- Home
- Skills
- Trading & Investing
- post trade mistake intelligence engine
post trade mistake intelligence engine
Analyzes trade history to quantify the PnL impact of execution mistakes and generate a prioritized improvement plan.
$5
Works with the AI Agents you already use
post trade mistake intelligence engine
Example session with this skill installed
Analyze these trades
- AAPL Long, entry 180, stop 178, exit 175. I deleted the stop when it got close.
- TSLA Short, entry 250, target 240, exit 248. Got scared and closed early.
- Read your context and instructions
- Compiled the post trade mistake
Summary
- Trades: 2
- Net PnL: -7.0R (Estimated)
Mistake Breakdown
| Mistake | Freq | Total Impact |
| Stop Deleted | 1 | -1.5R (additional loss) |
| Early Exit | 1 | -0.8R (missed gain) |
Top Mistake: Stop Deletion
Trade #1: Deleting stop increased loss by 150% vs original plan.
Plan
- Rule: If a stop is deleted, close position immediately at market.
- Goal: 0 deletions in 10 trades.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Manual trade reviews are often superficial, ignoring the hidden costs of emotional decisions and execution errors. Traders struggle to see the statistical difference between a valid loss and a costly mistake, leading to repeated failures without a clear path to correction.
What it does
- Normalizes raw trade logs and journal entries into a structured analytical framework.
- Categorizes failures across entry, exit, risk, stop-management, and emotional dimensions.
- Quantifies the R-multiple impact of mistakes like stop deletion, chasing, and FOMO.
- Identifies correlations between execution errors and external contexts like time of day or market volatility.
- Generates a prioritized improvement plan with specific, testable trading rules and measurable goals.
Why this beats prompting it yourself
Generic prompts often hallucinate PnL calculations or fail to distinguish between a plan-based loss and a psychological mistake. This skill applies a rigid taxonomy and counterfactual analysis to ensure every dollar lost to poor discipline is accurately accounted for and corrected via rule-based remedies.
Use cases
- Reviewing a weekly trading session to identify which psychological leaks cost the most capital.
- Auditing a series of losses to determine if the strategy is failing or if the execution is flawed.
- Refining risk management by analyzing the frequency and impact of "revenge" position sizing.
- Creating a data-driven pre-trade checklist based on your most recurring execution errors.
Known limitations
Requires entry price, exit price, and initial stop loss to calculate accurate R-multiple impact. Cannot quantify impact if counterfactual data (like original stop levels) is missing from logs.
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 entry/exit prices and initial stop loss for PnL impact calculations. Accuracy depends on the quality of trade notes provided.
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 3 months ago
Permissions
No special permissions declared or detected