Trader Memory Core

This is a state machine for tracking investment ideas from screener output through position close. It serializes thesis objects to YAML with lifecycle transitions (IDEA → ENTRY_READY → ACTIVE → CLOSED), position sizing, fractional share support for IBKR and other brokers, and postmortem reports with MAE/MFE analysis. Built for tying together the other trading skills on this marketplace: kanchi, earnings-trade-analyzer, VCP, PEAD, CANSLIM. The manual ingest path lets you backdate entries from broker statements. The CLI launcher uses uv when available to handle jsonschema dependency issues across different working directories. It's accounting infrastructure, not strategy. If you're running multiple screeners and forgetting what you thought three weeks ago, this keeps the receipts.

skills.sh installs: 3.6K
GitHub stars: 3.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tradermonty/claude-trading-skills --skill trader-memory-core --agent claude-code

Installs into .claude/skills of the current project.

Files

Trader Memory Core

Overview

Persistent state layer that bundles screening → analysis → position sizing → portfolio management outputs into a single "thesis object" per investment idea. Tracks what you thought, what happened, and what you learned — across conversations.

Phase 1 supports single-ticker theses: dividend_income, growth_momentum, mean_reversion, earnings_drift, pivot_breakout.

When to Use

After a screener (kanchi, earnings-trade-analyzer, vcp, pead, canslim, edge-candidate-agent) produces candidates
When transitioning a thesis from IDEA → ENTRY_READY → ACTIVE → CLOSED
When attaching position-sizer output to a thesis
When checking which theses are due for review
When closing a position and generating a postmortem with lessons learned

Prerequisites

Python 3.10+
pyyaml (already in project dependencies)
jsonschema (already in pyproject.toml; required by thesis_store.py and every command that imports it, including thesis_ingest.py and thesis_review.py)
FMP API key (optional, only for MAE/MFE calculation in postmortem)