Group documents by content similarity and topic using NLP vectorization and labeling.
npx skills add https://github.com/dandye/ai-runbooks --skill cluster-documents
Please help me install this Agent Skill. Skill: cluster-documents Source: https://github.com/dandye/ai-runbooks/tree/main/skills/cluster-documents Command: npx skills add https://github.com/dandye/ai-runbooks --skill cluster-documents
This skill analyzes a repository of documents to group them by content similarity, topic, or purpose, helping to reduce redundancy and reveal relationships.
Input the path to your document repository and run a clustering pass to produce labeled document groups.
High-intent search queries and answers about installing and using this skill.
To group related documents by content similarity automatically, this Skill applies NLP vectorization and clustering to identify redundancies and relationships, producing labeled document groups based on a configurable similarity threshold.
Organizing a large knowledge base by topic is achieved through automated document clustering, which text-normalizes your repository, groups related content by similarity, and generates meaningful labels for each cluster to speed up retrieval.
NLP clustering generates labels for document groups by vectorizing text content, grouping related documents based on similarity, and deriving meaningful labels for each cluster from the dominant terms within those groups.
You can control how document similarity is calculated during text mining by adjusting the SIMILARITY_THRESHOLD, which dictates the strictness of grouping related documents and impacts the final cluster structure.
Text normalization happens before vectorization for document clustering, ensuring consistent NLP processing by standardizing document content prior to grouping related documents and generating labels.
K-Dense-AIParse FCS files and extract event data as NumPy arrays.
ya-wayA data analysis tool that generates a clustered heatmap from a matrix of expression values, with optional row/column annotations and multiple output formats.
eddieluengCompute image and text embeddings for zero-shot classification and retrieval.
bianhaifeng789-hueTrain FastText supervised text classification models within accuracy and size constraints.
