Reference guide for pulling crypto OHLCV data via the unified ccxt pipeline at infrastructure/pipelines/crypto/. Use when the user asks how to pull, refresh, or access Binance/Coinbase/Kraken price data, or how to load crypto zips in research notebooks. Trigger phrases: 'crypto data', 'pull from binance', 'pull from…
Reference guide for pulling SEC EDGAR fundamentals via the edgartools pipeline at infrastructure/pipelines/edgar/. Use when the user asks how to pull, refresh, or access EDGAR data — income statements, balance sheets, cash flow, or quarterly filings. Trigger phrases: 'edgar data', 'pull fundamentals', 'SEC filings'…
On-demand LEAN API reference for gotchas, patterns, and best practices. Use when writing or reviewing QuantConnect algorithm code to avoid common pitfalls. Invoke when you need detailed code examples for LEAN API usage — the always-loaded claude.md has only imperative summaries.
Guide for setting up, launching, and working inside marimo notebooks for exploratory signal research against local WRDS/CRSP data. Use when the user asks how to start a marimo notebook, how WRDS data is formatted for marimo, how to use the marimo-pair skill, or how to load 30-stock equity universe price/fundamental…
Creates new data pipelines that output LEAN-formatted files. Use when the user wants to pull data from a new source (API, database, file) and make it available for local LEAN backtests. Trigger phrases: 'new pipeline', 'add data source', 'pull data from', 'download [X] data locally', 'create a pipeline for', 'set up…
QuantConnect project bootstrap specialist. Use proactively when asked to make, create, scaffold, or standardize a new project under MyProjects with standalone Git, project-local AGENTS.md and claude.md, and working local LEAN backtest and research setup.
Reference guide for pulling Polymarket prediction-market data via the Gamma + CLOB pipelines at infrastructure/pipelines/polymarket/. Use when the user asks how to pull, refresh, or access Polymarket market metadata or YES-token price history, or how to load it in research notebooks. Trigger phrases: 'polymarket'…
Use this agent when building a new QuantConnect LEAN algorithm from a strategy specification. It scaffolds the full project structure including main.py, domain/config.py, models/alpha.py, and models/portfolio.py following the atomic layered architecture. Examples:\n\n \nContext: User wants to build a momentum-based…
Process and analyze manually downloaded backtest results from the QuantConnect website. Parses orders, trades, logs, and result JSON files to perform sanity checks, realized P&L analysis, and trade-to-log correlation. Use when the user has downloaded backtest output files and wants them analyzed. Context: User…
Use this agent when algorithm code changes have been made to a QuantConnect project and you need to validate the code compiles and runs without errors before proceeding to notebook analysis or committing changes. This agent should be invoked proactively after any significant code modification.\n\n \nContext: The user…
Use this agent when asked to create or populate .ipynb files under a project's research/ directory in the QuantConnect workspace. This includes writing single notebooks or complete 5-notebook teaching series that use QuantBook() for data access. Trigger this agent whenever a user requests notebook creation, notebook…
Search and manage the References/ library of research material — books, papers, repos, notes, and web articles from QuantConnect blog, Quantacracy, and Quantpedia. Use when the user asks to find material on a topic, fetch new articles, or check what references exist. Context: User wants to know if they have any…
Reference guide for pulling data from WRDS into the local LEAN pipeline. Use when the user asks how to pull, refresh, or access WRDS data — equity prices, ETF constituents, sector classifications, or Piotroski F-scores. Trigger phrases: 'data from WRDS', 'pull from WRDS', 'refresh WRDS', 'WRDS pipeline', 'how do I get…
Build, smoke-test, publish, and verify the Q-agent Docker image (LEAN CLI + infrastructure pipelines + marimo). Handles LEANVERSION bumps, local iteration, GHCR pull verification, and CI debugging for the docker workflow.
Work inside a running marimo notebook's kernel — execute code, create cells, and build a notebook as an artifact. Use when the user wants to start a marimo notebook or work in an active marimo session.
Commit and push the QuantConnect repo to Git and GitHub. Handles staging, committing, marimo notebook rendering, and pushing. Use when the user wants to push to GitHub (not QuantConnect Cloud).
Run a local QuantConnect research notebook in the correct LEAN Docker environment, inspect executed outputs, extract rendered charts, and interpret the results. Use when the user asks to run, debug, validate, or explain a notebook under MyProjects//research/.ipynb.