Directory
Agent workflows for your own trading process. Filter by category, tag or skill level. Every entry is education only, with no tickers or signals.
Build a private pre-market scan digest from your own written rules
A script applies the screening rules you wrote down to your own universe and computes every number. An agent groups the results and sends you a private list with chart links to review before the open.
Watchlists & alert hygieneClassify your watchlist by trend stage every night
Each evening an agent applies your own numeric rules to label watchlist names by Weinstein stage (1-4) and logs only label changes that persist for your chosen minimum weeks; output goes to your journal after you review a diff.
Watchlists & alert hygieneKeep your TradingView watchlists in sync with your own stage tags
An agent proposes adds and removals for your own TradingView watchlists when your stage tags change, shows you the diff first, and only writes after you confirm.
Watchlists & alert hygieneGive every price alert an expiry date and clear stale ones weekly
An agent applies only the mechanical expiry and duplicate rules you give it to a TradingView alert list you supply (a file you copied, or a local read-only MCP output), and produces a dry-run clean-up table. It never judges which levels matter.
Earnings & event prepRecord each earnings date with a source, or "unknown"
Before each report, an agent gathers the confirmed report date with a source link, past post-report moves computed in code, and a flag against your own written rule for names inside that window.
Journaling & post-trade reviewReview every closed trade in R-multiples, automatically
An agent runs a script on your closed-trade CSV to compute R-multiple and holding days (and MAE/MFE if you supply price history), then checks each trade's execution against the plan you wrote before entry.
Journaling & post-trade reviewSummarise weekly journal stats by setup, with a minimum sample before any conclusion
Every weekend you paste pre-computed journal stats into an agent, which reports win rate, average R and expectancy by setup tag, regime and weekday, and labels any group below your minimum sample as not enough data.
Risk & position-sizing checksCheck position size and portfolio heat before you trade
Run a local Python script on your planned entry, stop and positions CSV, and paste only its stdout. The agent checks size, heat, theme concentration and, when present, correlation against your limits, and leaves the decision to you.
Market context & regimeBuild a market-regime dashboard from your own exposure rules
Each end of day, a script computes index trend, breadth and new highs versus new lows, then an agent applies your written rules and shows the matching exposure band next to every input. Missing or contradictory inputs mean no band.
News triage & researchTriage news on your holdings to material items with links
An agent filters company news down to material items such as guidance changes, share offerings, rating changes and legal or regulatory events, summarises each with a link, and drops rumours.
News triage & researchTurn your X feed into a daily digest of process lessons, with no tickers
From accounts you choose, an agent collects posts about trading process, such as risk management, journaling and tooling, drops anything that mentions specific securities, and sends you a short digest with links.
Market context & regimeTrack group and theme rotation with relative-strength ranks you compute
Once a week an agent ranks groups and themes by relative strength over a fixed universe you define, and lists new entrants to your top 20 strictly as one background input for your independent research, never to allocate capital.
Scanning & screeningReview recent IPOs against your written base criteria for research notes
An agent checks companies that listed in the last one to three years against your liquidity filter and your written definition of a base, then returns a private weekly list of current matches with the measurements.
Discipline, checklists & psychologyRun your pre-trade checklist and log the answers
Before you place a trade, the agent asks your five checklist questions, flags chasing or names that are not in your plan, and gives you a timestamped log line to paste into your journal.
Discipline, checklists & psychologyCheck exit-rule adherence after the close
After the close, the agent checks each open position against the exit rules you wrote and reports which rules were met. It reports; you decide.
Journaling & post-trade reviewPropose one evidence-backed playbook change from the weekly review
On Sunday the agent compiles your mistakes and best trades from the journal and proposes at most one change to your written playbook, with the evidence. You approve or reject it.
Backtesting & rule researchTest a rule you wrote against history, without fooling yourself
Describe a rule in plain English and an agent writes and runs Python on daily data to see how it behaved historically, with costs, out-of-sample checks and warnings about look-ahead and survivorship bias.
Market context & regimeBuild a weekly macro calendar in your time zone
Each Sunday you paste that week's public economic calendar and any company-report dates for names you follow, and the agent returns a short filtered list in your time zone for you to add to your own calendar yourself.
Records & tax adminPrepare EUR realised-gains workpapers for a Portugal Anexo J filing
An agent turns your broker's annual reports into a realised-gains table in EUR, using the exchange-rate method your accountant confirms, and flags dividend withholding, ready for your accountant to review.
News triage & researchKeep a research wiki that an agent maintains from your own sources
You drop sources into a folder the agent may only read. It compiles them into linked wiki pages on themes, sectors and concepts, answers your questions with links to those pages, and lists contradictions when you ask.
Journaling & post-trade reviewTurn your trade journal into a setup library the agent keeps current
From your journal and post-trade reviews, an agent maintains one linked page per setup. Each page holds your written definition, example trades, common mistakes and stats computed in code; a separate dated log records every definition change.
Agent ops: guardrails & costsMake your agent label every claim by source and how well it's confirmed
Give the agent a ranked list of source types and five confirmation labels. Every fact it writes carries both, conflicts are written down instead of smoothed over, and unconfirmed claims stay out of its conclusions.
Discipline, checklists & psychologyHave an agent argue against your trade plan before you act on it
Paste your written plan and the agent hunts for its weakest assumption, the claim you can't support, and the bias most likely at work. It never says whether to take the trade. It only tests your reasoning.
Journaling & post-trade reviewGet your agent to follow up on the promises you write in your journal
The agent pulls the commitments out of your journal notes, such as "next time I'll wait for the close", asks you about each one a few days later, and keeps a simple kept-or-broken record for your weekly review.
Discipline, checklists & psychologyFind what comes before your rule breaks with a pre-session state log
Before you trade, rate sleep, stress, mood and focus in a 20-second log. Each week an agent compares those ratings with your rule breaks and checklist skips, and shows a pattern only once the sample is big enough.
Agent ops: guardrails & costsHave one agent audit your other agents every week
A separate, read-only checker confirms that each of your agents actually ran, used fresh data, stayed inside its permissions and still follows its written rules. It reports; you save the evidence snapshot and fix what it flags.
Agent ops: guardrails & costsGive every agent the same short profile of your rules and vocabulary
One small profile, loaded as a skill or standing instruction, tells every agent your hard limits, where your rules live, your shorthand and your time zone. You stop re-explaining yourself and agents stop guessing.
Discipline, checklists & psychologyLet an agent interview you until your trading rules are written down
Many workflows assume written rules. In rounds of numbered questions, the agent asks how you actually trade, never suggesting answers, and turns your replies into a first-draft playbook that you edit and own.
Backtesting & rule researchMeasure the gap between a rule on paper and how you actually trade it
For one rule you already use, a script compares the trades an honest historical test says the rule would have taken with the trades your journal shows. You get counts and average R for missed, extra and timing differences, statistics only.
Discipline, checklists & psychologyLog every setup you pass on, so your weekly review sees both halves
When you pass on a setup you had planned for, log a one-line skip row right away with its grade and your reason. Each weekend an agent separates rule-based skips from unexplained ones, so your review covers the trades you didn't take.
Journaling & post-trade reviewDictate your trading thoughts each day and let an agent file them as dated notes
Speak your observations, hesitations and reasons for passing into any voice-to-text tool. An agent files the transcript under fixed headings in a dated note, adds nothing of its own, and your other agents read the folder before they work.
News triage & researchCheck a viral AI trading result for evidence before you copy any of it
Paste a post claiming big returns from an AI agent and get a fixed evidence check: auditable records, the post's own risk math, recycled copies and the funnel at the end. It reports what can be verified, never whether the strategy works.
Agent ops: guardrails & costsWrite a no-AI fallback for your routine before your model provider goes down
For each step of your routine that an agent runs, write down the manual version and how you'll know the step failed, and keep a tested second provider for the steps you rely on most. An outage then costs minutes, not your process.
Agent ops: guardrails & costsTag your journal trades with your own rules first and the model last
Setup and mistake tags are applied in a fixed order: your written rules in code, then tags you corrected before, and only then the model for leftovers. Uncertain tags go to a review pile, and model spend has a weekly cap.
Agent ops: guardrails & costsMake your agent prove a new script works by running it, not describing it
When an agent builds or changes a tool you rely on, such as a sizing calculator or a journal stats script, finish by having it run your real command on hand-checked test cases and show the raw output against your expected numbers.
Discipline, checklists & psychologyTest whether your written setup definition is clear enough to apply
Give an agent your setup definition and past charts you've labelled, minus the labels. It labels them from the text alone, cites the clause it used and notes where the text is silent, so you can tell a wording gap from a misread chart.
Risk & position-sizing checksCheck your drawdown rules before each session and record the day's mode
Before you look for anything new, a script reads your equity log and your own drawdown rules and records today's mode: normal, reduced size or review-only. If the data is missing or stale, it records review-only and explains why.
Journaling & post-trade reviewGrade each trade's decision before you see its result, then look for lucky wins
Grade each closed trade's process against your rules with the result hidden. Then an agent sorts trades into four boxes: good process and good result, good and bad, poor and good, poor and bad. Lucky wins are the ones to study.
Agent ops: guardrails & costsKeep a monthly cost-and-value line for every agent in your trading routine
Once a month, list each agent job with what it cost (plan share, API spend, minutes fixing it) and the value it delivered, measured in minutes saved and checks it caught, never trading profit. Then keep, fix or switch off each one.