skills.rest
santoosaraujo
santoosaraujoCOMMUNITY
Explore all skills by this author →
GitHub

strategy-dev-manager

Orchestrate quantitative strategy development from paper ingestion to validated factor implementation.

Updated Jul 29, 2026
Search Tags:#research#finance#backtesting#trading#quantitative#alpha
One-click install
npx skills add https://github.com/santoosaraujo/vibe-trading-claude --skill strategy-dev-manager
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: strategy-dev-manager
Source: https://github.com/santoosaraujo/vibe-trading-claude/tree/main/.claude/skills/strategy-dev-manager
Command: npx skills add https://github.com/santoosaraujo/vibe-trading-claude --skill strategy-dev-manager

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill bridges the gap between academic research and production-ready trading strategies by automating the ingestion, implementation, backtesting, and monitoring of quantitative factors.

Core Features & Use Cases

  • Automated Ingestion: Parses academic papers and research reports to extract quantitative signals and strategy rules.
  • Lifecycle Management: Handles the full workflow from hypothesis creation and backtesting to persistent artifact tracking and decay monitoring.
  • Use Case: A researcher can provide a PDF of a new momentum paper, and the skill will automatically extract the factor formula, scaffold the signal engine, run a backtest, and register the factor for live monitoring.

Quick Start

Use the strategy-dev-manager skill to ingest the paper at papers/momentum_research.pdf and implement it as a new factor.

Frequently Asked Questions about strategy-dev-manager

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

FAQPage Schema
How do I automate quantitative factor implementation from academic research papers?▼

Automated quantitative factor implementation parses academic research papers to extract strategy rules, scaffolds the signal engine, and runs backtests. It bridges academic research and production by tracking persistent artifacts and monitoring statistical decay.

What is the best way to manage the lifecycle of a quantitative trading strategy from hypothesis to backtesting?▼

Managing a quantitative trading strategy lifecycle requires orchestrating hypothesis creation, automated backtesting, signal engine scaffolding, and statistical decay monitoring. This approach maintains persistent research state from initial paper ingestion through validated factor implementation.

Can I use pandas and numpy to scaffold a signal engine for backtesting trading strategies?▼

Yes, scaffolding a signal engine for backtesting trading strategies utilizes pandas and numpy dependencies. The workflow integrates local data loaders and backtest runners to validate quantitative factors extracted from research papers.

Does quantitative strategy development require integration with local data loaders and artifact storage?▼

Quantitative strategy development requires integration with local data loaders, backtest runners, and artifact storage systems. This integration maintains persistent research state and enables automated ingestion of academic papers for factor implementation.

Why do quantitative factors experience statistical decay and how is it monitored?▼

Statistical decay in quantitative factors occurs when signal effectiveness diminishes over time. Monitoring decay involves tracking persistent artifacts throughout the research-to-production workflow to ensure validated factor implementation remains reliable.

What are the limitations of automated paper ingestion for quantitative trading strategy development?▼

Automated paper ingestion for quantitative trading strategy development depends on parsing academic papers with rapidocr_onnxruntime. Limitations include the need for local data loaders and backtest runners to validate extracted factor formulas before live monitoring.

Related Skills

Explore More Finance & Accounting Skills→
owenliangowenliang
19

arxiv-search

Search arXiv by keyword and retrieve paper titles and summaries.

Community
Intermediate
hxhyyyhxhyyy

factor-research

Evaluate trading factor predictive validity via IC/IR testing and quantile backtesting.

Community
Advanced
VernonOYVernonOY
81

alpha-evaluate

Computes factor quality via IC, ICIR, quintile, and robustness analyses.

Community
Advanced
koreal6803koreal6803
407

finlab

Automate quantitative trading strategy development and backtesting with FinLab.

Community
Advanced