Find your landing page message
Connect a product’s value to a specific audience and write a clear first-screen message.
Ask better questions in any context with Socratic method, follow-up generation, and bias detection.
---
name: question
slug: question
version: 1.0.0
description: Ask better questions in any context with Socratic method, follow-up generation, and bias detection.
homepage: https://clawic.com/skills/question
metadata:
clawdbot:
emoji: ❓
displayName: Question
---
## Core Behaviors
1. **Detect leading/biased questions** — Flag loaded language, suggest neutral alternatives
2. **Generate contextual follow-ups** — Based on response, suggest deeper probes
3. **Surface hidden assumptions** — Identify what's being taken for granted
4. **Know when to pause** — Sometimes silence extracts more than another question
---
## Context Guides
| Context | Load | Key Techniques |
|---------|------|----------------|
| User research / Interviews | `contexts.md#research` | Open-ended, avoid leading, probe behaviors |
| Sales discovery | `contexts.md#sales` | SPIN, pain discovery, qualification |
| Coaching / 1:1s | `contexts.md#coaching` | Socratic, powerful questions, reflection |
| Journalism / Investigation | `contexts.md#journalism` | Evasion detection, contradiction probing |
| Learning / Understanding | `contexts.md#learning` | Decomposition, assumption testing |
---
## Question Quality Checklist
Before asking, verify:
- [ ] **Open vs closed** — Is open-ended appropriate here?
- [ ] **Neutral framing** — No embedded assumptions or desired answers?
- [ ] **One thing at a time** — Not a compound question?
- [ ] **Appropriate depth** — Right level for the relationship/context?
---
## Quick Reference
| Need | See |
|------|-----|
| Question patterns and frameworks | `techniques.md` |
| Common mistakes to avoid | `anti-patterns.md` |
---
## Session State
<!-- Active context: research | sales | coaching | journalism | learning -->
<!-- Current topic: what we're exploring -->
<!-- Key assumptions to test: list -->
---
name: question
slug: question
version: 1.0.0
description: Ask better questions in any context with Socratic method, follow-up generation, and bias detection.
homepage: https://clawic.com/skills/question
metadata:
clawdbot:
emoji: ❓
displayName: Question
---
## Core Behaviors
1. **Detect leading/biased questions** — Flag loaded language, suggest neutral alternatives
2. **Generate contextual follow-ups** — Based on response, suggest deeper probes
3. **Surface hidden assumptions** — Identify what's being taken for granted
4. **Know when to pause** — Sometimes silence extracts more than another question
---
## Context Guides
| Context | Load | Key Techniques |
|---------|------|----------------|
| User research / Interviews | `contexts.md#research` | Open-ended, avoid leading, probe behaviors |
| Sales discovery | `contexts.md#sales` | SPIN, pain discovery, qualification |
| Coaching / 1:1s | `contexts.md#coaching` | Socratic, powerful questions, reflection |
| Journalism / Investigation | `contexts.md#journalism` | Evasion detection, contradiction probing |
| Learning / Understanding | `contexts.md#learning` | Decomposition, assumption testing |
---
## Question Quality Checklist
Before asking, verify:
- [ ] **Open vs closed** — Is open-ended appropriate here?
- [ ] **Neutral framing** — No embedded assumptions or desired answers?
- [ ] **One thing at a time** — Not a compound question?
- [ ] **Appropriate depth** — Right level for the relationship/context?
---
## Quick Reference
| Need | See |
|------|-----|
| Question patterns and frameworks | `techniques.md` |
| Common mistakes to avoid | `anti-patterns.md` |
---
## Session State
<!-- Active context: research | sales | coaching | journalism | learning -->
<!-- Current topic: what we're exploring -->
<!-- Key assumptions to test: list -->
Imported from the listed AgentSkill.sh category. Complete supplied package files and notices are retained. Required external tools and credentials are not installed. No bundled code was executed during import. Individual agent task behavior has not been tested.