edge-candidate-agent

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

Updated Mar 1, 2026
One-click install
npx skills add https://github.com/Dorpeer95/stocks-trading --skill edge-candidate-agent-dorpeer95
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: edge-candidate-agent
Source: https://github.com/Dorpeer95/stocks-trading/tree/main/.claude/skills/edge-candidate-agent
Command: npx skills add https://github.com/Dorpeer95/stocks-trading --skill edge-candidate-agent-dorpeer95

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Automates turning daily market observations into reproducible edge research tickets and Phase I-compatible strategy specs.

Core Features & Use Cases

  • Auto-detect edge candidates from EOD OHLCV and hints
  • Export artifacts as strategy.yaml + metadata.json for trade-strategy-pipeline Phase I
  • Validate interface compatibility against edge-finder-candidate/v1

Quick Start

Run the edge-candidate-agent to auto-detect candidates and export Phase I artifacts for a sample set.

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 converting daily OHLCV market data into reproducible edge research tickets?

You can automate turning daily OHLCV observations into edge research tickets by running an agent that auto-detects candidates from EOD data and applies hints to generate reproducible strategy specs. This enforces Phase I constraints during detection to ensure validity.

What is the best way to validate edge-finder-candidate compatibility for a trading strategy pipeline?

The best way to validate edge-finder-candidate compatibility is to run interface validation against the edge-finder-candidate/v1 specification. This checks your strategy artifacts and confirms they meet the required Phase I constraints before pipeline execution.

How do I export strategy artifacts to match the trade-strategy-pipeline Phase I format?

To export Phase I artifacts, the agent generates strategy.yaml and metadata.json files from detected edge candidates. These files are exported directly to the strategies/<candidate_id> directory, ensuring format compatibility with downstream trade-strategy-pipeline phases.

Do I need pyyaml to generate Phase I-compatible strategy specifications from market signals?

Yes, you need pyyaml installed because the agent exports strategy specifications in YAML format. The dependency ensures proper serialization of the strategy.yaml artifacts required for Phase I trade-strategy-pipeline compatibility.

Can I use daily EOD OHLCV data and hints to auto-detect edge candidates for quantitative research?

Yes, you can input daily EOD OHLCV data alongside market hints to auto-detect edge candidates. The agent processes these observations to identify potential trading edges and converts them into structured research tickets for quantitative analysis.

What are the limitations when enforcing Phase I constraints on edge candidate detection?

Phase I constraints limit edge candidate detection to specific interface compatibility rules defined by edge-finder-candidate/v1. The validation process ensures exported artifacts meet these strict structural requirements, rejecting any candidates that fail interface or constraint checks.