deep-document-processor
OfficialTurn huge docs into decision-ready context.
Software Engineering#document processing#context engineering#token efficiency#reasoning#information extraction#research synthesis
AuthorAndurilCode
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It compresses large documents into a token-efficient context artifact that preserves decision-relevant structure for downstream agent reasoning, avoiding wasted context budget from full inclusion, naive truncation, or human-oriented summaries.
Core Features & Use Cases
- Four-pass disciplined extraction: builds a structural survey, performs selective extraction under a strict token-compression budget, scans cross-references and conflicts, and assembles a single context artifact for the agent.
- Decision-optimized output: prioritizes constraints, dependencies, counter-intuitive facts, and anything that would change recommendations or outcomes.
- Document scale trigger: targets inputs longer than ~2000 tokens to keep context within limits while maintaining reasoning fidelity.
Quick Start
Use the deep-document-processor skill to process the attached document and produce a maximum-signal, compression-bounded context artifact optimized for agent decision-making.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: deep-document-processor Download link: https://github.com/AndurilCode/craftwork/archive/main.zip#deep-document-processor Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.