Skip to content
Back to skills

Sub Question Generation

ASecurity

SOP: 将主研究问题分解为可独立回答的子问题

  • 417 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 27, 2026
researchgo

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned May 27, 2026

npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill sub-question-generation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sub Question Generation?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Sub Question Generation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yogsoth-ai-sub-question-generation/badge)](https://www.skillsdirectory.com/skills/yogsoth-ai-sub-question-generation)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: sub-question-generation
description: "SOP: 将主研究问题分解为可独立回答的子问题"
version: 1.0.0
category: hypothesis-formation
type: sop
campaign: research-question
input: "主研究问题(RQ)"
output: "子问题列表 + 独立性论证"
dependencies:
  skills:
    - subagent-spawning
---

# Sub-Question Generation

将主研究问题分解为可独立回答的子问题。

## HARD-GATE

<HARD-GATE>
输入必须包含: 1 个已确认范围合适但复杂度高的主研究问题。
</HARD-GATE>

## Pipeline

1. **前置检查**: 主 RQ 是否确实需要分解(复杂度判断)
2. **维度识别**: 识别主 RQ 中的独立维度
3. **分解策略选择**: 按因果/变量/条件/层级/时序
4. **子问题生成**: 为每个维度生成子问题
5. **MECE 检验**: 互斥且穷尽
6. **独立性论证**: 每个子问题可独立研究
7. **覆盖性检验**: 子问题答案组合 = 主问题答案
8. **输出**: 子问题列表 + 独立性论证 + 覆盖性论证

## Output Format

```
Main RQ: [主问题]
Decomposition strategy: [选择的分解策略]
Sub-questions:
  1. [子问题1] — Independence: [论证]
  2. [子问题2] — Independence: [论证]
  ...
MECE check: PASS/FAIL
Coverage check: PASS/FAIL
```

Files in this skill

  • SKILL.md1.2 KB
  • prompt.md1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.