Skip to content
SkillScript-led5,454 tokens in use

Trader Memory Core

A persistent thesis store that tracks each trade idea from screener output to closed position, with state transitions, position data, review dates and postmortems.

7,430 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/trader-memory-core

Skill label

measured from its files

What installing Trader Memory Core costs

97tokens idle
5,454tokens in use
12,131tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/fmp_price_adapter.py, scripts/thesis_ingest.py, scripts/thesis_review.py, scripts/thesis_store.py, scripts/thesis_store_parts/lifecycle.py, scripts/thesis_store_parts/persistence.py, scripts/thesis_store_parts/positions_equity.py, scripts/thesis_store_parts/positions_futures.py, scripts/thesis_store_parts/queries.py, scripts/thesis_store_parts/validation.py, scripts/trader_memory_cli.py.

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure19/25
  • Examples15/15
  • Output15/15
  • Size13/15
  • Resources6/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 35
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 50
  • Reads credentials−15

    does this on the machine, and the frontmatter does not say so

    scripts/fmp_price_adapter.py, line 27
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/thesis_review.py, line 133

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity36
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers