Skip to content

hoavdc/CodexKit / skills/codexkit-survey-analyzer

codexkit-survey-analyzer

Unverified

Analyze survey and feedback data with statistical distributions, cross-tabulations, significance testing, and open-ended theme extraction. Produces executive-ready survey reports with segment comparisons and action recommendations. Use when processing NPS, CSAT, employee engagement, or market research surveys.

Survey Analyzer

When to Use

  • After collecting NPS, CSAT, or employee engagement survey responses
  • When analyzing market research or customer feedback data
  • When leadership needs actionable insights from survey results
  • When comparing satisfaction across segments (regions, teams, products)

Procedure

Step 1 — Data Overview

Summarize the survey:

  • Total responses vs invitations sent → response rate
  • Collection period
  • Question types: Likert scale, multiple choice, ranking, open-ended
  • Known biases: self-selection, non-response, recency

Step 2 — Quantitative Analysis

For each closed-ended question:

QuestionNMeanMedianStd DevDistribution Shape
[Q1 text][n][mean][median][sd]Normal / Skewed L / Skewed R / Bimodal

Calculate key indices:

  • NPS: % Promoters (9–10) − % Detractors (0–6)
  • CSAT: % Satisfied (4–5 on 5-point scale)
  • Engagement: Overall index from engagement battery

Step 3 — Segment Comparison

Cross-tabulate by key segments:

SegmentNScorevs OverallSignificant?
Region A12072+4Yes (p<0.05)
Region B9565−3No (p=0.12)

Test significance:

  • Chi-square for categorical × categorical
  • t-test or ANOVA for continuous × categorical
  • Flag small samples (<30) as unreliable

Step 4 — Open-Ended Theme Extraction

For free-text responses:

  1. Code responses into themes (max 8–10 themes)
  2. Count frequency of each theme
  3. Identify sentiment per theme (positive / neutral / negative)
ThemeFrequency% of ResponsesSentimentExample Quote
Onboarding speed4518%Negative"Took 3 weeks to get access"

Step 5 — Insight Synthesis

Structure insights as:

  • What: the finding (data-driven)
  • So What: why it matters (impact)
  • Now What: recommended action

Step 6 — Action Recommendations

PriorityInsightActionOwnerTimeline
1NPS dropped 8 pts in segment XInvestigate root causeCX Lead2 weeks

Inputs

InputRequiredFormat
Survey responsesYesCSV, spreadsheet, or summary tables
Question listYesQuestions with response types
SegmentsRecommendedHow to slice the data
Previous resultsRecommendedFor trend comparison

Output

## Survey Analysis — [Survey Name]

### Overview
- **Period:** Q1 2024 | **Responses:** 532 / 1,200 (44% response rate)
- **NPS:** +32 (↓4 from Q4) | **CSAT:** 78% (stable)

### Key Findings
1. **Onboarding satisfaction dropped 12 points** — driven by Region B
   - Root cause: New system rollout created delays
   - Action: Expedite training for Region B ops team

2. **Support quality is the #1 driver of promoter scores**
   - Correlation: 0.72 between support rating and NPS
   - Action: Protect support team headcount in budget cycle

### Segment Comparison
[Cross-tabulation table]

### Open-Ended Themes
[Theme frequency table with example quotes]

### Recommended Actions
[Prioritized action table with owners]

Definition of Done

  • Response rate calculated and bias noted
  • All quantitative questions summarized with distributions
  • Segment comparisons with significance testing
  • Open-ended themes extracted and quantified
  • What / So What / Now What insights provided
  • Action recommendations prioritized with owners

Quality Criteria

  • Data sources and assumptions are explicitly stated
  • Calculations are reproducible from provided inputs
  • Visualizations or tables have clear labels, units, and time ranges
  • Caveats and confidence levels are documented for estimates

Verification (4C)

CheckQuestion
CorrectnessAre formulas, aggregations, and statistical methods applied correctly?
CompletenessDoes the analysis cover all requested metrics and time ranges?
Context-fitAre the chosen metrics relevant to the business question being answered?
ConsequenceIf this data were used for a decision today, what blind spots remain?

Edge Cases

  • Missing or incomplete data — Document gaps and their potential impact on conclusions. Provide ranges instead of point estimates.
  • Outliers skewing results — Report with and without outliers. Document the decision to include or exclude.
  • Changing data definitions mid-period — Split analysis at the change boundary and note the schema difference.

Changelog

  • v1.0.0 — Initial release
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 318kUpdated Claude CodeCodexUnverifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 318kUpdated Claude CodeCodexUnverifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 318kUpdated Claude CodeCodexUnverifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 196kUpdated Claude CodeCodexVerifiedInstall