# avoid-leading-questions

avoid-leading-questions reviews a draft survey question, names the bias behind it, and gives a concrete rewrite for each of the three cases it covers.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 240 repo stars
- Author: franklee16
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/franklee16/academic-research-skills/tree/HEAD/running-surveys-experiments/avoid-leading-questions/SKILL.md
- Updated: 2026-09-18
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/avoid-leading-questions

## What it does

Point the skill at a draft survey item and it works out which bias is at play: the respondent guessing what answer the researcher wants, hiding a behaviour that looks bad in public, or nodding along with whatever the scale says. Each case gets its own fix.

For a nudge in the wording, the fix is to cut the lead-in that announces the expected answer. Adding items you expect to be irrelevant helps too: anyone who rates them as highly as the important ones is chasing agreement with you, not answering. Sensitive topics get pointed toward list experiments, randomized response or records of actual behaviour instead of self-report.

A plain yes/no about insider trading or drug use is not treated as a finished measurement. It reads as a floor for the sample rather than a rate. Interpretation problems and recall problems belong to `clarity-concreteness` and `survey-design-checklist`; this one does not cover them.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add franklee16/academic-research-skills --skill avoid-leading-questions -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/avoid-leading-questions/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/avoid-leading-questions/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add franklee16/academic-research-skills --skill avoid-leading-questions -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/avoid-leading-questions/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add franklee16/academic-research-skills --skill avoid-leading-questions -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/avoid-leading-questions/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install franklee16/academic-research-skills running-surveys-experiments/avoid-leading-questions/SKILL.md
```

2. **Manually: put the files in place**
- File: `.github/skills/avoid-leading-questions/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add franklee16/academic-research-skills --skill avoid-leading-questions -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/franklee16/academic-research-skills --path running-surveys-experiments/avoid-leading-questions
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/avoid-leading-questions/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/franklee16/academic-research-skills/tree/HEAD/running-surveys-experiments/avoid-leading-questions/SKILL.md

## When to use it
- strip a line about what experts believe out of a draft item
- ask about insider trading without respondents underreporting
- swap a yes/no comprehension check for an open question
- diagnose a survey where every answer is “agree”
- pick a list experiment for a question on drug use

## Example prompts
- Is this item leading? It opens with what experts believe before asking for the respondent's own view.
- How do I ask about insider trading so people don't lie?
- Everyone picks “agree” on every item of my survey — what should I change?

## Similar
- [scientific-critical-thinking](https://affpapa.org/en/nevibecode/skills/k-dense-ai-scientific-critical-thinking.md) — skill · 2600 installs
- [survey-generation](https://affpapa.org/en/nevibecode/skills/survey-generation.md) — skill · 1800 installs
- [measure-survey-analysis](https://affpapa.org/en/nevibecode/skills/measure-survey-analysis.md) — skill · 730 installs
- [deep-research](https://affpapa.org/en/nevibecode/skills/hkustdial-deep-research.md) — skill · 687 installs
- [instrument-designer](https://affpapa.org/en/nevibecode/skills/instrument-designer.md) — skill · 669 installs
- [research-survey](https://affpapa.org/en/nevibecode/skills/research-survey.md) — skill · 318 installs

From the same set: [franklee16/academic-research-skills](https://affpapa.org/en/nevibecode/by/franklee16/academic-research-skills.md) — 98 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
