Business & Operations

Maintains Obsidian vault organization and structure according to established conventions.

You are a specialized pullback detection system for trend continuation trading with concentrated positions (95% capital).

You are the risk management system for 95% concentrated position trading. Your role is CRITICAL - a single mistake can devastate the account.

Prepares meeting materials by gathering context from Obsidian vault, enriching with research, and creating comprehensive meeting documentation. Generates both internal prep notes with background and external agendas with structure, all saved as properly linked markdown notes in vault.

Manages Gmail through the Gmail API. Search and read emails, send messages, manage labels and filters, handle attachments, and automate email workflows. Use when working with Gmail, reading/sending emails, searching inbox, managing email organization, or processing email data.

Manages Google Drive files and folders through the Drive API. Search for files, read content, create and update documents, organize folders, manage permissions, and sync files. Use when working with Google Drive, uploading/downloading files, searching Drive content, or managing Drive organization.

Manages Google Docs, Sheets, and Slides through the Docs, Sheets, and Slides APIs. Create, read, and edit documents, spreadsheets, and presentations programmatically. Format content, manage collaboration, extract data, and automate document workflows. Use when working with Google Workspace documents, editing content, extracting data, or automating document creation.

Compare how an empirical variable or construct is measured across papers, including data sources, model roles, and local-project availability

Ingest a theory-modeling paper into the wiki: paper card plus assumptions/primitives, propositions/theorems, solution concept, and testable implications, bridged to the empirical layer on one shared graph

Generate a Related Work section for a paper from wiki knowledge — thematic grouping → narrative structure → LaTeX output, following citation-verification and academic-writing

Convert an empirical design into a Stata execution plan or optional do-file skeleton covering merge, variable construction, regressions, robustness, and exports

General-purpose cross-model review — Review LLM independently reviews any research artifact, outputs structured scores, wiki entity mapping, and improvement suggestions

Reset wiki state to a clean scaffold by scope (wiki / raw / log / checkpoints / all). Useful during development or carefree restarts after a botched setup.

End-to-end research orchestrator — idea discovery → experiment design → execution → verdict → paper writing, with human gates and session-resumable state

General-purpose multi-round iterative improvement — repeatedly calls /review on any research artifact, parses feedback, applies fixes, updates wiki, until the target score is reached

Parse review comments → atomize concerns (Rvx-Cy) → map to wiki claims → check evidence → Review LLM stress-test → generate rebuttal

Seed wiki/foundations/ with domain background knowledge so subsequent /ingest does not create duplicate concept pages for textbook material

Ingest a paper into the wiki — creates pages (papers + concepts + people + claims) and builds all cross-references and graph edges. Trigger whenever the user says "ingest", "add this paper", drops a `.pdf` / `.tex` / arXiv URL, or asks to fold a paper into the knowledge base.

Multi-phase research idea generation pipeline: landscape scan → dual-model brainstorm → first-pass filter → deep validation → write to wiki

Full experiment execution pipeline — prepare code → deploy → monitor → collect results, supporting three run modes

Ingest an empirical social-science paper into the wiki: paper card plus variables, datasets, models, mechanisms, identification, robustness, heterogeneity, and tables

Generate an empirical research design from ingested literature and local project data: question, theory, variables, data, model, identification, mechanisms, heterogeneity, and robustness

Add or remove raw sources, or update wiki content, per user request

Build a ranked shortlist of candidate papers (anchor-driven, topic-driven, or derived from current wiki state) that the user — or an upstream skill — may decide to feed into `/ingest`. Use whenever the user asks "what should I read next", "find papers similar to this one", "recommend related work", "what's around this topic", or whenever `/ingest` is invoked with `--discover`. Does not ingest; only proposes.