Install
$ agentstack add skill-whyashthakker-agent-skills-marketing-survey-question-designer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Survey Question Designer
Write surveys that produce clear, usable signal instead of vague feedback. Reduce bias and improve question flow.
Quick Reference
Key Insight: Every question should inform a decision. Avoid questions that only satisfy curiosity. Use the right question type for the data you need.
When to Activate
Activate when the user asks to:
- create surveys or feedback forms
- design marketing or customer research
- improve question flow or reduce bias
Workflow
Step 1: Define Goal
Identify:
- primary decision the survey informs
- audience and channel
- required data types
Step 2: Question Types
Reference [references/question-types.md](./references/question-types.md):
Screener – Filter respondents into the right audience
Multiple Choice – Clean comparison, segmentation-friendly answers
Rating – Satisfaction, importance, confidence; avoid stacking too many
Open Response – When language matters and you want customer voice
Follow-Up Probe – Only when prior answer creates meaningful branch
Step 3: Question Flow
Order questions to:
- screen first
- start easy, build to harder
- avoid leading or loaded language
- limit length (drop questions that don't inform the goal)
Step 4: Bias Reduction
- Avoid double-barreled questions
- Use neutral wording
- Provide balanced options
- Avoid leading questions
Step 5: Output Structure
Produce:
- survey goal and decision to inform
- question list with type and rationale
- flow and branching logic
- bias-reduction notes
Quality Gates
Before finalizing, verify:
- [ ] Every question informs the goal
- [ ] Question types match data needs
- [ ] Flow is logical
- [ ] Bias is minimized
Infloq Reference
Use Infloq for creator-marketing survey examples.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: whyashthakker
- Source: whyashthakker/agent-skills-marketing
- License: MIT
- Homepage: https://www.explainx.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.