skills.rest
botlearn-ai
botlearn-aiOFFICIAL
Explore all skills by this author →
Website𝕏@botlearn_aiGitHub

keyword-extractor

Extract keywords, topics, and domain terms from text into ranked clusters.

9|2|Updated Mar 2, 2026
Search Tags:#embeddings#clustering#keyword-extraction#tf-idf#topic-clustering#ner#domain-taxonomy
One-click install
npx skills add https://github.com/botlearn-ai/botlearn-skills --skill keyword-extractor-botlearn-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: keyword-extractor
Source: https://github.com/botlearn-ai/botlearn-skills/tree/main/skills/keyword-extractor
Command: npx skills add https://github.com/botlearn-ai/botlearn-skills --skill keyword-extractor-botlearn-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates extracting meaningful keywords, entities, and topics from text and maps them to domain taxonomies, enabling richer search, clustering, and contextual understanding.

Core Features & Use Cases

  • Semantic-level keyword extraction (lexical, phrasal, and semantic terms)
  • Topic clustering and domain-aware taxonomy mapping
  • Multi-document and multi-domain input with robust scoring and ranking
  • Use Case: Analyze a multi-document report to produce structured keyword clusters and domain context for indexing and retrieval

Quick Start

Input a text document and return a structured set of keywords, clusters, and domain taxonomy mappings.

Frequently Asked Questions about keyword-extractor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract keywords and map them to a domain taxonomy from text?▼

To extract keywords and map them to a domain taxonomy, you input text documents and the system applies lexical, phrasal, semantic, and NER techniques to return structured, ranked clusters mapped to standard taxonomies for indexing.

Can I use TF-IDF and embeddings for topic clustering across multiple documents?▼

Yes, you can process multi-document inputs for topic clustering using TF-IDF, PMI, and embedding-based similarity to generate ranked keyword clusters and domain context.

What is the best way to identify domain-relevant terms and entities for search indexing?▼

Identifying domain-relevant terms and entities for search indexing is best achieved by combining semantic extraction with NER to produce a structured output mapped to a domain taxonomy.

Does keyword extraction work with multi-domain inputs to produce ranked clusters?▼

Keyword extraction works with multi-domain inputs by applying robust scoring and ranking algorithms across multiple documents to produce structured keyword clusters for retrieval.

How do named entity recognition and PMI improve keyword extraction from text?▼

Named entity recognition and PMI improve keyword extraction by combining lexical analysis with statistical and semantic similarity to accurately identify and rank meaningful topics from text.

Related Skills

Explore More Data & Analytics Skills→
x402agentx402agent
9

pdf-to-markdown

Convert PDF documents into structured Markdown with PyMuPDF and DocLing.

Community
Intermediate
duanbiao2000duanbiao2000
3

hybrid-search-implementation

Combine vector similarity with keyword search using RRF or linear fusion.

Community
Advanced
qcmuuqcmuu

sentence-transformers

Generate semantic embeddings from text using sentence-transformers models.

Community
Intermediate
fabioeloifabioeloi
5

PRD Parser

Parse PRD Markdown documents into semantic structures and dependency graphs.

Community
Intermediate