Skip to content
SkillScript-led1,985 tokens in use

Trade Performance Coach

Reviews closed trades, partial exits and monthly aggregates for process adherence, risk discipline and execution, with evidence-tied behavior flags and next-session rules.

7,430 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/trade-performance-coach

Skill label

measured from its files

What installing Trade Performance Coach costs

96tokens idle
1,985tokens in use
6,278tokens, 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/review_trade_performance.py.

Touches

shelldetectednetworkdetectedwrites filesdetected

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 →
Good
  • Frontmatter12/15
  • Structure17/25
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources13/15

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 142
  • Reaches the network−10

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

    scripts/review_trade_performance.py, line 110
  • Writes files−8

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

    scripts/review_trade_performance.py, line 837

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

Trade Performance Coach reads recorded trade outcomes, postmortem findings, risk plans and journal notes, and writes a coaching report for the human trader. It covers process adherence, risk discipline, execution quality, possible behavior patterns such as FOMO entry, revenge trade, stop moved or size creep, next-session operating rules and reflection questions.

A deterministic Python script works from local JSON or YAML-style records and tolerates partial input by marking missing evidence as unclear. The skill is a process review only: it never says to buy, sell or size a security, and it is not therapy.

What You Get

  • A coaching report for a single trade, a partial close or a monthly aggregate
  • Process, risk and execution findings checked against your own risk plan
  • Behavior pattern tags with the evidence behind each one, in non-diagnostic language
  • Next-session operating rules and questions for reflection

Common Use Cases

  • Reviewing a closed trade to decide whether a loss was a process error, an execution error or acceptable variance
  • Checking a month of trades for repeated rule violations or size creep
  • Turning postmortem findings into a short list of rules for the next session

What Makes It Unique

It is built around guardrails: no buy or sell advice, no diagnosis, and no invented evidence. Incomplete input produces a review-required or journal-only result and a request for missing records. Numeric fields are validated, and the command stops with a field-specific error before any report is written when a value is invalid.

Under The Hood

The agent runs a Python script from the shell on a JSON record you supply, then writes reports into an output folder. The script works locally, needs no API key and makes no network calls. It is designed to take input from the trader memory and signal postmortem skills, and its numeric inputs such as planned risk, portfolio heat and consecutive losses are checked for valid, nonnegative values before it runs.

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