invisible-threads

Chunk documents, extract LLM insights, and cluster them into thematic threads.

9|2|Updated Feb 4, 2026

Search Tags:#content discovery #LLM #text analysis #topic modeling #thematic analysis #insight extraction

Ready to run

npx skills add https://github.com/cdeistopened/content-os --skill invisible-threads

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: invisible-threads
Source: https://github.com/cdeistopened/content-os/tree/main/skills/writing/invisible-threads
Command: npx skills add https://github.com/cdeistopened/content-os --skill invisible-threads

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-generativeai, sentence-transformers, networkx, python-louvain, scikit-learn, anthropic, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you discover non-obvious thematic connections and recurring ideas across a large collection of documents, transforming raw text into structured insights.

Core Features & Use Cases

Thematic Discovery: Identifies underlying themes and patterns within essays, articles, or transcripts.
Insight Extraction: Extracts quotable and specific insights, scoring them for novelty and specificity.
Use Case: When editing an anthology, use this Skill to find thematic links between different authors' works, enabling you to write more cohesive introductions or commentary.

Quick Start

Process your corpus of markdown files into a database, then extract and analyze insights to find thematic threads.

Frequently Asked Questions about invisible-threads

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

FAQPage Schema

How do I discover hidden themes across a large collection of documents?▼

Thematic analysis of a large text corpus works by chunking documents, extracting insights via an LLM, and clustering them into thematic threads. This process transforms raw text into structured insights by identifying underlying patterns and recurring ideas.

Can I use Claude or Gemini for text analysis and insight extraction?▼

Yes, Claude, Gemini, and Ollama are supported LLM backends for insight extraction. This allows flexible deployment options when processing your document corpus to score and extract quotable insights for novelty and specificity.

What is the best way to find thematic links between different authors' essays?▼

The best way to find thematic links between authors' essays is to process markdown files into a database, extract insights, and cluster them into threads. This reveals non-obvious thematic connections, enabling you to write cohesive commentary across an anthology.

What file formats do I need for topic modeling with this text analysis approach?▼

You need a corpus of markdown files for topic modeling. The Skill processes these markdown documents into a database before extracting and analyzing insights to find thematic threads across your text data.

Does this thematic analysis approach work with local LLMs?▼

Yes, thematic analysis works with local LLMs by supporting Ollama as a backend alongside Gemini and Claude. This enables flexible deployment to extract insights and cluster thematic threads without relying solely on external API providers.