questflowai/investorskills

Investor Skills is an open-source library that turns durable investing judgment into portable, structured formats. It collects how great investors think, filter opportunities, size risk, and act under uncertainty — then structures those patterns so humans can study them and AI finance agents can apply them.

What it solves

Investor Skills provides a structured, portable way to turn the complex decision-making processes of legendary investors into clear, actionable instructions for AI agents. It bridges the gap between abstract investment philosophy and the specific, rule-based logic required for automated financial analysis.

How it works

Each "skill" is a plain-text package containing a SKILL.md file (the agent's instructions) and an optional invest.md file (the investment schema). These files define an investor's specific worldview, including their preferred market regime, risk parameters, sizing rules, and signal filters. You can load these packages into AI agents like Claude Code, Cursor, or Questflow to have them evaluate opportunities or monitor portfolios using the specific logic of investors like Warren Buffett, Jesse Livermore, or others.

Who it’s for

This library is for developers building AI finance agents and researchers who want to codify and test investment strategies. It is designed for anyone who wants to move beyond generic AI advice and apply the specific, proven judgment systems of history's greatest investors to their own workflows.

Highlights

  • Portable library of structured investment judgment systems.
  • Includes templates for creating your own custom investor skills.
  • Provides extensive reference material, including reading lists, podcasts, and YouTube channels for each investor.
  • Compatible with various AI agent harnesses that can read Markdown instructions.
  • Features a wide range of styles, from value investing and macro-trend following to crypto-specific strategies.

Related

  • Project
    WordPress/mcp-adapter

    An official WordPress package that exposes WordPress abilities as Model Context Protocol (MCP) tools and resources, allowing AI agents to interact with WordPress functionality in a standardized way.

  • Project
    Picrew/awesome-agent-harness

    A curated list of engineering resources and GitHub projects focused on building robust, secure, and reliable infrastructure for autonomous AI agents.

  • Project
    agentjido/jido

    Jido is an Elixir‑native autonomous‑agent framework. It defines immutable agents with a `cmd/2` contract, actions that transform state, and directives that describe runtime‑owned side‑effects. Built on GenServer and OTP supervision, it supports multi‑agent hierarchies, signal routing, plugins, and execution strategies (direct or FSM). AI/LLM integration is optional via companion packages (`jido_ai`, `req_llm`). Install via Hex, define agents/actions, and run them under `AgentServer` for production‑grade reliability.

  • Project
    zakirkun/guardian-cli

    An AI-powered penetration testing automation framework that orchestrates security tools and multi-agent AI to perform adaptive security assessments and evidence-backed reporting.