# Question Generation

> SOP for generating research questions from promising gaps in the design space.

- Skill: `yogsoth-ai/question-generation` (Agent Skill)
- Install (CLI): `npx skillmds@latest add yogsoth-ai/question-generation`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/question-generation/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: yogsoth-ai (https://skillmd.com/u/yogsoth-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yogsoth-ai/question-generation

---


# Question Generation

Generate actionable research questions from high-scoring gaps in the design space.

## Tool

CC file write + `vault_add_edge`

## Protocol

1. For each priority gap, formulate a research question: "What happens when we combine X with Y?"
2. Write `questions/<question-slug>.md` with frontmatter (type: question)
3. Body: the question, why it's interesting, what we'd need to answer it
4. Add edges: raises (gap → question), related_to (question → relevant dimensions)
5. **Inline wikilinks:** For each edge created, ensure the question page body contains `[[dir/slug]]` pointing to the target (dir/slug = target path minus `.md`). Place inline at semantically relevant location. Skip if already present.

## HARD-GATE

<HARD-GATE>
Questions must be specific and answerable, not vague. "How does X work?" is too broad.
"What is the effect of combining local attention with graph-based routing?" is specific.
</HARD-GATE>

## Yield

Returns: `{ questions_created: number, paths: string[] }`