What models does this skill use?

It uses transformer models to analyze sentiment. For lighter CPU-only setups you can install alternatives like textblob or vaderSentiment.

Can I customize sentiment definitions?

Yes. You define the metrics, thresholds and business interpretation; the skill handles the analysis framework and scoring.

What are the system requirements?

Depends on your setup. Using transformers/torch requires Python and the listed libraries; a CPU-only option is available via textblob or vaderSentiment.

sentiment-analyzer

npx machina-cli add skill guia-matthieu/clawfu-skills/sentiment-analyzer --openclaw

Files (1)

SKILL.md

3.6 KB

Sentiment Analyzer

Analyze sentiment in customer feedback using transformer models - understand what your customers really feel at scale.

When to Use This Skill

Review analysis - Process hundreds of product reviews
NPS feedback - Categorize open-ended survey responses
Social listening - Monitor brand sentiment on social media
Campaign feedback - Evaluate response to marketing campaigns
Support insights - Categorize support ticket sentiment

What Claude Does vs What You Decide

Claude Does	You Decide
Structures analysis frameworks	Metric definitions
Identifies patterns in data	Business interpretation
Creates visualization templates	Dashboard design
Suggests optimization areas	Action priorities
Calculates statistical measures	Decision thresholds

Dependencies

pip install transformers torch pandas click
# Or for lighter CPU-only version:
pip install textblob vaderSentiment pandas click

Commands

Analyze Text

python scripts/main.py analyze "This product exceeded my expectations!"
python scripts/main.py analyze "The service was terrible and slow."

Batch Analysis

python scripts/main.py batch reviews.csv --column text
python scripts/main.py batch feedback.csv --column comment --output results.csv

Generate Report

python scripts/main.py report reviews.csv --column text --output sentiment-report.html

Examples

Example 1: Analyze Product Reviews

# Process CSV of reviews
python scripts/main.py batch amazon-reviews.csv --column review_text

# Output: amazon-reviews_sentiment.csv
# review_text                    | sentiment | score  | label
# "Absolutely love this!"        | positive  | 0.95   | Very Positive
# "It's okay, nothing special"   | neutral   | 0.52   | Neutral
# "Worst purchase ever"          | negative  | 0.12   | Very Negative

Example 2: NPS Feedback Categorization

# Analyze NPS survey responses
python scripts/main.py report nps-responses.csv --column feedback

# Output: sentiment-report.html
# Summary:
# - Positive: 62% (mainly: product quality, support)
# - Neutral: 23% (mainly: pricing concerns)
# - Negative: 15% (mainly: shipping delays)

Sentiment Categories

Score Range	Label	Interpretation
0.8 - 1.0	Very Positive	Enthusiastic, recommend
0.6 - 0.8	Positive	Satisfied, happy
0.4 - 0.6	Neutral	Mixed or indifferent
0.2 - 0.4	Negative	Disappointed, frustrated
0.0 - 0.2	Very Negative	Angry, will churn

Skill Boundaries

What This Skill Does Well

Structuring data analysis
Identifying patterns and trends
Creating visualization frameworks
Calculating statistical measures

What This Skill Cannot Do

Access your actual data
Replace statistical expertise
Make business decisions
Guarantee prediction accuracy

Related Skills

social-analytics - Get social data to analyze
content-repurposer - Use insights for content

Skill Metadata

Mode: centaur

category: analytics
subcategory: nlp
dependencies: [transformers, torch, pandas]
difficulty: intermediate
time_saved: 6+ hours/week

Source

git clone https://github.com/guia-matthieu/clawfu-skills/blob/main/skills/analytics/sentiment-analyzer/SKILL.mdView on GitHub

Overview

Sentiment Analyzer uses transformer models to gauge customer sentiment at scale. It helps analyze reviews, NPS feedback, social mentions, campaign responses, and support tickets to turn text into actionable sentiment signals.

How This Skill Works

The skill leverages transformer-based models to assign sentiment scores and labels. It supports batch analysis and report generation, with commands to analyze text, batch process files, and generate HTML reports.

When to Use It

Review analysis (process hundreds of product reviews)
NPS feedback categorization (categorize open-ended survey responses)
Social listening (monitor brand sentiment on social media)
Campaign feedback evaluation (evaluate response to marketing campaigns)
Support insights (categorize support ticket sentiment)

Quick Start

Step 1: Install dependencies (pip install transformers torch pandas click)
Step 2: Run a quick analyze (python scripts/main.py analyze 'This product is amazing')
Step 3: Generate a report or batch (python scripts/main.py batch reviews.csv --column text)

Best Practices

Define clear sentiment labels and score thresholds
Use labeled validation data to calibrate scores
Segment data by domain (e.g., reviews vs. support tickets)
Monitor drift and revalidate periodically
Combine sentiment with topic or intent signals for actionability

Example Use Cases

Analyze Product Reviews: Process a CSV of reviews to surface sentiment and scores per item
NPS Feedback Categorization: Classify open-ended survey comments into sentiment buckets
Social Listening: Track and compare brand sentiment across social media mentions
Campaign Feedback: Assess customer reactions to a recent marketing campaign
Support Insights: Prioritize tickets by sentiment to frontload critical issues

Frequently Asked Questions

Add this skill to your agents