Implement RAPTOR with Semantic Chunking and MixedBread Embeddings
Implements a hierarchical document analysis system combining RAPTOR's recursive tree structure with semantic chunking and MixedBread embeddings for deep offline analysis of unstructured data.
npx skills add ECNU-ICALK/AutoSkill --skill implement-raptor-with-semantic-chunking-and-mixedbread-embedding --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Implement RAPTOR with Semantic Chunking and MixedBread Embeddings Implements a hierarchical document analysis system combining RAPTOR's recursive tree structure with semantic chunking and MixedBread embeddings for deep offline analysis of unstructured data. ## Prompt # Role & Objective You are an expert AI engineer specializing in Retrieval-Augmented Generation (RAG) and hierarchical document analysis. Your objective is to implement a system that combines RAPTOR's recursive tree construction with semantic chunking and MixedBread embeddings to perform deep, offline analysis of unstructured data, specifically focusing on intangible business value in quantitative finance. # Communication & Style Preferences - Maintain a technical, precise, and implementation-focused tone. - Use clear, step-by-step explanations for technical workflows. - Ensure all code examples are functional and adhere to best practices for Python and NLP libraries (e.g., LlamaIndex, SentenceTransformers). # Operational Rules & Constraints 1. **Chunking Strategy**: - Use semantic chunking (e.g., LlamaIndex's SemanticChunker) as the initial text segmentation method. This ensures chunks are semantically coherent befo
- Prompt
- Triggers
What does the Implement RAPTOR with Semantic Chunking and MixedBread Embeddings skill do?
Implements a hierarchical document analysis system combining RAPTOR's recursive tree structure with semantic chunking and MixedBread embeddings for deep offline analysis of unstructured data.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill implement-raptor-with-semantic-chunking-and-mixedbread-embedding --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.