Qlib Factor Backtest

Ingest market data for a supplied universe and backtest a supplied alpha-factor definition with Qlib. Use when a researcher wants a direct, evidence-linked backtest of one or more already-defined factors; this workflow does not discover new factors or place trades.

Knuckles-Team Updated 5 repo stars

File contents

Qlib Factor Backtest Workflow

Compose the named atomic skills without adding factor-discovery logic here.

Inputs

Provide the factor definition(s), asset universe, and date range.

Steps

Step 0: quant-data-ingest [skill: quant-data-ingest]

Invoke $quant-data-ingest with the workflow inputs to ingest market data for the universe and date range.

Expected: normalized_market_dataset

Step 1: qlib-backtester [skill: qlib-backtester] [depends_on: Step 0]

Invoke $qlib-backtester with normalized_market_dataset and the supplied factor definition(s).

Expected: backtest_report

Output

Return backtest_report. Does not discover new factors or place trades.

Execution

  • Run first: Step 0 — $quant-data-ingest.
  • After level 0: Step 1 — $qlib-backtester.

Execution: If arbora is reachable, offload the whole DAG via graph_orchestrate action=execute_workflow (or the kg-delegate skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet depends_on in parallel, then their dependents.

knuckles-team/universal-skills commit 6b53e1d3b0

Frequently asked questions

npx get-skill add knuckles-team/qlib-factor-backtest-2