Back to catalog / Crypto trading tools
Strategy backtesting: control data bias before evaluating results
Build reproducible simulations that address look-ahead, survivorship, overfit, and trading costs.
Skills
Define information availability time, historical universe, missing-data rules, and execution-price model. Ensure features use only then-available data and include delisted assets where relevant. Separate train/validation/test periods or use walk-forward evaluation; do not inspect the final sample during optimization. Model fees, slippage, funding, execution delay, and capacity, then compare a naive benchmark and risk measures. Record seed, parameters, and dataset version. Report assumptions and uncertainty, not investment advice, and never connect the backtest to live orders.
Permissions
Prerequisites
- For developing/reviewing strategy backtests while controlling look-ahead, survivorship, selection, and cost biases.
- Fix data source/window, universe construction, execution timing, fees, and slippage assumptions.
Permissions
- May read historical prices and change simulator/strategy code; it should produce simulated orders only.
- Backtests do not predict future results or recommend trades; never connect a test to live order execution.
Limitations
Use point-in-time data and out-of-sample/walk-forward validation with fees, slippage, latency, and capacity; report benchmarks and bias.
Pinned upstream source
- Repository
- wshobson/agents
- File path
- plugins/quantitative-trading/skills/backtesting-frameworks/SKILL.md
- Pinned commit
46891e7e60da0e52baf1050b7b6391b64e84c6d9- Source checked
- 2026-10-14 · Reviewed against the pinned upstream source
Repository metrics
These values describe the upstream repository, not popularity or likes for an individual skill or playbook.
- Stars
- Not collected
- Forks
- Not collected
- Observed at
- Not collected
No metrics snapshot is available yet.
License: MIT
Compatible tools
Backtest engine · Point-in-time datasets · Out-of-sample evaluation
Main topic
Build a reproducible crypto research workflow