tradermonty/claude-trading-skills

Claude Code skills for equity investors and traders — market analysis, technical charting, economic calendars, screeners, and trading strategy development.

Claude Trading Skills – Overview

What it is

  • A collection of Claude Skills (small, reusable AI‑powered functions) that help individual investors run a structured, human‑in‑the‑loop trading workflow.
  • The repository ships the source code for each skill, a catalog, and ready‑to‑upload “.skill” packages that can be used in Anthropic’s Claude Web App or Claude Code.

Who it’s for

  • Time‑constrained investors who mainly hold long‑term ETFs or dividend stocks but occasionally do disciplined swing‑trading.
  • People who want a repeatable process for market‑review, risk‑management, trade‑planning, journaling and post‑trade analysis – not a fully‑automated signal service.

How it works

  1. Skills – Individual AI‑driven modules (e.g., market‑breadth‑analyzer, position‑sizer, trader‑memory‑core). Each skill takes specific inputs (public CSVs, API data from FMP, Alpaca, etc.) and returns a concise text or JSON output.
  2. Workflows – YAML manifests that chain skills together in a fixed order, inserting human‑decision gates where the user reviews the AI output before proceeding. Example workflows:
    • market‑regime‑daily – 15‑minute market check.
    • core‑portfolio‑weekly – Weekly portfolio review (requires Alpaca or CSV fallback).
    • swing‑opportunity‑daily – Finds swing‑trade candidates when risk limits allow.
    • trade‑memory‑loop – Journals closed trades and runs a post‑mortem.
    • monthly‑performance‑review – Summarises performance and suggests rule tweaks.
  3. Execution options
    • Claude Web App – Upload the pre‑built .skill zip, enable code execution, then run a workflow via the UI.
    • Claude Code (desktop/CLI) – Clone the repo, copy skill folders to ~/.claude/skills/, and invoke them from the local Claude environment.
  4. Data sources – Optional paid APIs (FMP, FINVIZ Elite, Alpaca) enhance certain skills; a “no‑API starter path” uses only public CSVs, chart screenshots, or local calculations.

Key benefits

  • Human‑centered: AI only suggests, never places orders.
  • Modular: Pick the skills you need; the catalog is auto‑generated from skills-index.yaml.
  • Open‑source: All skill definitions, manifests, and packaging scripts are publicly available under MIT.
  • Extensible: New skills can be added and referenced in workflows; a schema validator (scripts/validate_workflows.py) ensures consistency.

Typical first‑week steps

  1. Install Python 3.10‑3.13.
  2. Follow Your First Week docs to run the “no‑API” five‑skill starter path.
  3. Review the generated market‑posture summary and create a journal entry with trader‑memory‑core.
  4. Gradually add paid‑API integrations (Alpaca, FMP) to unlock richer data.

Cost considerations

  • Claude Web Skills are billed through your Anthropic account (Free, Pro, Max, etc.).
  • Data‑API subscriptions are optional; the core workflow works with free public CSVs.

Related project

  • The Hermes Trading Research Agent Work Package bundles these skills into a ready‑to‑run agent that offers slash‑commands like /pre‑market‑routine and /weekly‑portfolio‑review.

Quick reference

Category Example skills Typical integration
Market Regime market‑breadth‑analyzer, uptrend‑analyzer, exposure‑coach public CSV, optional FMP
Core Portfolio portfolio‑manager, kanchi‑dividend‑review‑monitor Alpaca, FMP
Swing Opportunities vcp‑screener, breakout‑trade‑planner FMP, FINVIZ
Trade Planning position‑sizer, technical‑analyst local calculation
Trade Memory trader‑memory‑core, signal‑postmortem local YAML
Strategy Research backtest‑expert, manifoldbt‑backtester local + optional data

Bottom line: Claude Trading Skills is a genuine, open‑source toolkit that leverages Anthropic’s Claude Skills to help individual investors build a disciplined, AI‑augmented decision process while keeping final control firmly in human hands.

Related

  • Project
    caiovicentino/polymarket-mcp-server

    Polymarket MCP Server is a Python‑based MCP server that lets Claude (or any LLM) autonomously discover, analyse, trade, and monitor Polymarket prediction‑market positions. It offers 45 tools across market discovery, analysis, trading, portfolio management, and real‑time monitoring, all guarded by configurable safety limits and full‑node authentication. A web dashboard provides visual control, and the project includes real‑API tests, MIT licensing, and detailed docs for both demo (read‑only) and live‑trading setups.

  • Project
    borghei/Claude-Skills

    Claude-Skills is a library of 385 ready-made skills that turn AI assistants into specialists for tasks like board preparation, product planning, compliance audits, code review, and marketing. It bundles Python tools for accurate computation and works across 11 AI assistants, with an ask-before-write approach to avoid guesswork.

  • Project
    staskh/trading_skills

    An AI-powered market analysis tool that consolidates technicals, fundamentals, and portfolio management into a conversational interface for traders.

  • Project
    Prorise-cool/Claude-Code-Multi-Agent

    Claude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`. Key points: - Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`. - Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates. - Skills are defined by `SKILL.md` files and are auto‑discovered. - Works entirely locally (no external API), integrates with Git, and is MIT‑licensed. Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.

  • Project
    daymade/claude-code-skills

    A marketplace of Claude Code plugins (skills) with a production‑hardened meta‑skill (`skill‑creator`) that helps you build, validate, and package new skills, plus dozens of ready‑made skill suites for docs, macOS/iOS dev, financial data, GitHub ops, and Claude Code power‑user workflows.