Orchestrate ΩmegaWiki initialization and parallel paper ingestion from raw sources.
npx skills add https://github.com/skyllwt/AutoSci --skill init-skyllwt
Please help me install this Agent Skill. Skill: /init Source: https://github.com/skyllwt/AutoSci/tree/main/.claude/skills/init Command: npx skills add https://github.com/skyllwt/AutoSci --skill init-skyllwt
This Skill converts your raw research inputs into a working ΩmegaWiki scaffold, then selects and ingests a curated set of papers to grow the wiki end-to-end with resumable, parallelized orchestration.
Run /init with your research topic (and omit --no-introduction unless you explicitly want local-only discovery) so the system prepares your raw inputs, selects a final paper set, and ingests them into wiki/ in parallel.
High-intent search queries and answers about installing and using this skill.
To bootstrap a research wiki from local PDFs and web notes, the system normalizes your raw inputs into prepared artifacts, scaffolds the wiki structure, and ingests a curated set of papers in parallel to populate topics and concepts.
Parallel paper ingestion works by fanning out one paper per subagent into an isolated worktree, then conservatively merging the results back to rebuild edges, citations, and indexes for the knowledge graph.
Yes, you can use external sources for paper discovery by omitting the local-only flag, allowing the planner to build a candidate shortlist from both local inputs and external discovery before trimming to a final set.
The best way to recover a failed wiki ingestion workflow is through its checkpoint-driven preparation manifests, which record progress and allow the resumable orchestration process to restart from the last successful state.
Yes, the deterministic wiki scaffolding process automatically creates provisional pages for summaries, topics, ideas, and concepts while strictly respecting rules for what may be auto-created.
During the wiki bootstrapping process, the planner trims the candidate shortlist to a final set of 8 to 10 papers before fetching and ingesting them into the knowledge graph.
SebasArenClassify raw materials and generate wiki pages from PDFs, notes, and URLs.
tronghieuRetrieves cited answers from Lumina-Wiki's graph of concepts and sources.
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.
andrehuangMap research papers into a per-topic wiki workspace with references.bib.
