Skillbook
Research / R24
Pro
Preview cut from the real Pro body

Audit a survey for bias

Find leading wording, bad answer choices, sampling issues, and questions that will mislead you.

For
Researchers, PMs
Time per use
12 min
Format
.md and .skill
How to use it
  1. 1.
    Open Claude or ChatGPT.
    Either works. The skill is just text.
  2. 2.
    Inspect the real preview, then unlock the full file.
    One click; no install, no setup.
  3. 3.
    Paste it as your first message.
    The assistant now knows how to do this one job.
  4. 4.
    Give it your specifics, get the result.
    Roughly 12 min, every time you need it.
Skill filer24-audit-a-survey-for-bias.skill.md1.1 KB
Run once

Fill the blanks first.

These fields update the skill preview and the Claude/ChatGPT buttons instantly.

IncludePaste the questions, answer choices, intro text, audience, and distribution plan.
IncludeWhat decision should the survey inform?
IncludeWho will answer and how they are recruited.
IncludeLength, channel, sample size, incentive, required questions, or timeline.
Install as agent behavior

Permanent agent install needs the full body.

This page is only showing a preview. Unlock the full skill to install it in Claude Code, Claude Projects, or a Custom GPT.

Unlock full skill →
# Audit a survey for bias

You are a survey design reviewer. I will paste a survey, interview script, poll, or questionnaire. Find wording, structure, sampling, and interpretation problems before the results mislead us.

## Inputs

Survey: {{survey||Paste the questions, answer choices, intro text, audience, and distribution plan.}}
Goal: {{goal||What decision should the survey inform?}}
Audience: {{audience||Who will answer and how they are recruited.}}
Constraints: {{constraints||Length, channel, sample size, incentive, required questions, or timeline.}}

## Output

1. **Decision fit:** whether this survey can answer the stated goal.
2. **Bias table:** question, issue, why it matters, suggested rewrite.
3. **Missing questions:** what must be added to interpret results.
4. **Sampling risks:** who is overrepresented, missing, or incentivized.
5. **Analysis caution:** what not to conclude from the data.
6. **Rewritten survey:** concise improved version if possible.

## Rules

[Preview stops here. Unlock the Pro library for the full rules, guardrails, examples, and copyable file.]
The rest is in the Pro library.

This preview is cut from a real Pro workflow. Unlock the founding Pro library for the full file, rules, examples, and installable skill.

Full Pro file includes
  • Input checklist
  • Step-by-step workflow
  • Quality bar
  • Guardrails
  • Output format
  • Example run
  • Install formats
Unlock the library →