- Home
- Skills
- Trading & Investing
- Trade Journal & Post-Mortem: Find Your Trading Leaks
Works with the AI Agents you already use
Trade Journal & Post-Mortem: Find Your Trading Leaks
Journal template, personal rulebook, pre-trade plan checks, process-graded post-mortems, and a stats script that shows where your own trades make and lose money. No buy/sell advice.
$15
Trade Journal & Post-Mortem: Find Your Trading Leaks
Example session with this skill installed
Here's my trade journal CSV for the last 3 months (40 trades, I tag mistakes and whether I followed my plan). Account is $25k. Where am I actually making and losing money?
- Read your context and instructions
- Compiled the trade journal
- Generated the data export
## Journal Analysis: 40 trades *Descriptive stats of your past trades only, not investment advice.* ### Overall | Net P&L | Win rate | Profit factor | Payoff ratio | Max drawdown | |---|---|---|---|---| | +$1,174 | 45% | 1.49 | 1.83 | $582 (2.3%) | **Longest loss streak:** 4. **8 losses were bigger than 1.5R**, meaning the stop wasn't honored or price gapped through it. ### Biggest finding: following your plan is your edge | | Trades | Net | Avg R | |---|---|---|---| | Followed plan | 22 | **+$1,727** | +0.30R | | Broke plan | 18 | **−$553** | −0.62R | If the 18 rule-break trades had simply not been taken, net P&L would have been about $553 higher. ### Cost of mistakes | Tag | Trades | Losses on tagged trades | Avg R | |---|---|---|---| | moved stop | 5 | $977 | −2.02R | | fomo entry | 8 | $614 | −0.43R | | oversized | 8 | $327 | −0.23R | "Moved stop" is your most expensive habit: 5 trades, all losers, averaging about twice your planned risk. ### By setup | Setup | n | Net | Profit factor | |---|---|---|---| | pullback | 14 | +$916 | 2.23 | | earnings gap | 12 | +$438 | 2.39 | | breakout | 14 | −$180 | 0.86 | Breakouts are slightly negative, but with only 14 trades that's tentative. Keep tagging and re-check at 30+. ### Possible US wash sales Several losses were followed by re-buying the same ticker within 30 days. Review these with a tax professional or check your broker's 1099-B. ### One change for next week **Place the stop order in the platform at entry and never widen it.** Measure: 100% of trades show a logged stop and no "moved stop" tags. Per-trade results with R-multiples are saved to trades_scored.csv.
trades_scored.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Most traders don't lose because they lack ideas. They lose because they can't see their own patterns: the setup that quietly bleeds money, the stop they keep moving, the size that creeps up after a losing streak. This skill makes those patterns visible from **your own trade records** and grades your **decisions**, not just your results. It works for stocks, ETFs, options, futures, forex and crypto. ## Five modes - **Setup:** a journal template (CSV/Sheets) plus a personal rulebook with your risk limits, setups, sizing, exits and no-trade conditions, in your words and with your numbers. - **Pre-trade plan:** a plan card with the position-size math, checked against your own rulebook (✅ / ⚠️ / ❌) before you enter. - **Single-trade post-mortem:** plan vs. actual, P&L and R-multiple, a process grade (A–F) independent of profit, and an outcome quadrant that flags "bad process, good outcome", the luck that reinforces bad habits. Ends with standard mistake tags and one specific, testable lesson. - **Journal analysis:** an included Python script reads your journal or a mapped broker export. It reports win rate, average win/loss, payoff ratio, profit factor, expectancy ($ and R), max drawdown and streaks, broken down by setup, side, weekday, plan adherence and mistake tag. It also flags trades with no stop, losses beyond 1.5R, and an approximate US wash-sale screen. - **Weekly / monthly review:** numbers, best and worst trades **by process**, the cost of each mistake, and **one** change for next period with a way to measure it. ## What it won't do It won't tell you what to buy, sell or hold, predict prices, rate tickers or recommend strategies. It reviews whether you followed **your** plan and what **your** history shows. The tax flags are a screen only, to confirm with a tax professional. If a conversation shows signs of chasing losses or money you can't afford to lose, it responds with care and suggests stepping back. *Not investment advice. Descriptive statistics of past trades only.*
Doesn't give buy/sell recommendations, predict prices or rate tickers. Analysis covers only the trades you provide. Broker exports may need column mapping. The wash-sale screen is approximate (it ignores options, other accounts and substantially identical securities), so confirm with a tax professional. Not investment advice.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Permissions
Terminal/Shell runs the included journal_stats.py (Python standard library only, no network calls, no broker connection). Read Files reads the journal CSV you provide. Write Files saves the per-trade results CSV.