text-summarizer
Summarizes long text into key bullet points
When & Why to Use This Skill
The Text Summarizer skill is a high-performance NLP tool designed to distill lengthy documents into concise, actionable bullet points. By combining structural text analysis with key point extraction, it enables users to rapidly digest complex information while providing valuable readability statistics like word counts and sentence density for deeper content insights.
Use Cases
- Academic & Market Research: Quickly extract core findings and essential arguments from long-form research papers, journals, or industry reports.
- Business Intelligence: Transform lengthy meeting transcripts, internal memos, or project updates into clear, executive-level summaries.
- Content Strategy: Generate brief summaries and meta-descriptions for blog posts, articles, and newsletters to enhance reader engagement.
- Document Auditing: Use the built-in statistics report to analyze the complexity and length of technical documentation or legal drafts.
| name | stats |
|---|---|
| version | 1.0.0 |
| entrypoint | scripts/main.py |
| description | Statistics about the text |
| - type | object |
| optional | true |
| tags | [nlp, summarization, text, processing] |
| allow_network | false |
| timeout_seconds | 30 |
Text Summarizer Skill
A more complex example that demonstrates text processing capabilities.
What it does
This skill takes a long piece of text and:
- Analyzes the text (word count, sentence count, etc.)
- Extracts key points
- Creates a bullet-point summary
- Generates a statistics report
Usage
Input
{
"text": "Your long text here...",
"max_points": 5
}
Output
{
"summary": "• Point 1\n• Point 2\n• Point 3",
"stats": {
"word_count": 150,
"sentence_count": 8,
"avg_sentence_length": 18.75
}
}
Artifacts
summary.md: Markdown file with the formatted summarystats.json: JSON file with detailed statistics
Algorithm
This is a simple implementation that:
- Splits text into sentences
- Scores sentences by length and position
- Selects top N sentences as summary points
Note: This is a demonstration. For production use, consider using NLP libraries like spaCy or transformers.