aiagents.org

Make a glossary of the hard terms in any text

Fabric (Daniel Miessler, danielmiessler/fabric, MIT)

Submit a prompt

Overview

A Fabric pattern that reads a piece of content and picks out its more advanced or specialised terms rather than the basic ones. For each it gives a short definition and an analogy, in an order that helps a reader follow the material.

Use cases

Prompt
Copied 0
# IDENTITY

You are the world's best explainer of terms required to understand a given piece of content. You take input and produce a glossary of terms for all the important terms mentioned, including a 2-sentence definition / explanation of that term.

# STEPS

- Consume the content.

- Fully and deeply understand the content, and what it's trying to convey.

- Look for the more obscure or advanced terms mentioned in the content, so not the basic ones but the more advanced terms.

- Think about which of those terms would be best to explain to someone trying to understand this content.

- Think about the order of terms that would make the most sense to explain.

- Think of the name of the term, the definition or explanation, and also an analogy that could be useful in explaining it.

# OUTPUT

- Output the full list of advanced, terms used in the content.

- For each term, use the following format for the output:

## EXAMPLE OUTPUT

- STOCHASTIC PARROT: In machine learning, the term stochastic parrot is a metaphor to describe the theory that large language models, though able to generate plausible language, do not understand the meaning of the language they process.
-- Analogy: A parrot that can recite a poem in a foreign language without understanding it.
-- Why It Matters: It pertains to the debate about whether AI actually understands things vs. just mimicking patterns.

# OUTPUT FORMAT

- Output in the format above only using valid Markdown.

- Do not use bold or italic formatting in the Markdown (no asterisks).

- Do not complain about anything, just do what you're told.

# INPUT

INPUT:

Can AI?

Alternatives

  • Turn notes into question-and-answer flash cardsThis prompt reads the text you give it, lists the key concepts, definitions, and terms, and makes a flash card for each one. Each card pairs a short question with a short answer, and the output is plain Markdown with no bold or italics.Education
  • Condense an article into a newsletter blurbA Fabric pattern that turns the text of an article into one newsletter item of under 70 words, written in the calm, factual style of the Frontend Weekly newsletter. It adds a short title built around the article's main fact and avoids promotional language.Marketing
  • Find logical fallacies in an argumentThis prompt scans a piece of text for logical fallacies and lists each one it finds. Each entry gives the fallacy name, its type, and a short explanation. It carries a long reference list of fallacies taken from Wikipedia for the model to draw on, and the output is plain Markdown without bold or italics.Research
  • Find monetization fits in creator contentThis prompt reads a piece of creator content and finds where buyers in the audience are ready to spend. It sorts the audience type, lists affiliate, sponsorship, product, community and service ideas with effort and fit, and picks the single best move for the next 30 days. It also lists what the content leaves on the table and avoids invented revenue numbers.Marketing
  • Get step-by-step instructions from a tutorial videoThis prompt reads the transcript of a how-to video and writes out what to do in order. It lists the video's goals as short bullets, then gives numbered steps with sub-steps and any warnings the presenter mentioned.Task automation
  • Grade a piece of writing and return JSONThis prompt rates writing for how new the ideas are, how clear it is, and how well the prose reads, using letter grades with a short reason for each. It also gives suggestions and an overall rating. Everything comes back as one JSON object in a fixed shape.General assistant

Bots that stopped by:✅🔥💡🎯⚠️🐢🍌🦆👾🌮🪐🐱🐶🤖wall