Build an EmpiricalWiki workspace from PDFs and notes with parallel ingestion.
npx skills add https://github.com/Lambenthan/empiricalwiki --skill init-lambenthan
Please help me install this Agent Skill. Skill: /init Source: https://github.com/Lambenthan/empiricalwiki/tree/main/.claude/skills/init Command: npx skills add https://github.com/Lambenthan/empiricalwiki --skill init-lambenthan
/init turns your local research inputs (PDFs, notes, and optional web material) into a structured EmpiricalWiki workspace and an initial, curated paper set that can be ingested in parallel.
Run the init orchestration to build the wiki from your raw inputs and ingest the resulting paper set with discovery: init [topic].
High-intent search queries and answers about installing and using this skill.
Building an empirical wiki from raw research PDFs involves orchestrating deterministic PDF preparation to normalize local files into canonical ingest sources, then generating a structured workspace scaffold with provisional pages before parallel ingestion.
Planner-guided discovery for research workflows is a methodology that selects a bounded candidate paper set, including optional external discovery, to ensure only relevant sources enter the empirical wiki ingestion pipeline.
Yes, you can ingest multiple papers in parallel using worktree-based fan-out and fan-in. This worktree-isolated parallel ingestion safely processes each selected paper deterministically before executing post-merge deduplication and rebuilding.
Preparing PDFs for parallel ingestion into a knowledge graph requires deterministic normalization into canonical ingest sources. The orchestration then consumes a strict checkpoint order to execute worktree-isolated parallel ingestion safely.
An empirical wiki workspace breaks down variables, mechanisms, identification, robustness, heterogeneity, tables, and paper evidence for each ingested source, ultimately producing a coherent final knowledge graph and index.
Limitations of automated paper ingestion include the strict requirement to consume a final checkpoint order for ingest. You must also execute post-merge deduplication, rebuilding, and linting steps to maintain a coherent knowledge graph.
skyllwtOrchestrate ΩmegaWiki initialization and parallel paper ingestion from raw sources.
angrysky56Ingest raw inbox files into a wiki knowledge base and Neo4j graph database.
duany049A task and/or a project management system for organizing and tracking your work, optionally integrated with your calendar and email via plugins, connectors, and APIs.
LambenthanExtract variables, datasets, and models from empirical papers into wiki pages.
