Abilityai/cornelius

coherence-sweep

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

domain-watch

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…

incubation-loop

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

manage-reference-data

Upsert and maintain entity notes in a REFERENCE-kind scope (external facts/records), then reindex so they become connection/insight targets. Generic across reference scopes; Company is the default. The scope's entity taxonomy (type/relationship) lives in that…

ref-audit

Integrity report for a reference scope — the reference-scope analog of /coherence-sweep. Scans every entity note for provenance violations (any note not provenance:reference), type/relationship enum violations, missing/invalid as_of, status/superseded_by…

ref-bridge

Bridge reference entities to the cognitive knowledge base — "this client maps to that insight you had." A thin mode over connection-finder that mounts core,Company/<sub> and surfaces entity↔insight bridges, making the reference scope more than a CRM.…

ref-ingest

The single entry point for incoming information of ANY kind about a reference entity (a person, org, product, engagement, or watched competitor). Extracts entity facts, RESOLVES them to the one existing canonical note (never duplicating), reconciles…

ref-query

Structured, temporal lookup against a reference scope — "what do we know about Acme Corp as of today?", "which engagements are active and expiring in 90 days?", "list our competitors". Respects status (active over superseded), validity windows, and as_of…

ref-reconcile

Keep a reference scope canonical and internally consistent. SENSE phase (auto) detects issues by invoking ref-audit; FIX phase (human-gated) resolves conflicts, repairs bidirectional link integrity (A cites [[B]] as client → does B back-link?), fixes/removes…

ref-refresh

Mechanical staleness sweep over a reference scope. Scans every note's as_of age against the per-type Freshness SLA, builds an overdue-sorted refresh queue, then splits by scope — market/ stale items are handed to ref-ingest (the gate-free overwrite branch)…

ref-supersede

Handle a validity transition on a reference entity — a contract renewal, role change, or re-termed price where a full prior snapshot matters. Creates the new status:active note (with valid_from/valid_until), marks the old note status:superseded +…

refresh-index

Rebuild the Local Brain Search FAISS index to reflect vault changes

talk

Conversational partner mode - delegates each exchange to the thinking-partner sub-agent, which embodies the knowledge base as its own memory and engages as an intellectual equal. Use for open-ended brainstorming, exploring ideas, or thinking out loud with…

update-changelog

Append a dated entry to the master Brain/CHANGELOG.md summarizing this session's knowledge-graph changes - notes created, connections/links added, and significant edits. Use after a vault working session to record what changed and why it matters.

ai-crystallize

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…

analyze-kb

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

auto-discovery

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

compute-lifecycle

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

create-article

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.

create-explanatory-image

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).

deep-research

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

detect-tensions

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

epistemic-classification

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.

epub-chapter-extractor

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.

get-perspective-on

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

get-youtube-transcript

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.

graduate-insights

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

ingest-source

Fully autonomous end-to-end ingestion of a SINGLE source (book, paper, article, transcript) into the knowledge base - prepare to markdown, extract insights against the live index, refresh the index, auto-link to existing knowledge, and changelog. One source…

insight-interview

KB-grounded Socratic interview. Searches existing notes on a topic, then runs a one-question-at-a-time dialogue to surface, sharpen, and extract your own thinking. Ends by running extract-insights on the full conversation transcript.

integrate-recent-notes

Find notes created in the last 14 days and discover their connections to the knowledge base

learn-new-things

Continuous learning heartbeat - autonomously researches, extracts insights, and expands knowledge base

manage-thinking-topics

Manage the incubation loop topic lifecycle — seed new questions, review status, crystallize converged conclusions, and retire stale topics

multi-format-book-extractor

Extract chapters from PDF, MOBI, and AZW3 book files into individual markdown files. Use when extracting non-EPUB books. PDF uses pymupdf with TOC-based chapter splitting and auto-OCR fallback (Gemini) for scanned/image-only PDFs; MOBI/AZW3 routes through…

propagate-change

Propagate staleness from a changed note through the Brain Dependency Graph - shows which downstream notes need review

scheduled-run

Wrapper for scheduled playbooks - handles git sync before and after execution

self-diagnostic

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.

test-memory-system

Comprehensive testing playbook for Local Brain Search memory improvements (Phases 1, 3, 4)

think-about-it

Free-form thinking mode - consider a topic through successive distinct knowledge-base perspectives (hub lenses, original frameworks, wildcard distant notes). One perspective pass per invocation, state persists across runs, emits [[DONE]] when the exploration…

advise

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

benchmark-memory

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