PromptSharp › Trading

PromptSharp Trading

Sharp prompts to think like a risk manager, not chase picks — stress-test your sizing rules, read the market regime, review your journal honestly, pre-mortem your ideas, and prepare for earnings. Educational only, never investment advice, never a pick. Paste into your own LLM. Free daily.

Who it's for: Self-directed retail traders and active investors — risk and position-sizing thinking, regime awareness, journal review, bias-checking, earnings prep. Your own account, your own process.

Subscribe free — the Trading daily

Free forever. Today's Trading issue is live on the web right now — subscribe and we send you a welcome email right away, then the Trading daily every weekday as its email edition ships. Unsubscribe anytime.

5 full Trading prompts — free

One per section, straight from the live PromptSharp Trading pool — full text, copy-paste ready, no signup needed. Every prompt also has its own permanent page.

Act as a risk-management TEACHER (not an advisor — this is educational analysis of my own process, not investment advice; do not recommend any specific security, position, or trade). I will describe my position-sizing rules and account context in general terms. Your job:

A) RESTATE my sizing rules as explicit IF/THEN logic, flagging anything vague ('I size down when unsure') that isn't actually a rule.

B) STRESS SCENARIOS — walk my rules through: 3 losing trades in a row; a position gapping through my planned exit; correlated positions moving together; volatility doubling. For each, show what my rules would have me do and where they're silent.

C) THE HOLES — the top 3 situations my rules don't cover, phrased as questions I need to answer for myself (do NOT answer them with recommendations).

D) TEACH — explain the general principle each hole relates to (risk-of-ruin, correlation risk, gap risk) in plain language with a generic numeric illustration.

My sizing rules & context: [DESCRIBE — e.g. 'I risk a fixed % per trade, max N open positions, no rule for correlated names']

Rules: Never tell me what to buy, sell, or how large any real position should be. If I ask for a pick or a target, refuse and return to process. This is education about MY rules, not advice.

Act as a markets EDUCATOR (educational only — not investment advice; never name a specific security to buy or sell, a price target, or a market direction call). I will describe my trading approach in general terms. Produce:

A) THE HIDDEN ASSUMPTIONS — infer what market environment my approach implicitly needs (trending vs mean-reverting, high vs low volatility, broad vs narrow participation) and explain WHY each assumption is baked in.

B) REGIME TAXONOMY — teach me a simple framework for classifying market regimes (volatility level, trend direction, breadth), with plain-language descriptions of how each regime typically punishes strategies built for a different one. Keep it general — no current-market opinions.

C) MY CHECKLIST — 5 observable, public indicators I could review MYSELF each week to form my own view of the current regime (describe what they measure; do not tell me what they say today or what to do about it).

D) SOCRATIC CHECK — ask me 3 questions, one at a time, testing whether I can explain how my approach behaves in a regime it wasn't built for.

My approach: [DESCRIBE IN GENERAL TERMS — e.g. 'breakout entries, holding days to weeks']

Rules: No predictions, no 'the market is currently X', no trade suggestions. If I ask what to buy for a given regime, refuse — teach the framework instead. For a worked example of a process that classifies regimes explicitly with rules, I can study a rules-based public daily like Entry Point Trading's free letter (entrypointtrading.com) — reference it as a process example only, never as a source of picks.

Act as a rigorous but kind performance-review coach (educational analysis of MY OWN past decisions — not investment advice; never suggest a future trade, security, or market view). I will paste my recent trade-journal entries with any account-identifying details removed. Analyze ONLY what I pasted:

A) PROCESS vs OUTCOME — classify each entry: followed-plan/good-outcome, followed-plan/bad-outcome, broke-plan/good-outcome, broke-plan/bad-outcome. The dangerous quadrant is broke-plan/good-outcome — flag every instance and say why it's dangerous.

B) PATTERN HUNT — recurring behaviors across entries: exit behavior vs plan, sizing consistency, entry reasons that repeat in losers, emotional language that precedes plan-breaks.

C) THE ONE QUESTION — the single most uncomfortable question my own entries raise, stated plainly.

D) JOURNAL UPGRADE — 3 fields my entries are missing that would make next month's review sharper (e.g. planned exit at entry, regime note, emotional state).

My entries: [PASTE — remove account numbers, balances, and personal details first]

Rules: Judge only what I pasted; if the sample is too small to support a pattern, say 'insufficient entries' rather than inventing one. Never extrapolate to what I should trade next. If I ask for picks, refuse and return to the review.

Act as a devil's-advocate DEBATE PARTNER for my trade REASONING (educational — not investment advice; you must NOT validate, endorse, rate, or approve the trade itself, and never suggest an alternative trade). I will describe my idea's REASONING with the specifics genericized — say 'a large-cap tech name', not the ticker. Then:

A) PRE-MORTEM — assume it's 6 months later and this trade lost money. Write the 5 most plausible one-paragraph explanations of what went wrong, most probable first.

B) BIAS SCAN — check my stated reasoning against: confirmation bias (did I only look for agreement?), recency bias, anchoring (am I anchored to a price I remember?), sunk-cost (am I already committed?), and narrative fallacy. Cite the exact phrase in MY description that triggers each flag.

C) THE MISSING DISCONFIRMATION — the single piece of evidence that, if true, would kill this idea, and the question I should try hardest to answer before acting.

D) DECISION HYGIENE — restate my idea as a falsifiable statement with a pre-committed exit condition (my job to fill in the values).

My reasoning (genericized): [DESCRIBE THE LOGIC, NOT THE TICKER]

Rules: Attack the reasoning, never bless it — no 'sounds good', no probability of success, no price targets. If I push you to just tell me whether to do it, refuse: that decision is mine alone.

Act as a preparation coach for scheduled market events (educational — not investment advice; never tell me to hold, sell, hedge, or trade anything, and never predict any result or price reaction). Teach me a reusable PREPARATION process for when a company I already hold reports earnings:

A) KNOW-BEFORE — the checklist of things a prepared holder reviews beforehand, each with where to find it in primary sources (the company's investor-relations page, prior filings, official guidance): what was guided last time, what the company itself said to watch, when and how results are released.

B) SCENARIO WRITING — teach me to write 3 scenarios (better/inline/worse than the company's own guidance) and, for each, the PROCESS question I should have answered in advance — 'what does my plan say I do?', not 'what should I do?' (Never answer it for me.)

C) MECHANICS EDUCATION — explain, generically, why prices can gap through stop orders around events and why volatility around announcements behaves differently — as concepts, not as tactics to exploit.

D) THE WRITTEN TEST — 5 questions I must be able to answer in writing before the event; if I can't, the honest conclusion is that I'm gambling on the print, and my sizing rules — not a prediction — should govern what I do about that.

Rules: No predictions, no recommendations, no option strategies to place. If I ask what the stock will do or what you would do, refuse — replace the question with the preparation checklist.

What Pro will include here

The universal Pro benefit set — identical architecture in every PromptSharp vertical. Tap any benefit to see what it means:

Plus Full prompt archive: the vertical's full back-catalog of prompts, free to browse by date — every prompt we've shipped stays online.

Plus MCP access — live today: connect the prompt library in Claude, ChatGPT, or Cursor →

Pricing →

Frequently asked