- Home
- Skills
- Trading & Investing
- worst setup pattern miner
worst setup pattern miner
Mines trade logs to isolate high-damage patterns and generates a data-backed "Stop Trading" playbook.
$5
Works with the AI Agents you already use
worst setup pattern miner
Example session with this skill installed
Analyze my last 50 trades from this CSV. Tell me why I keep losing on Tuesday mornings and what behavior is causing the biggest drawdown.
- Read your context and instructions
- Compiled the worst setup pattern
Executive Summary
The primary driver of drawdown is Tuesday morning 'Early Entries' during low-volatility regimes. This pattern occurred 8 times, resulting in -18.4R.
Top Combined Worst Pattern
Pattern: Tuesday Hesitation
- Time: Tuesday 09:30-10:15
- Behavior: Late entry after missing initial signal
- Result: 15% win rate, -2.3R average
- Stop Rule: No market entries before 10:15 AM on Tuesdays. Use limits only.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Traders often struggle to identify why they give back profits or where their execution quality collapses. Finding the specific environmental and behavioral variables that cause high-damage losses is difficult to isolate manually from messy journal data.
What it does
- Analyzes execution logs, trade journals, and broker statements to isolate negative expectancy patterns.
- Segments performance by market regime, volatility, time of day, session, and day of the week.
- Identifies behavioral correlations such as revenge trading, FOMO, and rule adherence failures.
- Calculates damage in R-multiples to rank patterns by their actual impact on the bottom line.
- Generates a concrete "Stop Trading" playbook with specific rules to avoid high-loss contexts.
Why this beats prompting it yourself
This skill goes beyond simple win/loss ratios by normalizing data into R-multiples and combining dimensions into compound pattern cards. It systematically audits behavior against environment, preventing you from missing the hidden correlations that generic prompts overlook.
Use cases
- Mining a quarterly trade log to find the specific hour that drains the most capital.
- Auditing execution quality to distinguish between good losses and bad behavior.
- Creating a "Friday Lunch" or "Post-Loss" restriction rule based on historical data.
- Isolating which setup variations consistently fail during low-volatility regimes.
Known limitations
Requires a minimum of 20 trades for statistical relevance. Findings are descriptive of past performance and may not predict future regime shifts.
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 at least 20 trades for valid mining. Works best with R-multiple data; dollar PnL analysis is less precise if risk sizes vary. Accuracy depends on the honesty of journal notes.
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