skills.rest
k1064190
k1064190COMMUNITY
Explore all skills by this author →
GitHub

edge-candidate-agent

Convert market observations into reproducible research tickets and strategy specs.

2|Updated Apr 6, 2026
Search Tags:#market analysis#backtesting#trade strategy#research ticket#trade pipeline
One-click install
npx skills add https://github.com/k1064190/stock-expectation --skill edge-candidate-agent-k1064190
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: edge-candidate-agent
Source: https://github.com/k1064190/stock-expectation/tree/main/.claude/skills/_archived/edge-candidate-agent
Command: npx skills add https://github.com/k1064190/stock-expectation --skill edge-candidate-agent-k1064190

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, PyYAML, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill transforms daily market observations into reproducible research tickets and Phase I-compatible candidate specs, facilitating trade strategy development and validation.

Core Features & Use Cases

  • Market Observation Conversion: Converts market observations, anomalies, or hypotheses into structured research tickets.
  • Edge Candidate Auto-detection: Daily auto-detection of edge candidates from EOD OHLCV data and optional human hints.
  • Ticket Export & Validation: Validates tickets and exports them as strategy.yaml and metadata.json for further analysis.
  • Integration with Pipeline: Pre-flight compatibility checks before running pipeline backtests to ensure seamless integration.
  • Use Case: If you have observed an interesting pattern in the market or an anomaly, use this Skill to turn it into a structured research ticket and export it for further analysis and potential trade strategy development.

Quick Start

Run the auto-detection script with the EOD OHLCV data and optional hints.

Frequently Asked Questions about edge-candidate-agent

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

FAQPage Schema
How do I convert market observations into reproducible research tickets for trade strategy development?▼

Converting market observations into reproducible research tickets involves transforming hypotheses and EOD OHLCV data into structured strategy specs. This process auto-detects edge candidates and exports them as validated strategy.yaml and metadata.json files for backtesting.

What is the best way to structure trade strategy hypotheses before running a backtest?▼

The best way to structure trade strategy hypotheses before backtesting is by converting them into Phase I-compatible candidate specs. This validates market observations and formats them into strategy.yaml files for seamless pipeline integration.

Do I need Python and pandas to auto-detect edge candidates from EOD OHLCV data?▼

Yes, you need Python with pandas, numpy, and PyYAML to auto-detect edge candidates from EOD OHLCV data. These dependencies support the scripts required to process market observations and output strategy specs.

How does pre-flight compatibility checking work for a trade strategy pipeline?▼

Pre-flight compatibility checking for a trade strategy pipeline works by validating research tickets before execution. It ensures exported strategy.yaml and metadata.json files meet structural requirements for seamless backtesting integration.

Can I use human hints to prioritize trade candidates from daily market anomalies?▼

Yes, you can use optional human hints to prioritize trade candidates from daily market anomalies. The auto-detection script combines these hints with EOD OHLCV data to identify and structure edge candidates into research tickets.

What file formats are exported when generating trade strategy candidate specs?▼

When generating trade strategy candidate specs, the exported file formats are strategy.yaml and metadata.json. These files contain the structured research ticket data needed for downstream analysis and backtesting.

Related Skills

Explore More Finance & Accounting Skills→
tradermontytradermonty
2.6k

us-market-bubble-detector

Score US equity market bubble risk using eight quantitative indicators.

Community
Advanced
pasie15pasie15

edge-candidate-agent

Convert daily market observations into edge research tickets and Phase I strategy specs.

Community
Advanced
Dorpeer95Dorpeer95

edge-candidate-agent

Automate daily OHLCV observations into edge research tickets and Phase I strategy specs.

Community
Advanced
644408071-design644408071-design
1

execution-model

Simulate slippage, market impact, and execution algorithms for backtesting.

Community
Advanced