bmad-distillator

Name: bmad-distillator
Availability: InStock
Author: enigmaicon-eng

Generate lossless LLM-optimized document distillates preserving facts and relationships.

1|Updated May 16, 2026

Search Tags:#information extraction #token budgeting #LLM context #document distillation #semantic splitting #round-trip validation #lossless compression

Ready to run

npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill bmad-distillator-enigmaicon-eng

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bmad-distillator
Source: https://github.com/enigmaicon-eng/AI-Enterprise-OS/tree/main/examples/BMAD-METHOD/src/core-skills/bmad-distillator
Command: npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill bmad-distillator-enigmaicon-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the problem of getting large sets of source documents into an LLM workflow without losing important facts by producing a lossless, token-efficient “distillate” that preserves every decision, constraint, relationship, and fact from the originals.

Core Features & Use Cases

Lossless document compression: Produces an LLM-optimized distillate that is not a lossy summary.
Routing and semantic splitting: Chooses single vs fan-out compression and splits into self-contained sections when outputs get too large for one context.
Completeness verification: Runs a completeness check to ensure extracted headings/entities appear in the final distillate, with targeted fix passes.
Optional round-trip validation: When requested, reconstructs originals from the distillate using a reconstructor and generates a validation report.

Quick Start

Use the bmad-distillator skill to create a distillate from the file paths you provide as source_documents.

Frequently Asked Questions about bmad-distillator

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

FAQPage Schema

How do I compress large documents for LLM context without losing important facts?▼

Document distillation for LLM context compresses source files into a lossless, token-efficient distillate that preserves every decision, constraint, and relationship. This avoids lossy summaries while fitting your token budget for downstream workflows.

What is semantic splitting and when do I need it for token budgeting?▼

Semantic splitting divides large documents into self-contained sections to improve retrieval granularity and fit strict token budgets. You need it when a single compressed output is too large for one LLM context window.

How do I verify that my document distillation captured all the original information?▼

To verify document distillation completeness, you can run a completeness check to ensure extracted headings and entities appear in the final distillate. Optional round-trip validation also reconstructs originals from the distillate to generate a validation report.

Do I need Python to run lossless document compression workflows?▼

Yes, Python3 is required as a dependency to run the routing scripts and generate the structured JSON distillates. The workflow uses these scripts to analyze sources and enforce formatting rules.

What is the best way to process multiple related documents into a single LLM-ready context?▼

The best way to process multiple related documents is using fan-out routing compression, which analyzes your sources and generates a unified, structured JSON distillate. This ensures all facts and relationships are preserved for downstream LLM consumption.

Are there limitations to reconstructing original documents from a compressed distillate?▼

A limitation of round-trip validation is that reconstructing original documents from the distillate happens without accessing the originals. This tests semantic completeness but does not produce a byte-for-byte identical copy of the source files.