- Home
- Skills
- Trading & Investing
- Backtest Reality Stress Tester
Works with the AI Agents you already use
Backtest Reality Stress Tester
Stress-test trading backtests for data leakage, execution realism, and overfitting to verify strategy credibility.
$9.99
Backtest Reality Stress Tester
Example session with this skill installed
Stress-test this Pine Script strategy. It shows a 4.0 profit factor, but I suspect repainting or lookahead bias. Here is the code and the CSV trade log from the last 12 months.
- Read your context and instructions
- Compiled the backtest reality stress
Verdict: Material realism gaps. Score: 42/100. Analysis detected lookahead bias in the entry logic (same-bar exit). When adjusted for a 1-bar delay and 0.05% slippage, the profit factor dropped to 0.85. The edge is likely an artifact of timing errors, not market inefficiency.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Most backtests suffer from survival bias, lookahead errors, and unrealistic execution assumptions. Developers often find that strategies with stellar historical results collapse immediately when faced with real-world slippage, fees, or unseen market regimes.
What it does
- Identifies hidden data leakage, lookahead bias, and repainting indicators in Pine Script or Python code.
- Calculates break-even friction levels to determine at what cost-per-trade the strategy edge disappears.
- Stress-tests performance against parameter sensitivity, trade concentration, and regime shifts.
- Evaluates the integrity of out-of-sample data and research chronology to detect search-bias and overfitting.
- Produces a tiered robustness score constrained by the quality of available evidence.
Frameworks & tools
Works with Pine Script (TradingView), Python (Pandas/Backtrader), CSV trade logs, and standard brokerage backtest reports.
Why this beats prompting it yourself
This skill enforces a two-stage scoring rubric that prevents "absence of evidence" from being mistaken for "robustness." It uses specialized failure-pattern recognition to catch subtle timing errors that generic LLM prompts typically overlook.
Use cases
- Auditing a Pine Script strategy before committing capital to a live bot.
- Validating third-party backtest claims before purchasing a trading signal or algorithm.
- Determining if a strategy edge is a result of over-optimization or genuine market inefficiency.
- Quantifying the impact of realistic slippage and borrow fees on high-turnover strategies.
Known limitations
Does not provide financial advice or guarantee future profits. Requires strategy code or detailed trade logs for high-confidence leakage detection.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Trading & Investing.
Requires strategy code or trade logs for high-confidence leakage detection. Cannot verify data integrity without raw bar access. Does not execute live trades or invent missing market data.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
- Software
Python