boof
par chiefsegundo
Search & ResearchRésumé
Convert PDFs and documents to markdown, index them locally for RAG retrieval, and analyze them token-efficiently.
Description
Ce que fait ce skill
Converts PDFs and documents to markdown using local ML (Marker), then indexes them into a semantic search store for retrieval-augmented analysis. Only relevant chunks are sent to the LLM instead of the full document. Supports batch processing and cross-document queries within a single collection.
Sending the full document to an LLM wastes tokens and causes lost-in-the-middle degradation; this retrieves only the semantically relevant excerpts while keeping everything local.
Quand l'utiliser
- Extracting key findings from a research paper without loading it in full
- Searching a grant proposal or NOFO for specific eligibility requirements
- Summarizing a long technical deck section by section
- Finding where a contract or policy document mentions a particular clause
- Comparing methodology or results across multiple academic papers
Exemple de workflow
User asks: Summarize the findings section of this 80-page research PDF
- 1
Run boof.sh on the PDF to convert it to markdown and index it locally
- 2
Use qmd query to retrieve chunks related to findings and results
- 3
Summarize each retrieved section individually
- 4
Merge section summaries into a consolidated final summary
A structured summary of the paper's findings drawn from indexed excerpts, without loading the full document into context
Prérequis
- Marker (local ML PDF-to-markdown tool, see setup-guide.md)
- QMD binary (semantic search and indexing tool, see setup-guide.md)
Installation
clawhub install chiefsegundo/boofExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.