reduce

Extract structured domain knowledge into classified vault notes.

Updated Jan 8, 2026

Search Tags:#documentation #vault #cross-linking #enrichment #knowledge-extraction #notes-management #domain-insights

Ready to run

npx skills add https://github.com/lightningfastsls/London_Lab --skill reduce-lightningfastsls

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: reduce
Source: https://github.com/lightningfastsls/London_Lab/tree/main/.claude/skills/reduce
Command: npx skills add https://github.com/lightningfastsls/London_Lab --skill reduce-lightningfastsls

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract insights", "mine this", "process this".

Core Features & Use Cases

Comprehensive extraction: convert raw sources into atomic, domain-relevant notes covering core claims, patterns, tensions, validations, enrichments, and open questions.
Enrichment and cross-linking: identify related notes and create enrichment tasks when a source adds depth, evidence, or new examples.
OPEN/CLOSED classifications: tag extractions as OPEN or CLOSED to guide follow-up work and integration.

Quick Start

Provide a source document to begin structured extraction into vault notes.

Frequently Asked Questions about reduce

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

FAQPage Schema

How do I extract structured knowledge from source material into a retrievable vault?▼

To extract structured knowledge, provide a source document to trigger comprehensive extraction into atomic notes covering core claims, patterns, tensions, validations, enrichments, and open questions for your domain vault.

What is the best way to manage cross-linking and duplicate detection for domain insights?▼

Managing cross-linking and duplicate detection is handled through a configurable pipeline that identifies related notes, creates enrichment tasks for added depth, and links extractions to prevent redundant domain insights.

How do I classify extracted notes to guide follow-up work and integration?▼

You classify extracted notes by tagging them as OPEN or CLOSED, which directly guides follow-up work and tracks the integration status of the structured knowledge within your domain vault.

Can I use comprehensive extraction to ensure zero skipped insights from domain-relevant sources?▼

Yes, comprehensive extraction is the default behavior, targeting a skip rate below 10% for domain-relevant sources. Zero extraction from a relevant source is treated as a bug to ensure complete knowledge extraction.

Does knowledge extraction support downstream enrichment when a source adds new evidence?▼

Yes, knowledge extraction supports downstream enrichment by identifying related notes and creating enrichment tasks whenever a source adds new depth, evidence, or examples to the existing domain insights.

Why does my notes-management extraction return zero insights from a domain-relevant source?▼

Zero insights from a domain-relevant source indicates a bug in the notes-management extraction process, which is designed to comprehensively extract all domain-serving insights with a skip rate below 10%.