Survey analysis

Skill shinzoxD/knackbox/skills/research/survey-analysis

Analyze survey results into themes, segments, and decision-ready findings. Use whenever the user shares survey responses, NPS or CSAT comments, form exports, or asks what the survey says — with counts and caveats rather than vibes.From its SKILL.md

Install

npx -y skills add shinzoxD/knackbox --skill survey-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.5 KB, 254 tokens by cl100k_base, as published. Nobody here has run it

Survey Analysis

Surveys mix quantitative items and open text. Report n, base rates, and selection bias. Do not overclaim causality.

Workflow

Clarify decision the survey should inform.
Profile sample: n, response rate if known, segments.
Quant: distributions, top-box, crosstabs with minimum cell sizes.
Qual: code open ends into themes with counts.
Insights + recommendations with confidence.
Limitations: bias, wording, seasonality.

Output format

## Survey readout: <name>
**Sample:** n=…

### Key findings
1. …

### Quant summary
tables

### Themes from open ends
| Theme | Mentions | Example |

### Recommendations
…

### Limitations
…

Rules

Always show denominators.
Avoid percent of tiny bases without warning.
Do not invent responses.
Separate correlation from "users want X because".
Protect respondent privacy in examples.
NPS: document calculation if used.

Edge cases

Low n: directional only.
Multi-select: clarify base.
Translated responses: caution on nuance.

What ships with it: 1 file

1.2 KB alongside SKILL.md

benchmarks/

prompts.json1.2 KB