trade-journal
Skill37 starsChanged 37 days agoMITView on GitHub
Use when reviewing trading performance and decisions. Covers what to record, separating process from outcome, identifying real patterns in your own behavior, and turning a review into a rule change. Trigger on "review my trades from last month", "help me set up a trading journal", "i keep losing on the same kind of trade". Do not use for writing the risk rules themselves — see the risk-management skill.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- PatrickSUDO/fadacai-portfoliotheir own version, first seen Nov 13, 2026
- bocodes1/claude-skillstheir own version, first seen Oct 11, 2026
- IngAs8/ClaudeSkilltheir own version, first seen Sep 28, 2026
- Serennity007/claude-trading-skills-67their own version, first seen Aug 25, 2026
- NT-NinjaTrader/mcp-skillstheir own version, first seen Jul 25, 2026
- ZICXR/A-Stock-Skillstheir own version, first seen Jun 22, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- agiprolabs/claude-trading-skills★ 366same name
- PatrickSUDO/fadacai-portfolio★ 145same name
- ZICXR/A-Stock-Skills★ 26same name
- jackson-video-resources/skills★ 17same name
- NT-NinjaTrader/mcp-skills★ 8same name
- tusharagg1/aifolimizer★ 2same name
- bocodes1/claude-skills★ 0same name
- IngAs8/ClaudeSkill★ 0same name
- Serennity007/claude-trading-skills-67★ 0same name
- Yahmez3/Claude-Skills★ 0same name
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 repository137 other files it gives its agents.
- agent-instructionsSkill
- agent-memorySkill
- hooksSkill
- plugin-developmentSkill
- skill-authoringSkill
- skill-reviewSkill
- slash-commandsSkill
- subagentsSkill
- agent-designSkill
- context-engineeringSkill
- fine-tuningSkill
- llm-cost-optimizationSkill
- llm-evaluationSkill
- llm-integrationSkill
- mcp-serverSkill
- ml-pipelineSkill
- model-selectionSkill
- prompt-engineeringSkill
- ragSkill
- structured-outputSkill
- api-designSkill
- background-jobsSkill
- cachingSkill
- djangoSkill
- event-driven-architectureSkill
- fastapiSkill
- graphqlSkill
- microservicesSkill
- nestjsSkill
- realtime-websocketsSkill
- spring-bootSkill
- competitive-analysisSkill
- lead-researchSkill
- product-analysisSkill
- resumeSkill
- user-researchSkill
- database-performanceSkill
- data-modelingSkill
- data-qualitySkill
- pandasSkill
- postgresSkill
- sparkSkill
- brand-guidelinesSkill
- generative-artSkill
- themingSkill
- ui-reviewSkill
- visual-designSkill
- architecture-decisionsSkill
- bug-fix-protocolSkill
- cli-developmentSkill
- code-reviewSkill
- debuggingSkill
- design-patternsSkill
- domain-modelingSkill
- git-workflowSkill
- legacy-modernizationSkill
- refactoringSkill
- repository-explorationSkill
- simple-designSkill
- system-designSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
After a losing streak, to determine whether the process or the market changed.
- Distinctive: line 56
Look for the revenge trade: the position taken immediately after a loss, larger than the rules permit, in a setup you would normally skip.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Trade Journal
Purpose
Learn from your own decisions rather than from your outcomes. A profitable trade taken against your rules is a bad trade that will be repeated; a losing trade taken correctly is a good one. Without a journal, these are indistinguishable.
When to Use
- Recording a trade at entry.
- Reviewing performance over a period.
- After a losing streak, to determine whether the process or the market changed.
- Identifying recurring mistakes.
Capabilities
- Structured trade recording: thesis, plan, execution.
- Process-versus-outcome separation.
- Pattern identification across trades.
- Rule-adherence tracking.
- Converting findings into rule changes.
Inputs
- The trades: entry, exit, size, and — crucially — the reasoning at the time.
- The plan as it was stated before the outcome was known.
- Market context.
Outputs
- A record that permits honest review.
- Identified patterns, not anecdotes.
- Specific rule changes with a date.
Workflow
- Record the thesis before the outcome — At entry, in writing: why, where the stop is, where the target is, and what would prove the thesis wrong. Written afterwards, this is a rationalization, and it will be a flattering one.
- Grade the process, not the profit and loss — Did you follow your rules? That is a binary question with a clear answer, and it is the only one you control.
- Categorize by setup and by mistake — Not by outcome. "Chased an extended entry" is a category. "Lost money" is not.
- Review a sample large enough to be meaningful — Twenty trades minimum. Any five trades can be attributed to anything.
- Look for the pattern, not the story — Are the losses concentrated in one setup? One time of day? Trades taken after a loss? These are behavioral patterns and they recur.
- Change one rule, and date it — Then measure whether it helped. Changing five rules at once means learning nothing.
Best Practices
- The most common and most costly journaling error is writing the thesis after the outcome is known. Memory is not merely imperfect; it actively reconstructs the past to justify the present.
- Grade every trade against the rules, independently of whether it made money. A rule violation that was profitable is the most dangerous event in trading, because it is reinforced.
- Look for the revenge trade: the position taken immediately after a loss, larger than the rules permit, in a setup you would normally skip. It is nearly universal and it is visible in the data.
- Track the trades you did not take. A rule that keeps you out of losers is doing its job, and it is invisible without a record.
- Screenshot the chart at entry. Your memory of what the setup looked like will drift toward whatever justifies the outcome.
- A journal you do not review is a diary. The review is the entire point.
Examples
A trade record that permits an honest review:
## 2026-06-14 | LONG NVDA | Momentum breakout
**Written at entry, before the outcome.**
Thesis : Breaking out of an 8-week base on 2.3x average volume. Relative
strength +6% vs SPY over 63 days. Earnings are 5 weeks away.
Entry : 118.40
Stop : 112.80 (below the base low; the breakout is invalid below it)
Target : 134.00 (the measured move; 2.8:1 reward-to-risk)
Size : 340 shares. Risk $1,904 = 0.95% of equity. Within the rules.
Invalidation: A close below 112.80, or a failed breakout that closes back
inside the base.
Regime check: trend up, volatility contracting. Breakouts are favored. PASS.
Pre-trade gate: PASS (stop set, risk within limit, sector exposure 18%/30%).
---
**Written at exit.**
Exit : 113.10 on 2026-06-21. Stopped out. -$1,802 (-0.90%).
Process grade: A. The setup met every criterion. The stop was where the thesis
was invalidated. The size was correct. It was executed as
planned and it did not work.
Outcome : Loss.
Lesson : NONE. This is what a losing trade taken correctly looks like.
Do not change anything on the basis of this trade. The breakout
failed. Some do.The review that finds the actual pattern:
Q2 review: 47 trades.
By outcome: 21 winners, 26 losers. Net +2.1%.
By process grade: 38 followed the rules, 9 did not.
The finding is in the second line, not the first:
Rule-following trades (38): +8.4% win rate 55% avg R +0.31
Rule-breaking trades (9): -6.3% win rate 22% avg R -0.70
Every rule-breaking trade shares one characteristic: it was entered within
90 minutes of closing a losing position. Seven of the nine were in a setup
graded "C" or worse. Six were oversized.
This is a revenge-trading pattern. It is not a strategy problem; the strategy
made 8.4% this quarter. It is a behavioral problem that cost 6.3%.
Rule change, effective 2026-07-01:
No new position within 2 hours of closing a losing trade. No exceptions,
no override. This is a hard gate, enforced in the pre-trade checklist,
not a resolution to be more disciplined.
Measure: count rule-breaking trades next quarter. Target: zero.Notes
- The revenge-trading pattern in the example is close to universal among discretionary traders and is invisible without a journal — every individual instance feels justified in the moment.
- The rule change is a mechanical gate, not a resolution. "I will be more disciplined" has never worked for anyone. A rule that cannot be overridden has.
- This is educational material about trading process and review, not financial advice.
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.

