Sentiment Analysis

This is a straightforward sentiment analysis prompt from aj-geddes's useful-ai-prompts collection. It covers the main approaches you'd expect: lexicon-based, machine learning, deep learning, aspect-based, and multilingual analysis. The skill walks through different sentiment types and gives you a framework for analyzing emotional tone in text, whether you're parsing customer feedback, social media, or support tickets. It's comprehensive enough to handle various use cases but light on implementation details, so you'll need to adapt the prompts to your specific context. The repo has 245 stars and passed security audits from Gen Agent Trust Hub, Socket, and Snyk. Good starting point if you need sentiment analysis added to your agent without building the prompt structure from scratch.

GitHub stars: 317
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aj-geddes/useful-ai-prompts --skill 'Sentiment Analysis' --agent claude-code

Installs into .claude/skills of the current project.

Files

Sentiment Analysis

Overview

Sentiment analysis determines emotional tone and opinions in text, enabling understanding of customer satisfaction, brand perception, and feedback analysis.

Approaches

Lexicon-based: Using sentiment dictionaries
Machine Learning: Training classifiers on labeled data
Deep Learning: Neural networks for complex patterns
Aspect-based: Sentiment about specific features
Multilingual: Non-English text analysis

Sentiment Types

Positive: Favorable, satisfied
Negative: Unfavorable, dissatisfied
Neutral: Factual, no clear sentiment
Mixed: Combination of sentiments

Implementation with Python

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
import re
from collections import Counter

SKILL.md on GitHub