Students & Study

Verified against ChatGPT · 2026-08-10

Pull a real study vocabulary list out of an assigned reading, sized for spaced repetition, not a glossary dump

Extracts only the words from an assigned text that are actually worth memorizing, with example sentences and a spaced-repetition-friendly format, instead of every unfamiliar-looking word in the passage.

ChatGPT (GPT-5.1)4 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

Pull a vocabulary study list from the text below, but only the words actually worth memorizing for AP English Literature exam prep — need vocabulary that shows up across period-appropriate texts, not just this novel. — not every word that merely looks advanced.

SOURCE TEXT
Chapter 3 of 'The Great Gatsby' (paste or describe the excerpt), roughly 1,200 words covering Nick's first visit to Gatsby's party.

WHY I'M STUDYING THIS
AP English Literature exam prep — need vocabulary that shows up across period-appropriate texts, not just this novel.

WORDS I ALREADY KNOW (skip these even if they appear)
affluence, gaudy, wistful

TARGET LIST SIZE
15

Selection rule: include a word only if it's likely to recur in this subject area beyond this one text, or if not knowing it would block understanding a sentence in the passage — skip proper nouns, one-off technical terms unique to this exact passage, and words you judge I likely already know from context even if they weren't in my known-words list. For each selected word, give: the word as it appears in the text, a definition in plain language (not a dictionary-copy definition), the exact sentence from the source text it appeared in, and one new example sentence in a different context so I'm not just memorizing the original sentence shape. Format each entry as a front/back flashcard pair — front is the word alone, back is definition plus both example sentences — so this can be dropped directly into a spaced-repetition app without reformatting.

If the text is short enough that meeting the target count would force you to include marginal words just to hit the number, tell me the real count you'd recommend instead and explain briefly why, rather than padding the list to match what I asked for.

Output as a numbered flashcard list in the front/back format described, followed by one line noting any words you deliberately excluded that I might expect to see (like a word that looked hard but you judged as already-known from context).

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

Asked to "pull vocabulary" from a text with no selection rule, GPT-5.1 tends to over-include: it flags every word above a certain register as noteworthy, which produces a list dominated by words you'll recognize by context and never see again versus the smaller set of words that actually recur across a subject area or genuinely block comprehension — the selection rule here gives the model an actual filter (recurs beyond this text, or blocks understanding) instead of a vague "advanced-sounding" threshold, which is the difference between a 40-word glossary dump and a 15-word list worth memorizing. Requiring a second, freshly generated example sentence in addition to the original source sentence directly targets a known weakness of rote vocabulary study: if you only ever see a word in the one sentence it was drilled from, recall becomes tied to that sentence's shape rather than the word's actual meaning, so a slightly reworded appearance on a real exam can fail to trigger recognition — a second context sentence forces the definition itself to do the work. Instructing the model to say when hitting your target count would force marginal inclusions matters because a target count is a proxy for "a useful amount," not a hard requirement, and a model that silently pads a 9-word natural list up to a requested 15 by including words you didn't need is optimizing for matching the number you asked for rather than the actual goal the number was standing in for.

What you get back

7. Front: languid Back: Moving or done in a slow, relaxed, low-energy way. Source: "She was languid in her chair, as if the heat had settled into her bones." New: The dog stretched into a languid pose on the porch, unbothered by the afternoon sun.

Verified against

ChatGPT GPT-5.1 · 2026-08-10

Changelog

  • 2026-08-10 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
All Students & Study prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY