# Scope Clarification

> Structured questioning SOP to determine research boundaries, depth, and breadth. Used during spec generation.

- Skill: `yogsoth-ai/scope-clarification` (Agent Skill)
- Install (CLI): `npx skillmds@latest add yogsoth-ai/scope-clarification`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/scope-clarification/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/scope-clarification

---


# Scope Clarification

Ask the user 2-3 questions to understand research boundaries. Use AskUserQuestion with multiple choice options where possible.

## Questions (select 2-3 most relevant based on North Star)

1. **Depth vs Breadth**
   - "How should this research be structured?"
   - Options: (A) Broad survey — cover many angles lightly (B) Deep dive — focus on 1-2 aspects thoroughly (C) Balanced — moderate coverage with selective depth

2. **Sub-topic Boundaries**
   - "Are there specific sub-topics to include or exclude?"
   - Open-ended — let user specify

3. **Output Ambition**
   - "What level of output are you aiming for?"
   - Options: (A) Exploratory — map the landscape, identify directions (B) Hypothesis-ready — produce testable claims (C) Experiment-ready — full design with methodology

4. **Domain Scope**
   - "Is this domain-specific or cross-domain?"
   - Options: (A) Single domain — stay within [inferred field] (B) Cross-domain — actively seek analogies from other fields (C) Let the research guide this

## Rules

- Ask ONE question at a time
- Skip questions whose answers are obvious from the North Star
- Record answers for use in pipeline composition