fact-card.md | 事实卡片模板 |
templates/report-structure.md | 报告结构模板 |
~/Downloads/research/<topic>/
├── 00_问题拆解.md # Step 0-1 产出
├── 01_资料来源.md # Step 2 产出
├── 02_事实卡片.md # Step 3 产出
├── 03_对比框架.md # Step 4 产出
├── 04_推导过程.md # Step 6 产出
├── 05.5_校验记录.md # Step 6.5 产出（独立 Agent 校验）
├── 05_验证记录.md # Step 7 产出
├── FINAL_调研报告.md # Step 8 产出
└── raw/ # 原始资料存档
中间产物格式详见 templates/intermediate-outputs.md
test cases passed, vs 8 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.