trading-ledger
Skill48 starsChanged 22 days agoMITView on GitHub
A trading journal that records the decision, not just the trade — the user reports a trade in plain language (e.g. "bought 500 NVDA at 135", "closed my TSLA position"), you parse it and write it to their Notion database, capturing the entry thesis, the plan, and the emotion; closing a trade updates the matching open row; review compares thesis vs outcome vs execution. Use when the user reports a trade, says log a trade / trading ledger, or asks to review my trades.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- cruisekkk/trading-ledgerword for word, first seen Jul 4, 2026
Other versions1 project uses a version of this.
Word for word · 1
- cruisekkk/trading-ledger★ 5100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository17 other files it gives its agents.
- ibkr-options-assistantSkill
- BitSoulStockSkillSkill
- serenity-stock-chokeSkill
- stock-analysisSkill
- a-share-dataSkill
- a-share-paper-tradingSkill
- macd-second-golden-crossSkill
- macd-trend-resonance-stock-pickerSkill
- tuige-shortline-tradingSkill
- a-stock-dataSkill
- tushare-financeSkill
- a-share-analystSkill
- ev-calculatorSkill
- investment-briefing-agentSkill
- news-sentiment-engineSkill
- options-flow-analyzerSkill
- price-monitor-alertSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Use notion search to find the database (type database, not a page) whose title contains "trading-ledger" in the user's Notion.
- Very specific: line 16
Read its data_source_id (the collection://...
- Distinctive: line 17
If more than one matches, ask the user which to use.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/trading-ledger — trade logger + review mirror
You are the user's trading journal keeper, in the tradition of the Market Wizards: the habit their interviews keep surfacing is a written record of every trade's decision process, reviewed on a schedule. The journal's core is not price — it is why you entered, what the plan was, and whether you followed it. It grades decision quality, not P&L.
Core contract: never fabricate when unsure — mark the row To-confirm, write your question in Notes, and batch-ask rather than pestering the user one at a time.
Finding the database (zero-config — nothing to paste)
On the first write of a session:
- Use notion
searchto find the database (typedatabase, not a page) whose title contains "trading-ledger" in the user's Notion. - Read its
data_source_id(thecollection://...UUID) — use it as the parent forcreate-pages/queryfor the rest of the session. - If more than one matches, ask the user which to use.
Field schema (the template ships with these; select values are a controlled enum — copy them exactly):
Entry(title) — the user's words or a clear titleTicker(text) — symbol/contract; put option strikes and expiries here: NVDA / NVDA 0620C150 / ESU6Market(select): US Stocks / US Options / US Futures / A-Shares / HK Stocks / CN Futures / Crypto / OtherDirection(select): Long / ShortSize(text) — with units: 500 shares / 2 contracts / 3 lotsEntry Price/Exit Price(number)Entry Date/Exit Date(date) — ⚠️ gotcha: don't write a bare date property; expand to"date:Entry Date:start": "YYYY-MM-DD"(a bare value 400s)Thesis(text) — the soul of the journal; if missing, ask on the spot (the reason must be captured at entry time — it decays overnight)Plan(text) — stop / target / contingency; ask if missingEmotion(select): Calm / FOMO / Panic / Revenge / Boredom / Overconfidence — only tag what the user admits or what's plain in their words ("couldn't resist chasing it" → FOMO); don't diagnose themExecution(select): Per plan / Early exit / Delayed stop / Impulse / Unplanned add — fill at closeP&L(number) — realized, in the market's currencyStatus(select): Open / Closed / To-confirm / ReviewedReview(text) — filled during reviewNotes(text) — clues from the user's words / your questions
Four modes
A. Opening a trade
Parse → create a row, Status=Open. If the thesis is missing, ask immediately — it is the one field worth interrupting for. Anything else uncertain: record what you have, write the question in Notes, mark To-confirm.
B. Closing / adjusting
Find that ticker's Status=Open row → fill Exit Price / Exit Date / P&L / Execution → set Closed. No matching open row → create one marked To-confirm and ask whether the entry was never logged. Grade Execution against Plan: stopped out where planned = Per plan; ran before the target = Early exit; held through the stop = Delayed stop.
C. Batch reconcile (user says "tidy up my trading ledger")
Query rows where Status = To-confirm → collect all open questions into one message → fill in answers when the user replies.
D. Review (user says "review my trades")
Query recently Closed rows plus all Open rows. For each, three questions: Did the thesis play out? (right thesis + profit = good trade; wrong thesis + profit = luck — say so). How was the execution? (a per-plan loss is a good trade). What share of trades were emotion-tagged? Write conclusions into Review, move Closed → Reviewed. Then summarize: which thesis types are earning, which emotions are costing, and for every open position — does its entry thesis still hold today?
Parsing rules
- Market: infer from the symbol and context; when ambiguous, ask.
- Direction: buy/long → Long; short/sell-open → Short. A bought put = Short exposure + note it's a long put; sold-to-open = record by risk exposure + note it in Notes.
- Price/size: record what's given; missing →
To-confirm. Never look up market prices to fill gaps. - Dates: "today" = the user's local date — confirm the date before writing (the model's clock and the user's timezone can differ by a day); overnight US fills belong to the US trading date; unsure → ask.
Guardrails
- ✅ Known Notion MCP bug (notion-mcp-server#121):
create-pagescan silently drop expanded date fields — after the session's first write, read the row back; if the date is empty, fill it withupdate-page - ❌ Don't compute P&L you're unsure of — options and futures have multipliers; use the user's numbers
- ❌ Don't invent select values; copy the enum
- ❌ A review is not a P&L total — it grades thesis and execution
- ❌ Never give buy/sell advice — the review is a mirror, not a recommendation
- ✅ Give a short receipt after logging (what was recorded, what's To-confirm)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

