Abilityai/cornelius - 第 2 页

brain-merge

Compare and selectively merge Brain directories across any two agent instances. Supports diff (see what's unique where), pull (import from another brain), and learn (bidirectional exchange).

原文语言：英语

changelog-protocol

Protocol for creating dated changelog files after significant agent sessions. Use when completing vault operations, discovery sessions, insight extraction, or any work requiring documentation.

原文语言：英语

dialectic

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…

原文语言：英语

elicitation-techniques

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.

原文语言：英语

extract-document-insights

Extract insights from external documents (research papers, books, articles). Spawns document-insight-extractor subagent. Requires session name.

原文语言：英语

extract-insights

Extract unique insights and perspectives from personal content (conversations, transcripts, notes). Spawns insight-extractor subagent.

原文语言：英语

find-connections

Discover hidden connections and relationships between notes in the knowledge base

原文语言：英语

git-commit-push

Stage, commit, and push changes to remote repository with approval gate

原文语言：英语

insight-capture-format

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.

原文语言：英语

manage-watching-domains

Manage domain-watch surveillance configs — seed new domains, review scan status and proposals, activate Watch Log proposals into thinking topics, pause domains, and update PIRs or watch queries

原文语言：英语

nano-banana-image-generator

Generate images using Google's Nano Banana (Gemini 2.5 Flash Image). Use when creating infographics, diagrams, thumbnails, social media graphics, or any AI-generated images. Costs $0.039/image.

原文语言：英语

quick-search

Fast knowledge base retrieval - single FAISS search + graph connections, no subagents or LLM orchestration

原文语言：英语

recall

Retrieve relevant knowledge from Obsidian vault using 3-layer semantic search based on conversation context

原文语言：英语

search-vault

Quick search across Obsidian vault using keywords or semantic similarity

原文语言：英语

start-here

Orientation guide - introduces Cornelius, its core capabilities, main use cases, and the abilities marketplace

原文语言：英语

synthesize-insights

Combine multiple insights into coherent narrative

原文语言：英语

update-dashboard

Update dashboard.yaml with current knowledge base metrics from analysis report

原文语言：英语