bmad-distillator

Distill source documents into a lossless, sectioned distillate for LLM contexts.

Updated Nov 6, 2025
One-click install
npx skills add https://github.com/skyoxu/godotgame --skill bmad-distillator-skyoxu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-distillator
Source: https://github.com/skyoxu/godotgame/tree/main/.agents/skills/bmad-distillator
Command: npx skills add https://github.com/skyoxu/godotgame --skill bmad-distillator-skyoxu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Distillator provides lossless compression of source documents into a single, token-efficient distillate, preserving all facts, decisions, constraints, and relationships for downstream LLM workflows.

Core Features & Use Cases

  • Lossless distillation of multiple documents into a compact, token-efficient format suitable for context-limited LLMs
  • Supports semantic splitting into sectional distillates with orientation and cross-references
  • Useful for PRD-like workflows, architecture reviews, and knowledge baselining across documents

Quick Start

Distill a set of source documents into a single lossless distillate optimized for downstream LLM workflows.

Frequently Asked Questions about bmad-distillator

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

FAQPage Schema
How do I compress multiple documents for an LLM context window without losing facts?▼

Lossless document distillation compresses multiple source documents into a single, token-efficient distillate that preserves all facts, decisions, constraints, and relationships for downstream LLM contexts.

What is lossless distillation for LLM workflows?▼

Lossless distillation is a compression technique that consolidates multiple input documents into a compact, token-efficient format while strictly preserving all original facts, decisions, constraints, and relationships.

How do I distill source documents into a token-efficient format step by step?▼

Provide source_documents, downstream_consumer, token_budget, and output_path to distill inputs into a portable distillate with frontmatter and sectioned content, optionally enabling validation with the --validate flag.

Can I split a compact distillate into sections for better LLM context orientation?▼

Yes, lossless distillation supports semantic splitting into sectional distillates complete with orientation and cross-references, ensuring structured navigation for downstream LLM consumers.

Does lossless document compression work for knowledge baselining and architecture reviews?▼

Yes, lossless distillation is specifically useful for PRD-like workflows, architecture reviews, and knowledge baselining across multiple documents while maintaining a strict token budget for LLMs.