Verified against ChatGPT · 2026-08-12
Run your own stock research against a structured checklist and get told exactly what's still missing
Takes whatever research a requester has already done on a stock and checks it against a structured due-diligence checklist, flagging gaps by name instead of generating a generic research template from scratch.
The prompt
Ready to copy — highlighted parts are example details you can swap.
You are checking existing stock research against a structured due-diligence checklist to find what's missing, not writing a fresh research report and not telling the requester whether to invest. This is a gap-analysis exercise on the requester's own work. STOCK / COMPANY A mid-cap industrial equipment manufacturer. RESEARCH I'VE ALREADY DONE Revenue has grown 8% annually for 3 years, gross margin around 34%, management owns about 12% of shares, main competitor is a larger diversified conglomerate. CHECKLIST AREAS TO COVER Revenue quality and trend, competitive moat, management incentive alignment, balance sheet strength, valuation context. SPECIFIC RISK FACTORS I WANT CHECKED Customer concentration (do they rely on one or two large clients), exposure to raw material price swings, debt maturity schedule. For each checklist area, do one of three things: (a) if the existing research clearly covers it, say so and briefly restate what was found; (b) if the existing research touches on it but leaves an obvious gap (a number mentioned without its trend, a competitor named without a comparison), name the specific gap; (c) if the existing research doesn't address it at all, say so plainly rather than filling the gap yourself with unverified information — flag it as "not yet researched" and note what specifically should be looked up (e.g. "check the 10-K's risk factors section for supplier concentration" rather than a vague "do more research"). Do not generate new financial figures, price estimates, or forward projections to fill any gap — your job is to identify where the requester's own research is thin, not to substitute your own numbers for missing ones. For each specific risk factor listed, state directly whether the existing research addresses it, partially addresses it, or doesn't touch it at all. OUTPUT FORMAT 1. Checklist table: area | status (covered / partial gap / not researched) | note. 2. Risk factor check: each listed risk factor | addressed / partial / not addressed | what's missing if not fully addressed. 3. A prioritized list of the three most important gaps to close before this research would be considered reasonably complete for the requester's own stated purpose.
Customize
Optional — swap in your own details for the highlighted parts above.
Why this works
The rule against generating new financial figures or filling a gap with the model's own numbers is the load-bearing constraint in this prompt, because a gap-analysis tool that quietly writes in plausible-sounding figures to complete a thin checklist item stops being a gap analysis and becomes a fabricated research report the requester might mistake for verified information — the entire value of the exercise depends on the boundary between "here's what you found" and "here's what's still missing" staying visible rather than getting blurred. Requiring a specific next action for every "not researched" flag ("check the 10-K's risk factors section for supplier concentration" rather than "do more research") matters because GPT-5.1 defaults to vague encouragement when it doesn't have a concrete instruction to be specific, and a checklist that just says "needs more work" everywhere gives the requester no actual direction on where their next hour of research time should go. The three-tier status system (covered / partial gap / not researched) is more useful than a binary done/not-done because most real research lands in the partial category — a number mentioned without its trend, a competitor named without a direct comparison — and collapsing that into a binary would either overstate how complete the research is or understate genuine partial progress already made. Checking named risk factors separately from the general checklist areas ensures that specific concerns the requester cares about (customer concentration, debt maturity) don't get lost inside a generic due-diligence template that wasn't built around this particular company's actual risk profile.
What you get back
Competitive moat: partial gap — you've named the main competitor but haven't compared market share, pricing power, or switching costs between the two. Customer concentration risk: not addressed — check the 10-K's customer concentration disclosure or investor presentation for revenue-by-customer breakdown. Top 3 gaps to close: customer concentration data, debt maturity schedule, and a direct valuation comparison against the named competitor.
Verified against
ChatGPT GPT-5.1 · 2026-08-12
Changelog
- 2026-08-12 — Initial publish, verified against ChatGPT GPT-5.1.
Need this built into your business?
If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.
EXPLORE WHAT SCULT BUILDS
