reduce

To extract structured domain knowledge from raw literature sources, the skill converts source material into standalone notes capturing claims, evidence, patterns, tensions, and enrichments with clear provenance. It externalizes reasoning to support end-to-end traceability in a knowledge graph.

Knowledge graph enrichment works by analyzing experimental data and automatically generating enrichment tasks that strengthen existing notes and improve cross-linking opportunities. This process surfaces core domain claims, evidence, and validations while maintaining explicit source references for traceability.

Yes, you can extract structured notes from large documents and multiple sources. The skill supports multi-source processing with automatic chunking and cross-chunk coordination to ensure comprehensive extraction of arguments, evidence, and reasoning across the entire input.

The best way to externalize reasoning and capture hypotheses is to convert source material into composable standalone notes. This approach emphasizes comprehensive extraction of domain claims, evidence, patterns, and tensions rather than simple summaries, ensuring topic-map connections are established.

No, you do not need external prompts to generate structured notes with provenance. The skill requires no external prompts beyond the input source document itself, automatically producing standalone, composable notes with explicit source references and topic-map connections for attribution.

Comprehensive domain note extraction distinguishes itself from basic summarization by surfacing core domain claims, evidence, patterns, tensions, validations, and enrichments. It generates enrichment tasks and cross-linking opportunities for the knowledge graph, whereas summarization only condenses text.