trade-journal
Structured trade logging, performance review, behavioral pattern detection, and strategy attribution for systematic improvement
By agiprolabs · 398 installs
npx skills add agiprolabs/claude-trading-skills --skill trade-journal
Source repository · Upstream listing
Trade Journal
Structured trade journaling for systematic improvement. Log every trade with context, review performance at multiple cadences, detect behavioral patterns that destroy edge, and attribute returns to specific strategies.
Why Journaling Matters
Most traders fail not from bad strategies but from bad behavior. A trade journal transforms subjective "feel" into objective data:
Strategy Attribution : Know which setups actually make money vs. which feel profitable
Behavioral Detection : Catch revenge trading, FOMO entries, and premature exits before they compound
Pattern Recognition : Discover that your Monday morning trades lose money, or that you cut SOL winners too early
Accountability : Written rationale before entry forces deliberate decision making
Improvement Tracking : Measure whether changes to your process actually improve results
Without a journal, you optimize on noise. With one, you optimize on signal.
Trade Record Structure
Every trade record captures context at entry and outcome at exit. See references/record format.md for the complete 18 field schema.
Minimum Required Fields
Strategy Tagging
Use consistent tags to enable performance attribution:
Category Tags
Momentum momentum breakout , trend continuation , pullback entry
Mean Reversion range fade , oversold bounce , deviation snap
Event Driven listing play , catalyst trade , news reaction
On Chain whale follow , wallet copy , flow signal
DeFi lp entry , yield farm , arb capture
Rationale Templates
Write rationale before entering. Templates by setup type:
Storage Format
The journal uses JSON for structured querying and CSV for spreadsheet compatibility.
JSON Format (Primary)
CSV Format (Export)
Analytics from Journal Data
Win Rate by Strategy
Performance by Time of Day
Profit Factor by Token Type
Behavioral Pattern Detection
The journal enables detection of destructive trading patterns. See references/review framework.md for the full framework.
Revenge Trading
Rapid re entry after a loss, often with larger size:
FOMO Detection
Entering after large moves without proper setup:
Entry rationale is vague or missing
Setup quality self rated below 5/10
Entry during a move that already exceeded 1 ATR
Cutting Winners / Riding Losers
Tilt Detection
Size escalation after losses suggests emotional trading:
Review Cadence
Daily Review (5 minutes)
How many trades today? P&L?
Did I follow my rules on every trade?
Any emotional decisions?
One thing I did well, one thing to improve
Weekly Review (30 minutes)
Win rate and profit factor by strategy
Behavioral pattern check (revenge trades, tilt, FOMO)
Best and worst trade of the week — what made them different?
Strategy performance vs. expectations
Adjust position sizing if needed
Monthly Review (2 hours)
Full strategy attribution analysis
Equity curve review — drawdown periods and recovery
Compare actual vs. planned risk per trade
Performance by token type, time of day, day of week
Are any strategies consistently losing? Consider dropping them
Review and update strategy parameters
See references/review framework.md for detailed review checklists and questions.
Partial Exits and Scaled Entries
Real trading involves scaling in and out. The journal handles this with child records:
See references/record format.md for full documentation of partial exit handling.
Files
References
references/record format.md — Complete 18 field trade record schema, field descriptions, tagging taxonomy, CSV/JSON examples, partial exit handling
references/review framework.md — Daily/weekly/monthly review checklists, behavioral red flags, performance decay detection
Scripts
scripts/trade logger.py — CLI trade logger: add, list, update, compute stats, filter, demo mode (stdlib only)
scripts/journal analyzer.py — Journal analysis: strategy performance, behavioral patterns, time based analysis, demo mode (stdlib only)
Dependencies
Both scripts use Python standard library only ( json , datetime , argparse , collections ). No external packages required.
Disclaimer
This skill provides tools for trade record keeping and performance analysis. It does not provide financial advice, trading recommendations, or guarantee any trading outcomes. All analysis is informational and for personal review purposes only.