project-thoth

Initialize a new user's research assistant. Use this on first interaction or when user asks to "get started", "set up", or "introduce yourself". Also use when you don't know the user's research interests or the human memory block still has placeholder text.

Walk the user through new Thoth features since their last onboarding or update. Use when the user asks "what's new", "what changed", or "what can you do now". Also use after check_whats_new returns updates to walk through them.

Create, manage, and iterate on research plan documents in the Obsidian vault. Use when the user asks for a research plan, literature review roadmap, or when you need to formalize your own working research strategy.

Conduct deep analysis of research papers, synthesize literature, and generate comprehensive reviews. Use when user needs thorough paper analysis, literature reviews, or cross-paper synthesis.

Manage external knowledge collections (textbooks, lecture notes, background material) and search them to support research. Use when user wants to upload reference material or query foundational knowledge.

Answer questions using your existing research collection and external knowledge. Use when user asks questions about papers they have, wants summaries, or seeks insights from their knowledge base.

Customize what information is extracted from papers (schema) and how it's extracted (prompts). Use when the user wants to change analysis fields, instructions, or prompt templates.

Manage and optimize the RAG (Retrieval-Augmented Generation) system including reindexing, search optimization, and custom index creation. Use when user wants to improve search quality, reindex their collection, or create specialized indexes.

Manage external MCP server connections to extend Thoth's capabilities

Execute and monitor discovery sessions for finding research papers across academic sources. Use when running discovery searches.

Coordinate multi-phase research workflows with parallel specialist execution. Use when orchestrating complex research tasks requiring multiple agents.

Set up custom article sources from any website using LLM-powered auto-detection. Use when user asks to add a new source, scrape a website, create a workflow, or wants papers from a site not already supported.

Discover and download academic PDFs using DOIs, arXiv IDs, or paper titles. Downloaded PDFs are automatically processed by the PDF monitor service.

Find and curate research papers from academic sources. Use when user asks to find papers, search for research, discover articles, or explore a new topic.

Manage large-scale research projects requiring multiple phases of discovery, analysis, and synthesis. Use when user is working on survey papers, thesis chapters, or comprehensive research projects.

Set up and manage automated recurring research searches. Use when user wants to stay updated on a topic, create scheduled searches, or refine existing queries.

View and modify Thoth configuration settings. Use when user wants to change API keys, paths, search settings, or other configuration options.

Collaboratively create and refine new skills through iterative design - validate needs, design structure, draft content, test, and refine.

Systematic deep research through discovery sources, vault, and web - refine query, collect papers, analyze, synthesize findings into comprehensive markdown report.

Set up effective automated discovery - from vague idea to working system in one streamlined conversation.

Defragment and clean research agent memory - consolidate paper info, organize research domains, remove redundancy from research tracking.

Search conversation history for research context - papers discussed, citations analyzed, discoveries made, or questions explored.

Guide users through creating effective research questions for automated paper discovery. Use when user wants to set up automated paper discovery or create new search queries.