Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Execute this skill enables AI assistant to analyze the sentiment of text data. it identifies the emotional tone expressed in text, classifying it as positive, negative, or neutral. use this skill when a user requests sentiment analysis, opinion mining, or emoti... Use when analyzing code or data. Trigger with phrases like 'analyze', 'review', or 'examine'.
.claude/skills/jeremylongshore-analyzing-text-sentiment/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 50% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | -1% | 0% |
Classify text sentiment as positive, negative, or neutral with confidence scores for customer reviews, social media posts, and survey responses.
This skill empowers Claude to perform sentiment analysis on text, providing insights into the emotional content and polarity of the provided data. By leveraging AI/ML techniques, it helps understand public opinion, customer feedback, and overall emotional tone in written communication.
This skill activates when you need to:
User request: "Analyze the sentiment of these customer reviews: 'The product is amazing!', 'The service was terrible.', 'It was okay.'"
The skill will:
User request: "Perform sentiment analysis on the following tweet: 'I love this new feature!'"
The skill will:
This skill can be integrated with other Claude Code plugins to automate workflows, such as summarizing feedback alongside sentiment scores or triggering actions based on sentiment polarity (e.g., escalating negative feedback).
The skill produces structured output relevant to the task.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→fail | 10,924 | 8,864 | -19% | 1 | 1 | 0% | 2,484 | 2,581 | +4% | 0 | 0 | — |
case-11 | fail→pass | 14,914 | 14,484 | -3% | 1 | 1 | 0% | 3,331 | 3,687 | +11% | 0 | 0 | — |
case-01 | pass→pass | 13,220 | 10,191 | -23% | 1 | 1 | 0% | 2,701 | 2,681 | -1% | 0 | 0 | — |
case-02 | pass→pass | 8,147 | 9,682 | +19% | 1 | 1 | 0% | 1,791 | 2,714 | +52% | 0 | 0 | — |
case-03 | pass→pass | 8,852 | 10,163 | +15% | 1 | 1 | 0% | 1,766 | 2,777 | +57% | 0 | 0 | — |
case-05 | pass→pass | 7,763 | 7,449 | -4% | 1 | 1 | 0% | 1,661 | 2,249 | +35% | 0 | 0 | — |
case-06 | pass→pass | 12,626 | 10,057 | -20% | 1 | 1 | 0% | 2,632 | 2,835 | +8% | 0 | 0 | — |
case-07 | pass→pass | 8,562 | 9,544 | +11% | 1 | 1 | 0% | 1,825 | 2,786 | +53% | 0 | 0 | — |
case-08 | pass→pass | 10,658 | 11,103 | +4% | 1 | 1 | 0% | 2,193 | 2,817 | +28% | 0 | 0 | — |
case-09 | pass→pass | 10,236 | 10,200 | -0% | 1 | 1 | 0% | 2,202 | 2,820 | +28% | 0 | 0 | — |
case-10 | pass→pass | 12,418 | 12,441 | +0% | 1 | 1 | 0% | 2,557 | 3,150 | +23% | 0 | 0 | — |
case-12 | pass→pass | 6,393 | 8,934 | +40% | 1 | 1 | 0% | 1,305 | 2,639 | +102% | 0 | 0 | — |
case-13 | fail→pass | 8,491 | 9,434 | +11% | 1 | 1 | 0% | 1,762 | 2,563 | +45% | 0 | 0 | — |
case-14 | pass→pass | 10,734 | 11,854 | +10% | 1 | 1 | 0% | 2,274 | 3,311 | +46% | 0 | 0 | — |
case-15 | pass→pass | 7,339 | 11,735 | +60% | 1 | 1 | 0% | 1,663 | 3,218 | +94% | 0 | 0 | — |
case-16 | fail→fail | 4,852 | 4,633 | -5% | 1 | 1 | 0% | 1,150 | 1,561 | +36% | 0 | 0 | — |
case-17 | fail→pass | 13,100 | 12,755 | -3% | 1 | 1 | 0% | 2,778 | 3,353 | +21% | 0 | 0 | — |
case-18 | fail→fail | 8,414 | 10,847 | +29% | 1 | 1 | 0% | 1,788 | 2,827 | +58% | 0 | 0 | — |
case-19 | fail→pass | 5,619 | 5,318 | -5% | 1 | 1 | 0% | 1,193 | 1,789 | +50% | 0 | 0 | — |
case-20 | pass→pass | 2,348 | 2,064 | -12% | 1 | 1 | 0% | 422 | 970 | +130% | 0 | 0 | — |
case-21 | fail→fail | 2,700 | 2,479 | -8% | 1 | 1 | 0% | 481 | 974 | +102% | 0 | 0 | — |
case-22 | pass→pass | 2,418 | 2,352 | -3% | 1 | 1 | 0% | 416 | 931 | +124% | 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 +18 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.