Convert unstructured inputs into RAG-ready Markdown documents with YAML metadata.
npx skills add https://github.com/joleques/northstar-ai --skill documentador-rag
Please help me install this Agent Skill. Skill: documentador-rag Source: https://github.com/joleques/northstar-ai/tree/main/.codex/skills/documentador Command: npx skills add https://github.com/joleques/northstar-ai --skill documentador-rag
Converts heterogeneous, unstructured inputs into deterministic, canonical Markdown documents explicitly prepared for vector-database ingestion and semantic chunking. It enforces fidelity to the original input, prevents undocumented summarization, and structures content so downstream pipelines can reliably separate theoretical and practical chunks.
Teoria and Pratica so each chunk's role is explicit for retrieval and pipeline processing.Use the documentador-rag skill to convert meeting-audio.mp3 into a deterministic Markdown document with required YAML metadata, separated theory and practice sections, and Summary blocks suitable for semantic chunking.
High-intent search queries and answers about installing and using this skill.
To convert unstructured meeting transcripts into Markdown for RAG ingestion, this Skill transforms raw inputs into deterministic .md files with YAML metadata and per-section Summary blocks optimized for semantic chunking and vector databases.
Separating theory and practice content for semantic chunking requires structurally marking sections as Teoria and Pratica, ensuring each chunk's role is explicit for retrieval pipelines to process theoretical and practical information independently.
Yes, you can use raw JSON and API specs as inputs for knowledge base document generation. The Skill supports broad input formats including Swagger specs and technical documents to build deterministic RAG corpora.
RAG pipelines retrieve incomplete technical details from summarized documents due to undocumented summarization. This Skill enforces strict fidelity to input content, preserving all technical details without summarization for accurate vector retrieval.
No, you do not need to manually add metadata to Markdown files before vector database ingestion. This Skill automatically produces canonical .md files containing a required YAML metadata block optimized for automated chunking.
To format raw audio transcripts for semantic search, this Skill converts unstructured inputs into hierarchical Markdown documents with per-section Summary blocks suitable for semantic chunking and vector ingestion.
argenIngest unstructured artifacts into a project's chronicle layer.
robertbr123Manage and query vector embeddings with metadata using chromadb.
dandudziDesign and implement RAG pipelines with chunking, embeddings, and vector stores.
jolequesTransform raw product context into RAG-ready Markdown documentation with YAML metadata.