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.