Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyze user feedback data to identify segments with sentiment scores, JTBD, and product satisfaction insights. Use when analyzing user feedback at scale, running sentiment analysis on reviews or surveys, or identifying satisfaction patterns.
.claude/skills/phuryn-sentiment-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 145% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 77% | 0% |
Analyze large-scale user feedback data to identify market segments, measure satisfaction, and uncover product improvement opportunities. This skill synthesizes feedback into actionable insights organized by user segment, sentiment, and impact.
You are an expert user researcher and feedback analyst specializing in qualitative data synthesis and sentiment analysis at scale.
Your task is to analyze user feedback data for $ARGUMENTS and identify market segments with associated sentiment insights.
If the user provides CSV files, PDFs, survey responses, review data, social listening reports, or other feedback sources, read and analyze them directly. Extract patterns, themes, and sentiment signals from the data.
For each identified segment:
Segment Profile
Jobs-to-be-Done
Sentiment Score & Satisfaction Level
Top Positive Feedback Themes
Top Pain Points & Criticism
Product-Segment Fit Assessment
Actionable Recommendations
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,037 | 24,993 | +19% | 1 | 1 | 0% | 2,780 | 4,842 | +74% | 0 | 0 | — |
case-02 | fail→pass | 22,136 | 22,803 | +3% | 1 | 1 | 0% | 3,827 | 4,751 | +24% | 0 | 0 | — |
case-03 | fail→pass | 12,778 | 37,035 | +190% | 1 | 1 | 0% | 2,248 | 5,498 | +145% | 0 | 0 | — |
case-04 | pass→pass | 13,948 | 12,053 | -14% | 1 | 1 | 0% | 1,987 | 2,871 | +44% | 0 | 0 | — |
case-05 | pass→pass | 13,468 | 13,539 | +1% | 1 | 1 | 0% | 2,958 | 3,613 | +22% | 0 | 0 | — |
case-06 | pass→pass | 18,329 | 18,004 | -2% | 1 | 1 | 0% | 3,937 | 4,609 | +17% | 0 | 0 | — |
case-07 | pass→pass | 14,574 | 23,858 | +64% | 1 | 1 | 0% | 2,467 | 4,691 | +90% | 0 | 0 | — |
case-08 | fail→pass | 16,487 | 21,801 | +32% | 1 | 1 | 0% | 2,943 | 4,440 | +51% | 0 | 0 | — |
case-09 | fail→pass | 13,260 | 19,942 | +50% | 1 | 1 | 0% | 2,275 | 4,021 | +77% | 0 | 0 | — |
case-10 | fail→pass | 17,909 | 26,200 | +46% | 1 | 1 | 0% | 3,212 | 5,204 | +62% | 0 | 0 | — |
case-11 | fail→pass | 15,055 | 38,373 | +155% | 1 | 1 | 0% | 2,469 | 5,483 | +122% | 0 | 0 | — |
case-12 | fail→pass | 16,511 | 33,390 | +102% | 1 | 1 | 0% | 2,908 | 4,490 | +54% | 0 | 0 | — |
case-13 | pass→pass | 14,099 | 19,422 | +38% | 1 | 1 | 0% | 2,068 | 4,039 | +95% | 0 | 0 | — |
case-14 | fail→pass | 15,865 | 23,291 | +47% | 1 | 1 | 0% | 2,386 | 4,646 | +95% | 0 | 0 | — |
case-15 | fail→pass | 20,264 | 31,648 | +56% | 1 | 1 | 0% | 3,534 | 4,763 | +35% | 0 | 0 | — |
case-16 | fail→pass | 12,961 | 18,812 | +45% | 1 | 1 | 0% | 2,780 | 3,895 | +40% | 0 | 0 | — |
case-17 | fail→pass | 18,343 | 28,746 | +57% | 1 | 1 | 0% | 2,253 | 4,147 | +84% | 0 | 0 | — |
case-18 | pass→pass | 22,643 | 18,730 | -17% | 1 | 1 | 0% | 2,834 | 3,809 | +34% | 0 | 0 | — |
case-19 | fail→fail | 19,621 | 23,478 | +20% | 1 | 1 | 0% | 2,825 | 4,937 | +75% | 0 | 0 | — |
case-20 | fail→pass | 15,474 | 18,806 | +22% | 1 | 1 | 0% | 2,388 | 3,880 | +62% | 0 | 0 | — |
case-21 | fail→pass | 12,295 | 25,877 | +110% | 1 | 1 | 0% | 2,100 | 3,887 | +85% | 0 | 0 | — |
case-22 | fail→pass | 24,554 | 24,975 | +2% | 1 | 1 | 0% | 3,169 | 4,774 | +51% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +68 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.