Trader Memory Core keeps one thesis object per investment idea, so what you thought, what happened and what you learned survives across conversations. It registers theses from screener outputs, moves them through IDEA, ENTRY_READY, ACTIVE and CLOSED states, attaches position sizing, trims and closes positions, and lists which theses are due for review.
When a position closes it writes a postmortem with P&L, lessons and, when a market data key is available, MAE and MFE metrics. State lives in local YAML files with an index, and the skill keeps records without giving advice.
What You Get
- One validated YAML thesis file per idea in a state folder, with a JSON index
- A command line for ingest, list, transition, open-position, trim, close and terminate actions
- A review-due list for a chosen date and a portfolio summary
- A postmortem report in a journal folder with P&L, lessons and optional MAE and MFE
Common Use Cases
- Registering the candidates from a screener run as theses to follow
- Recording entries, trims and exits so a position’s history stays complete
- Closing a position and writing the postmortem that feeds a weekly or monthly review
What Makes It Unique
Other skills produce a result and forget it. This one is the memory they share: its thesis files are the input for the performance digest, the postmortem skill and the coach. Schema validation protects the state, and the instructions tell the agent never to edit thesis files by hand to work around a missing dependency.
Under The Hood
The agent runs a Python command line tool from the shell. It reads screener output files and writes thesis YAML files, an index JSON and journal postmortems into state folders on your machine. The tool needs PyYAML and Python 3.10 or later. Postmortems can fetch price history from the Financial Modeling Prep API when a key is available, to compute MAE and MFE. Everything else is local, with no other network use.