- Home
- Skills
- Trading & Investing
- repainting fake signal inspector
repainting fake signal inspector
Audit Pine Script strategies for repainting, lookahead bias, and unrealistic backtest results.
$5
Works with the AI Agents you already use
repainting fake signal inspector
Example session with this skill installed
Audit this snippet for lookahead bias
strategy.entry("Long", strategy.long, when=clover > 0)
strategy.exit("Exit", "Long", stop=low - 10 * syminfo.mintick)
- Read your context and instructions
- Compiled the repainting fake signal
Finding #1: Lookahead Exit Bias
Severity: high
Line: strategy.exit(...)
Issue: Using 'low' of the current bar to set a stop loss on the same bar.
Why it is unrealistic: The strategy assumes it knows the bar's low before it occurs.
Suggested fix: stop=low[1] - 10 * syminfo.mintick
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
TradingView backtests often show impossible returns due to hidden coding errors. Pine Script strategies frequently suffer from repainting and lookahead bias, where the script "sees" future prices to trigger perfect entries that can never happen in live trading.
What it does
- Identifies repainting risks in
request.securitycalls and indicator calculations. - Detects lookahead bias where stops or targets use current bar data before it exists.
- Audits
strategy()parameters for unrealistic slippage, commission, and fill assumptions. - Flags duplicate signal logic that artificially inflates trade counts or equity curves.
- Provides concrete Pine Script code fixes for every high-severity finding.
Frameworks & tools
TradingView Pine Script (v4 and v5).
Why this beats prompting it yourself
Generic LLMs often miss subtle execution nuances like process_orders_on_close interactions or barstate persistence. This skill uses a specialized audit workflow to trace the order lifecycle bar-by-bar, catching logic traps that pass standard syntax checks.
Use cases
- Verifying a purchased or open-source Pine Script strategy before risking capital.
- Debugging "too good to be true" backtest results that disappear in forward testing.
- Hardening entry and exit logic to ensure signals confirm only on closed bars.
- Adding realistic execution constraints like slippage and commissions to existing scripts.
Known limitations
Cannot execute the code to see visual repainting; relies entirely on static analysis of the provided script logic.
Static analysis only. Cannot detect repainting caused by external data feed delays not present in the code logic.
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 any payment.
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 3 months ago
Permissions
No special permissions declared or detected