Initial commit

.claude-plugin/plugin.json

@@ -0,0 +1,15 @@
+{
+  "name": "sentiment-analysis-tool",
+  "description": "Sentiment analysis on text data",
+  "version": "1.0.0",
+  "author": {
+    "name": "Claude Code Plugins",
+    "email": "[email protected]"
+  },
+  "skills": [
+    "./skills"
+  ],
+  "commands": [
+    "./commands"
+  ]
+}

README.md

@@ -0,0 +1,3 @@
+# sentiment-analysis-tool
+
+Sentiment analysis on text data

commands/analyze-sentiment.md

@@ -0,0 +1,15 @@
+---
+description: Execute AI/ML task with intelligent automation
+---
+
+# AI/ML Task Executor
+
+You are an AI/ML specialist. When this command is invoked:
+
+1. Analyze the current context and requirements
+2. Generate appropriate code for the ML task
+3. Include data validation and error handling
+4. Provide performance metrics and insights
+5. Save artifacts and generate documentation
+
+Support modern ML frameworks and best practices.

plugin.lock.json

@@ -0,0 +1,65 @@
+{
+  "$schema": "internal://schemas/plugin.lock.v1.json",
+  "pluginId": "gh:jeremylongshore/claude-code-plugins-plus:plugins/ai-ml/sentiment-analysis-tool",
+  "normalized": {
+    "repo": null,
+    "ref": "refs/tags/v20251128.0",
+    "commit": "4f2e24bf3f21cb9304b6753ee21951ee09d64bda",
+    "treeHash": "a0511720cbec522e3ff017f146222fba081c64b99a968d4a5227eb93b28f0f0d",
+    "generatedAt": "2025-11-28T10:18:44.999697Z",
+    "toolVersion": "publish_plugins.py@0.2.0"
+  },
+  "origin": {
+    "remote": "git@github.com:zhongweili/42plugin-data.git",
+    "branch": "master",
+    "commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390",
+    "repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data"
+  },
+  "manifest": {
+    "name": "sentiment-analysis-tool",
+    "description": "Sentiment analysis on text data",
+    "version": "1.0.0"
+  },
+  "content": {
+    "files": [
+      {
+        "path": "README.md",
+        "sha256": "0de2a536b702d5f455d5cc74edfde631f3d027fa5754ddcbaabdf46b95787498"
+      },
+      {
+        "path": ".claude-plugin/plugin.json",
+        "sha256": "5902aeb2259573bd02c4ddaebbdfa688b7751e341d58f7a4ebdc169438560a8b"
+      },
+      {
+        "path": "commands/analyze-sentiment.md",
+        "sha256": "043efb83e2f02fc6d0869c8a3a7388d6e49f6c809292b93dd6a97a1b142e5647"
+      },
+      {
+        "path": "skills/sentiment-analysis-tool/SKILL.md",
+        "sha256": "ebcdbd56fb7f88f873c7edb6cb6da95381f0f85101580e72fea18cad63b5f263"
+      },
+      {
+        "path": "skills/sentiment-analysis-tool/references/README.md",
+        "sha256": "ef6791725c663d0e011a794e14b432802f8d35dad318837c37a92f9d6aa31d9d"
+      },
+      {
+        "path": "skills/sentiment-analysis-tool/scripts/README.md",
+        "sha256": "fe4c0667f578fbe02674b1a663434f52f3c7477b5876a09242141fd7073fd4e0"
+      },
+      {
+        "path": "skills/sentiment-analysis-tool/assets/sentiment_analysis_report_template.md",
+        "sha256": "01caa8acd31808c35c3f23a13a5c34ba85e034db5175c3563e32e93856064f70"
+      },
+      {
+        "path": "skills/sentiment-analysis-tool/assets/README.md",
+        "sha256": "73dc5a0f5eb652779ed46638ffc490909fec969039b75f829425ee1440319228"
+      }
+    ],
+    "dirSha256": "a0511720cbec522e3ff017f146222fba081c64b99a968d4a5227eb93b28f0f0d"
+  },
+  "security": {
+    "scannedAt": null,
+    "scannerVersion": null,
+    "flags": []
+  }
+}

skills/sentiment-analysis-tool/SKILL.md

@@ -0,0 +1,53 @@
+---
+name: analyzing-text-sentiment
+description: |
+  This skill enables Claude 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 emotion detection on any text, such as customer reviews, social media posts, or survey responses. Trigger words include "sentiment analysis", "analyze sentiment", "opinion mining", "emotion detection", and "polarity".
+allowed-tools: Read, Write, Bash, Grep
+version: 1.0.0
+---
+
+## Overview
+
+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.
+
+## How It Works
+
+1. **Text Input**: The skill receives text data as input from the user.
+2. **Sentiment Analysis**: The skill processes the text using a pre-trained sentiment analysis model to determine the sentiment polarity (positive, negative, or neutral).
+3. **Result Output**: The skill provides a sentiment score and classification, indicating the overall sentiment expressed in the text.
+
+## When to Use This Skill
+
+This skill activates when you need to:
+- Determine the overall sentiment of customer reviews.
+- Analyze the emotional tone of social media posts.
+- Gauge public opinion on a particular topic.
+- Identify positive and negative feedback in survey responses.
+
+## Examples
+
+### Example 1: Analyzing Customer Reviews
+
+User request: "Analyze the sentiment of these customer reviews: 'The product is amazing!', 'The service was terrible.', 'It was okay.'"
+
+The skill will:
+1. Process the provided customer reviews.
+2. Classify each review as positive, negative, or neutral and provide sentiment scores.
+
+### Example 2: Monitoring Social Media Sentiment
+
+User request: "Perform sentiment analysis on the following tweet: 'I love this new feature!'"
+
+The skill will:
+1. Analyze the provided tweet.
+2. Identify the sentiment as positive and provide a corresponding sentiment score.
+
+## Best Practices
+
+- **Data Quality**: Ensure the input text is clear and free from ambiguous language for accurate sentiment analysis.
+- **Context Awareness**: Consider the context of the text when interpreting sentiment scores, as sarcasm or irony can affect results.
+- **Model Selection**: Use appropriate sentiment analysis models based on the type of text being analyzed (e.g., social media, customer reviews).
+
+## Integration
+
+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).

skills/sentiment-analysis-tool/assets/README.md

@@ -0,0 +1,6 @@
+# Assets
+
+Bundled resources for sentiment-analysis-tool skill
+
+- [ ] example_reviews.json: A collection of example customer reviews with their corresponding sentiment labels (positive, negative, neutral).
+- [ ] sentiment_analysis_report_template.md: A template for generating a sentiment analysis report, including sections for data overview, methodology, results, and conclusions.

skills/sentiment-analysis-tool/assets/sentiment_analysis_report_template.md

@@ -0,0 +1,76 @@
+# Sentiment Analysis Report
+
+**Generated by the sentiment-analysis-tool Plugin**
+
+## 1. Introduction
+
+This report presents the findings of a sentiment analysis performed on [Specify the text data source, e.g., customer reviews, social media posts, survey responses]. The analysis aims to identify and quantify the overall sentiment expressed in the text data, providing insights into [Specify the purpose of the analysis, e.g., customer satisfaction, brand perception, public opinion].
+
+## 2. Data Overview
+
+### 2.1. Data Source
+
+*   **Source:** [Specify the source of the text data, e.g., Amazon product reviews, Twitter API, internal survey data].
+*   **Collection Method:** [Describe how the data was collected, e.g., web scraping, API extraction, database query].
+*   **Time Period:** [Specify the time period covered by the data, e.g., January 1, 2023 - December 31, 2023].
+*   **Data Volume:** [Specify the number of text entries analyzed, e.g., 10,000 reviews].
+
+### 2.2. Data Preprocessing
+
+*   **Preprocessing Steps:** [Describe the preprocessing steps applied to the data, e.g., removal of punctuation, lowercasing, stemming/lemmatization, stop word removal].
+    *   Example: "The text data was preprocessed by removing punctuation, converting all text to lowercase, and removing common stop words such as 'the,' 'a,' and 'is'."
+
+## 3. Methodology
+
+### 3.1. Sentiment Analysis Technique
+
+*   **Technique Used:** [Specify the sentiment analysis technique used, e.g., lexicon-based approach, machine learning model (specify the model, e.g., Naive Bayes, Support Vector Machine, transformer model)].
+    *   Example: "We employed a lexicon-based approach using the VADER (Valence Aware Dictionary and sEntiment Reasoner) lexicon, which assigns sentiment scores based on the valence of individual words and phrases."
+*   **Justification for Choice:** [Explain why this technique was chosen, e.g., computational efficiency, accuracy, suitability for the data].
+    *   Example: "VADER was chosen for its speed and effectiveness in analyzing sentiment in social media text, particularly for handling slang and emoticons."
+
+### 3.2. Sentiment Scoring
+
+*   **Sentiment Scale:** [Describe the scale used to quantify sentiment, e.g., positive, negative, neutral; or a numerical scale (e.g., -1 to +1)].
+    *   Example: "Sentiment was scored on a scale of -1 (negative) to +1 (positive), with 0 indicating a neutral sentiment."
+*   **Thresholds:** [Define the thresholds used to classify sentiment into different categories, if applicable].
+    *   Example: "Scores between -1 and -0.2 were classified as negative, scores between -0.2 and 0.2 were classified as neutral, and scores between 0.2 and 1 were classified as positive."
+
+## 4. Results
+
+### 4.1. Overall Sentiment Distribution
+
+*   **Positive Sentiment Percentage:** [Insert percentage of text entries classified as positive].
+*   **Negative Sentiment Percentage:** [Insert percentage of text entries classified as negative].
+*   **Neutral Sentiment Percentage:** [Insert percentage of text entries classified as neutral].
+*   **Visualization (Optional):** [Include a chart or graph illustrating the sentiment distribution, e.g., a pie chart or bar graph].
+
+### 4.2. Key Sentiment Drivers
+
+*   **Positive Keywords/Phrases:** [List the most frequently occurring keywords or phrases associated with positive sentiment].
+    *   Example: "Keywords associated with positive sentiment include 'excellent,' 'amazing,' 'highly recommend,' and 'great value'."
+*   **Negative Keywords/Phrases:** [List the most frequently occurring keywords or phrases associated with negative sentiment].
+    *   Example: "Keywords associated with negative sentiment include 'disappointed,' 'terrible,' 'poor quality,' and 'slow delivery'."
+*   **Examples of Positive Sentiments:** [Provide examples of text entries classified as positive].
+*   **Examples of Negative Sentiments:** [Provide examples of text entries classified as negative].
+
+### 4.3. Sentiment Trends (Optional)
+
+*   [If applicable, analyze sentiment trends over time, e.g., changes in sentiment scores over a period of weeks or months].
+*   [Include a chart or graph illustrating sentiment trends].
+
+## 5. Conclusion
+
+The sentiment analysis reveals that [Summarize the overall sentiment and its implications, e.g., "the majority of customer reviews express positive sentiment towards the product, indicating high customer satisfaction"]. Key findings include [Highlight the most important findings, e.g., "the positive sentiment is primarily driven by the product's ease of use and excellent customer service, while negative sentiment is associated with issues related to delivery times"]. These insights can be used to [Suggest actionable steps based on the findings, e.g., "focus on maintaining the high level of customer service and addressing the delivery time issues to further improve customer satisfaction"].
+
+## 6. Limitations
+
+*   [Describe any limitations of the analysis, e.g., potential bias in the data, limitations of the sentiment analysis technique].
+    *   Example: "The analysis is limited by the potential bias in the data, as customers with strong opinions are more likely to leave reviews. Furthermore, the lexicon-based approach may not accurately capture nuanced sentiment expressions."
+
+## 7. Recommendations
+
+*   [Provide recommendations for future analysis or actions based on the findings and limitations].
+    *   Example: "We recommend conducting further analysis using a machine learning model trained on a domain-specific dataset to improve accuracy. Additionally, gathering more balanced data from different sources would help mitigate potential bias."
+
+---

skills/sentiment-analysis-tool/references/README.md

@@ -0,0 +1,7 @@
+# References
+
+Bundled resources for sentiment-analysis-tool skill
+
+- [ ] sentiment_analysis_api.md: Documentation for the sentiment analysis API used by the tool, including input parameters, output format, and error handling.
+- [ ] sentiment_analysis_best_practices.md: A guide on best practices for using sentiment analysis, including data preprocessing, handling biases, and interpreting results.
+- [ ] sentiment_lexicon.md: A detailed lexicon of words and their associated sentiment scores, providing Claude with a reference for understanding sentiment analysis.

skills/sentiment-analysis-tool/scripts/README.md

@@ -0,0 +1,6 @@
+# Scripts
+
+Bundled resources for sentiment-analysis-tool skill
+
+- [ ] analyze_sentiment.py: Script to perform sentiment analysis on a given text input. This would allow Claude to execute the analysis directly.
+- [ ] example_usage.py: Script to demonstrate how to use the sentiment analysis tool with different text inputs and expected outputs.