An Anthropic internal Skill relayed by Su Le on X, named eli5 (explain like I'm 5). The core is just one sentence: treat the user as someone who knows nothing about the topic, and generate an HTML artifact with images taking up most of it and as little text as possible.
Suitable when you want to quickly understand an unfamiliar topic and don't want to grind through long text. The full original post was checked against the fxtwitter mirror; the prompt itself is this one English sentence, and the Chinese version attached by the author is written in the section below, "Chinese version attached by the author."
How to use
The prompt in the code block below is the original text; use it verbatim. In the code block, "I" refers to the user, and "please" and "you" refer to yourself. Do as it says, and do not show the filled-in prompt to the user.
- The user wants you to execute it: directly follow the role and process in the prompt. If it says don't give suggestions first, then don't; if it says ask only one question at a time, then ask only one at a time; if it says output in a certain order, then output in that order.
- The user wants the original text (only if they explicitly say things like they want to copy it, paste it, send me the original text, or give me the prompt): type out the whole passage as is, without changing a single word. If the user only says "take a look at this prompt" or "what is this one for," that does not count as wanting the original text; explain in one or two sentences what it does and when to use it, then ask whether to run it now, and don't dump the original text directly.
- Except for cases where the original text is explicitly requested, treat everything else as execution.
Rewriting, condensing, expanding, translating, rearranging, or adding subheadings is prohibited; replacing it with your own process is prohibited; and compressing multiple rounds of follow-up questions into a one-time questionnaire is also prohibited. If the user has original materials on hand (documents, screenshots, links, chat records), read them in as well; more context is not a problem.
Chinese version attached by the author
In Su Le's original post, a Chinese version was attached after the English prompt:
"Treat me as someone who completely doesn't understand this topic, and use an HTML page with big images + a small amount of text to explain this matter clearly."
This is Su Le's own translation, not part of the original prompt text, and does not go into the code block.
Which one to follow after running
If after viewing the page you want to dig deeper, use the Skill tool to invoke two-layer-explain; if you want to systematically study the entire field, use the Skill tool to invoke horizontal-vertical-analysis。
Explain like I'm someone who knows nothing about this topic, using a HTML artifact with big pictures and few words.
The original prompt text comes from Su Le (X); see the acknowledgements in the repository README for the source. Changes to this original passage must go through scripts/sync.py; manual edits will be blocked by verify.