
Analyze knowledge base structure and update the knowledge-base-analysis.md report
Systematic benchmarking framework for Local Brain Search memory system with LLM-as-judge scoring
Autonomous research pipeline - discover, extract, and integrate cutting-edge insights into knowledge base
Apply Eugene's email tone of voice when writing, drafting, or composing emails. Use when the user asks to write an email, draft a reply, compose a message, or send communication. Auto-applies Eugene's professional yet authentic voice with direct authority, conversational expertise, and actionable insights.
Extract all chapters from an EPUB file into separate markdown files. Use when the user wants to split an EPUB into individual chapter files, extract EPUB chapters, or convert an ebook to separate markdown documents.
Handle Google OAuth token expiration and re-authentication. Use when Google Workspace operations fail with authentication errors, expired tokens, 401 Unauthorized, or authorization URL is returned. Provides streamlined re-authentication workflow.
Standard format for capturing and documenting insights in the knowledge base. Use when harvesting insights, creating permanent notes from user perspectives, or documenting unique thinking patterns.
Review sent emails from past month to identify those needing follow-up responses
Check inbox for new emails, respond to council members using Luminous knowledge, and extract insights for the knowledge base. Prevents duplicate responses.
Lightweight project management - create, track, update, and archive projects with folder-based structure
Quick search across Obsidian vault using keywords or semantic similarity
Ingest foundational documents into the Brain - decompose into source notes, atomic permanent notes, and MOCs
Extract unique insights and perspectives from personal content (conversations, transcripts, notes). Spawns insight-extractor subagent.
Orientation guide - introduces Cornelius, its core capabilities, main use cases, and the abilities marketplace
Wrapper for scheduled playbooks - handles git sync before and after execution
Rebuild the Cornelius voice agent system prompt from knowledge base sources
Run self-diagnostics on Cornelius agent to verify skills, commands, agents, and integrations are working. Use when troubleshooting, after configuration changes, or for regular health checks.
Solve problems using knowledge base insights - extracts search terms, runs parallel KB queries, synthesizes advice grounded in your own frameworks
Discover non-obvious cross-domain connections through random sampling and pattern analysis
Protocol for creating dated changelog files after significant agent sessions. Use when completing vault operations, discovery sessions, insight extraction, or any work requiring documentation.
Create long-form articles from knowledge base insights. Use when writing articles, blog posts, Substack content, or synthesizing knowledge into publishable content. Includes tone of voice, structure templates, and knowledge base integration.
An Electric Monk engine — two subagents believe fully committed positions on the user's behalf while the orchestrator performs structural contradiction analysis and synthesis. By outsourcing belief work to agents, the user operates from a belief-free position where they can analyze the structure of the contradiction rather than being inside either side. Use when the user wants to stress-test an idea, resolve a genuine tension, build a deeper mental model, or make a high-stakes decision where the tradeoffs are unclear. Works across any domain — technical architecture, product strategy, philosophy, personal decisions, risk analysis, policy, creative direction.
Advanced techniques for extracting insights, probing user thinking, and conducting cognitive interviews. Use when harvesting insights, exploring beliefs, clarifying concepts, or helping users articulate their unique perspectives.
Framework for distinguishing research findings from hypotheses and speculative synthesis. Use when extracting insights from research, creating notes from external sources, or classifying the epistemic status of claims.
Extract insights from external documents (research papers, books, articles). Spawns document-insight-extractor subagent. Requires session name.
Discover hidden connections and relationships between notes in the knowledge base
Stage, commit, and push changes to remote repository with approval gate
Review and graduate notes to permanent status using Zettelkasten principles. Consolidates AI extractions and document insights into curated permanent notes.
Find notes created in the last 14 days and discover their connections to the knowledge base
Generate images using Google's Nano Banana 2 (Gemini 3.1 Flash Image Preview). Use when creating infographics, diagrams, thumbnails, social media graphics, or any AI-generated images. Costs $0.067/image.
Fast knowledge base retrieval - single FAISS search + graph connections, no subagents or LLM orchestration
Retrieve relevant knowledge from Obsidian vault using 3-layer semantic search based on conversation context
Rebuild the Local Brain Search FAISS index to reflect vault changes
Combine multiple insights into coherent narrative
Comprehensive testing playbook for Local Brain Search memory improvements (Phases 1, 3, 4)
Update Knowledge Graph Changelog
Update dashboard.yaml with current knowledge base metrics from analysis report
Sync capability updates from cornelius-internal (private) to cornelius (public) repo, excluding personal/private skills and sanitizing paths
Conversational Partner Mode
--- name: send-email description: Send emails via Google Workspace with duplicate prevention. Use when composing or sending emails. Checks Sent folder before sending to prevent duplicates. argument-hint: [recipient] [subject] [body] automation: gated --- # Send Email with Duplicate Prevention Send emails safely through the google-workspace subagent with built-in duplicate detection. ## State Dependencies | Source | Location | Read | Write | Description | |--------|----------|------|-------|-
Continuous learning heartbeat - autonomously researches, extracts insights, and expands knowledge base
Extract Eugene's perspective on a topic (called by Ruby or user)