Abilityai/cornelius

AI-powered second brain template for Claude Code + Obsidian

This repository also configures its own agents. See what cornelius tells them →

110Stars on the repository
82Mods indexed here, across every type
8d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

advise

01

Abilityai/cornelius

Skill Claude Code

Solve problems using knowledge base insights - extracts search terms, runs parallel KB queries, synthesizes advice grounded in your own frameworks.

not rated 110 +1 changed 8d ago A SkillSpector: pass 27 tokens original MIT

ai-crystallize

02

Abilityai/cornelius

Skill Claude Code

Autonomous AI crystallization - synthesizes converged thinking topics into ai-inferred notes in a dedicated folder. Never touches the human-curated permanent knowledge base and never changes a topic's status, so manual crystallization stays available to the user.

not rated 110 +1 8d ago A SkillSpector: warn 54 tokens original MIT

analyze-kb

03

Abilityai/cornelius

Skill Claude Code

Analyze knowledge base structure and update the knowledge-base-analysis.md report.

not rated 110 +1 8d ago A SkillSpector: pass 17 tokens original MIT

auto-discovery

04

Abilityai/cornelius

Skill Claude Code

Discover non-obvious cross-domain connections through random sampling and pattern analysis.

not rated 110 +1 changed 8d ago A SkillSpector: pass 17 tokens original MIT

benchmark-memory

05

Abilityai/cornelius

Skill Claude Code needs its repo

Systematic benchmarking framework for Local Brain Search memory system with LLM-as-judge scoring.

not rated 110 +1 changed 8d ago A SkillSpector: pass 20 tokens original MIT

changelog-protocol

06

Abilityai/cornelius

Skill Claude Code

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

not rated 110 +1 8d ago A SkillSpector: pass 35 tokens original MIT

coherence-sweep

07

Abilityai/cornelius

Skill Claude Code needs its repo

Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report.

not rated 110 +1 8d ago A SkillSpector: pass 31 tokens original MIT

compute-lifecycle

08

Abilityai/cornelius

Skill Claude Code needs its repo

Compute lifecycle scores for all insight and framework notes - detect which notes are crystallizing or becoming generative.

not rated 110 +1 8d ago A SkillSpector: pass 24 tokens original MIT

create-article

09

Abilityai/cornelius

Skill Claude Code needs its repo

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.

not rated 110 +1 changed 8d ago A SkillSpector: warn 47 tokens original MIT

Abilityai/cornelius

Skill Claude Code needs its repo

Generate explanatory diagrams and infographics that visually communicate concepts. Iterates autonomously until images are logically correct, text is clean, and the concept explanation is clear. Uses Nano Banana (Gemini 2.5 Flash Image).

not rated 110 +1 8d ago A SkillSpector: warn 51 tokens original MIT

deep-research

11

Abilityai/cornelius

Skill Claude Code

Autonomous research pipeline - discover, extract, and integrate cutting-edge insights into knowledge base.

not rated 110 +1 8d ago A SkillSpector: pass 21 tokens original MIT

detect-tensions

12

Abilityai/cornelius

Skill Claude Code needs its repo

Detect productive contradictions between notes - high semantic similarity with opposing conclusions that represent synthesis opportunities.

not rated 110 +1 changed 8d ago A SkillSpector: pass 20 tokens original MIT

dialectic

13

Abilityai/cornelius

Skill Claude Code

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…

not rated 110 +1 changed 8d ago A SkillSpector: pass 122 tokens original MIT

domain-watch

14

Abilityai/cornelius

Skill Claude Code

Autonomous perception layer - scans KB for new notes matching domain watch configs, checks gap resonance with the Thinking Registry, probes external signals via web search, and auto-activates HIGH/MEDIUM signals into the Thinking Registry for the incubation loop.

not rated 110 +1 8d ago A SkillSpector: warn 52 tokens original MIT

Abilityai/cornelius

Skill Claude Code

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.

not rated 110 +1 8d ago A SkillSpector: pass 40 tokens original MIT

Abilityai/cornelius

Skill Claude Code

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.

not rated 110 +1 8d ago A SkillSpector: warn 40 tokens original MIT

Abilityai/cornelius

Skill Claude Code

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

not rated 110 +1 changed 8d ago A SkillSpector: pass 32 tokens original MIT

extract-insights

18

Abilityai/cornelius

Skill Claude Code

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

not rated 110 +1 8d ago A SkillSpector: pass 28 tokens original MIT

find-connections

19

Abilityai/cornelius

Skill Claude Code

Discover hidden connections and relationships between notes in the knowledge base.

not rated 110 +1 changed 8d ago A SkillSpector: pass 15 tokens original MIT

get-perspective-on

20

Abilityai/cornelius

Skill Claude Code

Extract the user's perspective on a topic (called by a content agent or user).

not rated 110 +1 changed 8d ago A SkillSpector: warn 21 tokens original MIT

Abilityai/cornelius

Skill Claude Code

Extract the transcript from a YouTube video by URL or video ID. Use when the user shares a YouTube link and wants the transcript, captions, or text content of the video. Falls back automatically if the requested language isn't available.

not rated 110 +1 changed 8d ago A SkillSpector: pass 53 tokens original MIT

git-commit-push

22

Abilityai/cornelius

Skill Claude Code

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

not rated 110 +1 8d ago A SkillSpector: pass 19 tokens original MIT

graduate-insights

23

Abilityai/cornelius

Skill Claude Code

Review and graduate notes to permanent status using Zettelkasten principles. Consolidates AI extractions and document insights into curated permanent notes.

not rated 110 +1 8d ago A SkillSpector: warn 31 tokens original MIT

incubation-loop

24

Abilityai/cornelius

Skill Claude Code needs its repo

Autonomous iterative thinking loop - processes active topics using rotating analytical moves (ACH, Bayesian updating, steelmanning, cross-domain bridging, implication checks) and persists reasoning state across scheduled runs.

not rated 110 +1 8d ago A SkillSpector: warn 42 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: