Back to directory

Finance Skills

A collection of AI agent skills for financial analysis and trading, covering market data, valuation, earnings analysis and social-feed reading, for educational use.

Finance Skills

Finance Skills is a collection of agent skills for financial analysis and trading, built on the Agent Skills open standard, and explicitly for educational and informational purposes rather than financial advice. It installs through general-purpose plugin or skill command-line tools, either as grouped plugin bundles for Claude Code, Codex and Cursor, or as individual skills.

Its market-analysis skills cover company valuation combining discounted cash flow, relative and sum-of-the-parts methods, earnings previews and recaps, analyst estimate trend analysis, ETF premium and discount tracking, options payoff charts, SaaS valuation compression, a trend-and-volatility-contraction strategy analysis, stock correlation for pair-trading candidates, and liquidity analysis using spread, volume and market-impact measures, mostly built on the yfinance market-data library. A separate group of read-only social-reader skills covers feeds such as Twitter/X, Discord, LinkedIn, Telegram and Y Combinator, plus a generic fallback for other sources.

It is written in JavaScript and released under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.