skills.rest
darkounus90
darkounus90COMMUNITY
Explore all skills by this author →
GitHub

edge-candidate-agent

Generate research tickets and export Phase I-compatible strategy specifications for trading pipelines.

1|Updated Feb 18, 2026
Search Tags:#machine learning#data analysis#trading#strategy spec#research ticket
One-click install
npx skills add https://github.com/darkounus90/BOTTX3 --skill edge-candidate-agent-darkounus90
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: edge-candidate-agent
Source: https://github.com/darkounus90/BOTTX3/tree/main/.agents/skills/edge-candidate-agent
Command: npx skills add https://github.com/darkounus90/BOTTX3 --skill edge-candidate-agent-darkounus90

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, pandas, numpy, scikit-learn, uv, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the process of generating research tickets from market observations and exporting them as pipeline-ready strategy specifications, reducing manual effort and speeding up the trading pipeline.

Core Features & Use Cases

  • Edge Research Ticket Generation: Automatically detects market patterns and generates structured research tickets from EOD observations.
  • Strategy Spec Export: Converts validated tickets into Phase I-compatible strategy specifications for use in trading pipelines.
  • Use Case: Imagine you're analyzing market data for potential trading opportunities. Use this Skill to automatically detect patterns, generate research tickets, and export the specifications for further analysis and trading.

Quick Start

Run the auto-detection script on the latest market data to generate research tickets.

Frequently Asked Questions about edge-candidate-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate research ticket generation from market observations?▼

To generate research tickets automatically, you run an auto-detection script on your latest market data. This process analyzes EOD observations to detect market patterns and outputs structured research tickets, reducing manual effort in your trading pipeline.

How do I export Phase I-compatible strategy specifications for trading pipelines?▼

Exporting Phase I-compatible strategy specifications requires converting validated research tickets into a pipeline-ready format. This Skill takes your validated tickets and automatically exports them as strategy specifications ready for downstream analysis and trading pipeline execution.

Do I need Python and machine learning libraries to generate trading strategy specs?▼

Yes, Python and various libraries are required for data analysis, machine learning, and pipeline validation. You need PyYAML, pandas, numpy, scikit-learn, and uv installed to run the auto-detection scripts and export strategy specifications successfully.

What is the best way to convert validated research tickets into pipeline-ready strategy specs?▼

The best way to convert validated research tickets into pipeline-ready strategy specs is by automating the export process. This Skill handles the conversion directly, transforming validated tickets into Phase I-compatible strategy specifications for immediate use in trading pipelines.

Can I use scikit-learn and pandas for market pattern detection in trading analysis?▼

Yes, you can use scikit-learn and pandas for market pattern detection in trading analysis. This Skill leverages these libraries alongside numpy to process EOD market observations, detect patterns automatically, and generate structured research tickets for trading strategy development.

What are the limitations of automating trading strategy spec exports from EOD data?▼

Limitations of automating strategy spec exports include reliance on EOD observations rather than real-time market data, and dependency on Python libraries like pandas, numpy, and scikit-learn. The process is designed for Phase I-compatible strategy specifications and may not cover all advanced pipeline validation scenarios.

Related Skills

Explore More Software Engineering Skills→
ginaechoginaecho

agentic-labeling

Automate dataset clustering, feature engineering, and cluster interpretation with multi-agent architecture.

Community
Advanced
4tie4tie

profitable-strategy-discovery

Discover profitable crypto trading strategies via AutoQuant and Freqtrade backtesting.

Community
Advanced
thanhtai040805thanhtai040805
2

ml-strategy

Forecast future returns and generate trading signals using sklearn models.

Community
Intermediate
IhsanDanish25IhsanDanish25
2

edge-candidate-agent

Convert EOD market observations into research tickets and candidate specs.

Community
Advanced