Daily fund briefing combining platform health and trading activity. Use when the user asks "morning report", "daily report", "fund briefing", "how is the fund", "fund status", "trading status", "portfolio summary", "what happened overnight", "morning briefing", "how are we doing", "is everything running", "check the platform", "platform status", "are services healthy", "check health", or "is the fund ok".
Autonomous model training optimization loop using autoresearch methodology. Invoked as `/autotrain <model-name>` (e.g., `/autotrain tide`). Iteratively modifies model architecture code, runs training via parallel local execution, evaluates a target metric, and keeps or reverts changes to find the best model. Uses parallel Agent workers for hyperparameter search and sequential iterations for architecture changes. Use when the user wants to optimize a model, run autoresearch, find the best architecture, or improve training metrics. Includes epoch escalation (Mode C) for pushing past plateaus. Optionally accepts `--metric <name>` to specify the optimization target.
Read and analyze a research paper using the three-pass method tailored for quantitative finance, machine learning, and technology papers. Walks through three named passes — Orientation, Comprehension, and Implementation — pausing between each. Use when the user provides a paper URL and wants structured analysis. Trigger on "read this paper", "analyze this paper", "/read-paper", or when a URL to a research paper is provided.