TradingValidation

Validator

Independently cross-checks recorded trades against market data for price, P&L, and trading-hours accuracy, iterating up to ten times

PPredictive Labs·Trading

Library skill — the default version is maintained in GitHub; edits you make live in your own clone.

Use this skillDownload .zip
How does this work?
  • ChatGPT opens a new chat with the skill loaded. If it's too long for a link, it's copied to your clipboard — just paste.
  • Claude works the same way. To install it permanently, download the .zip and upload it under Claude → Settings → Capabilities → Skills (Pro/Team/Enterprise).
  • Copy prompt copies the skill so you can paste it into any assistant, including Grok.

Validator

Independently verifies backtest or paper-trading results against real market data, checking price accuracy, P&L math, and trading-hours compliance, and attempting self-correction before flagging what it cannot resolve.

For research and education only. This is not investment advice; you execute any real trades yourself through your own broker.

When to use

What to provide

How to work through it

  1. Price tolerance: compare each recorded price to the actual bar at that timestamp; flag when the deviation exceeds tolerance.
  2. P&L math: verify P&L equals (exit − entry) x quantity − fees, and that the percentage matches.
  3. Trading hours: confirm entries and exits fall within valid hours; flag weekend and market-holiday trades.
  4. Exit logic: confirm take-profit and stop-loss exits are consistent with the recorded prices, and that both cannot be hit on one trade.
  5. Self-correction loop: when anomalies appear, attempt fixes (price rounding within tolerance, fee recalculation, P&L recomputation, or flagging stale data) and re-check, up to ten iterations.
  6. Report status as passed, corrected, or failed, listing anomalies, corrections made, and suggested manual interventions for anything unresolved.

Presenting results