- Home
- Skills
- Trading & Investing
- Trading Mistake Pattern Detector
Works with the AI tools you already use
Trading Mistake Pattern Detector
Detect and quantify recurring execution, risk, and behavioral patterns from trading journal data.
$5
Trading Mistake Pattern Detector
Example session with this skill installed
Analyze my June trading journal CSV. Look for recurring exit mistakes and tell me if my P&L impact is coming from cutting winners early or holding losers too long.
- Read your context and instructions
- Compiled the trading mistake pattern
- Generated the document
I have analyzed your June trading journal consisting of 42 closed trades. I normalized your 'Exit Reason' notes and cross-referenced them against your R-multiple outcomes.
Trading Mistake Pattern Report - June
| Mistake | Occurrences | Frequency | Evidence Level | Est. R-Impact | Priority |
|---|---|---|---|---|---|
| Early Profit Taking (Fear) | 9 | 21.4% | Observed | -6.2R | High |
| Holding Losers Past Stop | 3 | 7.1% | Pattern | -4.5R | High |
| Moving Target (Greed) | 2 | 4.8% | Observed | +1.1R | Low |
| Technical Exit (Rule Based) | 28 | 66.7% | Observed | 0.0R | N/A |
Pattern Breakdown: Early Profit Taking
Your journal notes frequently mention "feeling shaky" or "securing the bag" when price reached 1:1 RR, despite your strategy calling for a 2:1 RR exit. This behavior clustered heavily during the NY Morning session (7/9 instances) and typically occurred after you experienced a losing trade earlier in the day.
Corrective Action Plan: NY Session Discipline
- Trigger: Reaching 1:1 RR on a trade after a prior loss.
- Current Behavior: Manual market exit to "lock in" small gains.
- Replacement Behavior: Set 'Break Even' stop and close the terminal. Let the hard target or stop be hit.
- Measurement: Percentage of trades reaching 2:1 RR target when the setup remains valid.
Next steps
- Update your pre-trade checklist to include a "Recency Bias" check if the previous trade was a loss.
- Review your July data in 4 weeks to see if the R-impact of "Early Profit Taking" has decreased.
- Consider automated bracket orders to remove the manual exit temptation during high-volatility sessions.
trading-mistake-pattern-detector.pdf
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Traders often struggle to identify the specific behavioral and execution patterns that drain their capital. Individual trade reviews usually fail to uncover the systemic risk, discipline, and FOMO patterns that only become visible through objective, multi-period data analysis.
What it does
- Identifies recurring entry, exit, risk management, and discipline mistakes across hundreds of trades.
- Quantifies the frequency and P&L impact of specific behaviors like 'revenge trading' or 'moving stops'.
- Correlates emotional states and session times with rule-breaking patterns.
- Tracks progress over weekly or monthly review cycles to see if mistake frequency is decreasing.
- Generates a prioritized corrective action plan with measurable metrics for behavior replacement.
Why this beats prompting it yourself
Generic LLM prompts often hallucinate correlations or provide vague psychological advice. This skill uses a strict evidence-based taxonomy and normalization process to ensure every identified pattern is backed by journal data, distinguishing between observed facts and hypotheses.
Use cases
- Conducting a monthly post-mortem on a trading journal to find the highest-impact leakage.
- Identifying if specific setups or sessions are prone to higher rates of FOMO or late entries.
- Comparing execution quality between different months to validate process improvements.
- Detecting hidden sequences, such as a large loss leading to immediate revenge-based oversizing.
Known limitations
Cannot analyze trades without journal data. Does not provide financial advice or trade signals. Requires clear labels for P&L, risk, and setup names to perform impact quantification.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 5 days ago
- Passed all security checks, Safe to install