bmad-distillator

Compress textual documents into token-efficient summaries for LLM consumption.

1|Updated May 31, 2026

Search Tags:#compression #document analysis #knowledge summarization #document distillation #LLM input prep

Ready to run

npx skills add https://github.com/sfines/slf-llm-wiki-py --skill bmad-distillator-sfines

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bmad-distillator
Source: https://github.com/sfines/slf-llm-wiki-py/tree/main/.agents/skills/bmad-distillator
Command: npx skills add https://github.com/sfines/slf-llm-wiki-py --skill bmad-distillator-sfines

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bmad, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the creation of compact, accurate, and complete summaries from knowledge documents, streamlining access for downstream AI workloads and saving users from time-consuming manual summary tasks.

Core Features & Use Cases

Document Distillation: Transform detailed source documents into a lossless, token-efficient summary while preserving key details.
Automatic Routing and Compression: Based on content analysis, route to optimal processing steps and perform language-level compression for LLM workflows.
Customization Options: Provide inputs such as desired distillate size or specific sections for inclusion, enabling flexibility for various needs.

Quick Start

Activate the bmad-distillator skill with 'distill documents: <file_path>' and let it do its job.

Frequently Asked Questions about bmad-distillator

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

FAQPage Schema

How do I compress knowledge documents for LLM input preparation?▼

Document distillation for LLM consumption compresses textual documents by applying intelligent deduplication, thematic grouping, and language-level compression to minimize source tokens while preserving context without loss.

Can I customize the summary size when distilling documents for LLM workflows?▼

Yes, document distillation allows customization options where you provide inputs such as the desired distillate size or specify particular sections for inclusion, enabling flexibility to match various LLM workflow requirements.

How does automatic routing work during document analysis and compression?▼

Automatic routing during document analysis evaluates the content and dynamically directs it to optimal processing steps. This ensures the language-level compression and deduplication mechanisms are applied efficiently for LLM workflows.

Do I need the bmad dependency to run document distillation?▼

Yes, the bmad framework is a required dependency to run this document distillation process. You must have the bmad environment configured to execute the automatic routing and compression scripts.

What is the best way to prepare large textual documents for AI workloads without losing context?▼

The best way to prepare large textual documents for AI workloads is through lossless document distillation, which applies thematic grouping and deduplication to compress source information while strictly preserving key details and context.