Agentic Quant Research — AI skill for Claude Code
Front page of my AI quant research system.
How to install Agentic Quant Research
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open oscar-chw/agentic-quant-research and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agentic Quant Research does
Front page of my AI quant research system. Centrepiece: a Claude Code orchestrator and its subagents, under a gated work graph, turned López de Prado's Advances in Financial Machine Learning into 1,805 cited claims and a tested Python library: 1,400+ claims verified by passing tests (758 tests, 0 failing). Also links its vault and harnesses.
Alternatives in AI
- Scikit Learn — Machine learning with scikit-learn library 6.4k ★
- Claudekit AI ML Tools — AI and machine learning tools collection 1.9k ★
- ML Training Pack — Machine learning model training skills 1.6k ★
README
AI Quant Research System: From a Textbook to a Tested Library with Gated Agents
[](https://github.com/oscar-chw/agentic-quant-research/actions/workflows/ci.yml) [](https://github.com/oscar-chw/agentic-quant-research/actions/workflows/lint.yml)
This is the front page of Oscar's AI quant research system: a vault that keeps book notes and measured results as cited, version-controlled notes, a harness whose gates decide when work is done, and AI coding agents that read, build and review. Its centrepiece is one complete build: over about four days in September 2026, a Claude Code orchestrator and its subagents turned López de Prado's *Advances in Financial Machine Learning* into 1,805 paraphrased, cited claims and a tested Python library. The result in this repository: 1,400+ extracted claims verified by passing tests (758 tests, 0 failing). Across the whole project, the orchestrator and about 140 AI subagents (per private session logs) completed 266 gated tasks.
How the parts connect (purple marks this repository; every other named repository is a separate component):
flowchart TB
OSCAR["Oscar
goals and review"]:::ext
GRAPH{"plan gate graph
exit 0 = done"}:::gate
AGENTS["AI coding agents
Claude Code, subagents"]:::step
subgraph VAULT["Vault: the second brain"]
direction LR
BOOK[("Book notes and
measured results
this repo")]:::key
PAPERS[("Paper layer
quant-research-vault")]:::data
end
LIB["pmlab library
and tests, this repo"]:::key
AH["agent-harness
rules, memory,
guard, work graph"]:::step
ASOF["asof-research
LLM proposes, code
scores, human decides"]:::step
PM["Polymarket-Crypto-5min
July 2026, separate,
not from the book"]:::ext
OSCAR -->|"goals, con
Related Skills
Capy Cortex
Autonomous memory and learning system for AI coding agents. LLM-powered knowledge extraction, triple fusion re
Equity Research Agent
Autonomous Tier-1 Equity Research & DCF Financial Modeling Agent. Produces 10-tab institutional Excel models,
Saurabh AI Systems
AI architect for GTM and martech. I design and ship production agentic systems for B2B sales and marketing: le
Continual Memory Policy Model
Experimental local-first memory-policy research for Codex and Claude Code, with delayed feedback and gated ada
University Research Agent
Tool-using AI agent with a responsive web chat interface. A Python backend runs an agentic loop on the Claude
Agentic Review Gate
Governed, auditable AI review platform: the review and approval work a team does by hand, as a webhook-trigger
Related Agents
Hva Desk
The HVA Desk — reads Meta insights by impression volume, runs the deterministic CLEAR scorer, and converts the
Fintech Frontend Engineer
Fintech frontend specialist. Invoke for frontend work in a fintech context: payment flows, financial data disp
Delivery Lead
Orchestrator and Scrum Master. Owns flow and gate transitions — no work advances between gates without its app