# Intake

> Lightweight intent clarification dialogue — only invoked when the entry point cannot determine the correct strategy from context alone. Maximum 3 questions. Pure routing, not profiling.

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

---


# Intake

Lightweight intent clarification. Only invoked when the entry point can't determine the correct strategy from context alone.

## Execution

Dialogue — inline, 1-3 questions max.

## What to Clarify

1. What's the research question or topic?
2. What's the purpose? (entering new field / exhaustive coverage / specific question / building argument / tracing lineage)
3. Any seed papers or prior context?

## Key Behavior

- This is NOT actor-profiling. No background questions, no resource mapping.
- Pure intent → strategy routing.
- Keep it under 3 exchanges.
- If the user's first answer makes the strategy obvious, stop asking and route immediately.
- Prefer multiple-choice when possible (e.g., "Are you: (a) entering a new field, (b) doing exhaustive coverage, (c) investigating a specific question, (d) building an argument, (e) tracing from known papers?")