trading-experiment
Autonomous crypto strategy research via backtesting. Claude designs experiments, writes strategy code, runs backtests via MCP tools, analyzes results, and iterates until a target threshold is met.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin trading-experiment in dapmeupfam/trading-experiment. Commands read from the repo's manifest — 1 month ago.
What it installs
Skills (1)
experimentThis skill should be used when the user asks to \"run a trading experiment\", \"find a trading strategy\", \"backtest strategies\", \"research crypto strategies\", \"optimize a trading strategy\", \"find alpha\", or wants autonomous strategy research and backtesting. Designs, backtests, and iterates
Subagents (3)
experiment-runnerUse this agent to autonomously run crypto strategy research experiments. It iterates through the experiment cycle (design -> code -> backtest -> analyze -> repeat) using MCP backtesting tools until a performance threshold is met. <example> Context: User invoked /trading-experiment and wants autonomo
rubber-duckStrategy advisor that discusses trading ideas before code is written. Analyzes what worked, what failed, and suggests concrete improvements. Spawned by experiment-runner before each coding iteration to clarify the hypothesis and produce a focused coding brief.
strategy-coderWrites backtesting.py Strategy subclasses from coding briefs. Receives a structured brief from the experiment-runner, reads the code guide and available helpers, and produces clean strategy code. Fresh context each iteration — no accumulated state.
Maintain trading-experiment?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.