qc-deep-feature-forensics12-dimensional technical feature attribution engine — compares winner vs loser trade entry conditions using RSI, Bollinger, MACD, volume surge, gap, and more...
Install via ClawdBot CLI:
clawdbot install tltby12341/qc-deep-feature-forensicsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated May 12, 2026
A quant fund uses this skill to analyze entry conditions of winning vs losing trades in their backtest. By extracting 12 technical features, they identify which factors (e.g., volume surge, gap percentage) most contribute to profitability, allowing them to refine their strategy and filter out low-probability setups.
Individual traders run this skill on their own trade logs to understand why some trades performed better. The what-if simulation helps them test hypothetical rules (e.g., avoid trades with RSI > 70) to improve future entries without risking real capital.
Risk managers at a hedge fund use the feature attribution to detect when winning trades share common microstructures (e.g., strong gaps with volume confirmation). This insight helps set dynamic risk limits and adjust position sizing based on market conditions.
Researchers developing trading algorithms use the skill to validate new entry signals. The statistical comparison of winners vs losers provides empirical evidence for which indicators matter, aiding in feature selection for machine learning models.
Trading academies incorporate this skill into their curriculum to teach students how to conduct post-trade analysis. By running it on simulated trades, students learn to objectively evaluate their decision-making and develop data-driven trading plans.
Offer a premium SaaS platform that integrates this skill, allowing users to upload their trade history and receive automated forensic reports. Revenue comes from monthly or annual subscriptions with tiered pricing based on report frequency and number of trades analyzed.
Provide one-on-one coaching services where a coach runs this skill on clients' trades and interprets results to recommend personalized trading improvements. Revenue is from session fees or packages.
License the skill as an API that other trading platforms (e.g., brokerages, portfolio management tools) can integrate to offer advanced analysis features to their users. Revenue from licensing fees per API call or flat monthly fee.
💬 Integration Tip
To integrate, ensure the Python environment meets pandas, numpy, and yfinance dependencies, and provide a user interface for uploading CSV trade logs; cache management is automatic but pre-populate cache for offline use.
Scored May 12, 2026
Crypto news search, AI ratings, trading signals, and real-time updates via the OpenNews 6551 API. Supports keyword search, coin filtering, source filtering,...
A股股票十维深度分析（1000分制）。当用户输入「查询股票 <代码>」「分析股票 <代码>」「股票 <代码>」时自动触发。包含：基本信息、财务数据、技术分析、资金流向、市场情绪、风险提示、机构持仓、估值分析、股东结构、消息面，最后输出综合评分和投资建议。
Orchestrates AI-driven analysis and response to service failures by extracting logs, diagnosing issues, and recommending fixes or controlled restarts.
Provides real-time global financial data analysis including central bank policies, macro indicators, market trends, valuations, and risk metrics with source...
Use HackRF One SDR for frequency scanning, IQ capture, signal analysis, waterfall generation, and demodulation. Use when the user wants to scan radio frequen...
Create a calm seasonal closet swap checklist for rotating clothes, shoes, accessories, storage bins, repairs, weather readiness, and reset tasks without dona...