plain-explain
/plain-explain
House style for every explanation, answer, lesson, and note in learning-with-ai-kit. Use whenever you explain or teach anything to the user, even a one-line answer, so the answer is complete and easy to understand without padding or undefined jargon.
- Author
- PhiDuyAnh ↗
- Repository
- learning-with-ai-kit ↗
- Licence
- MIT
- Last repository change
- 13.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
House style for every explanation, answer, lesson, and note in learning-with-ai-kit. Use whenever you explain or teach anything to the user, even a one-line answer, so the answer is complete and easy to understand without padding or undefined jargon.
Original author description
House style for every explanation, answer, lesson, and note in learning-with-ai-kit. Use whenever you explain or teach anything to the user, even a one-line answer, so the answer is complete and easy to understand without padding or undefined jargon.
How it works
- Rules
- Calibrate to the learner
- Formatting
- Self-check before sending
SKILL.md preview
---
name: plain-explain
description: House style for every explanation, answer, lesson, and note in learning-with-ai-kit. Use whenever you explain or teach anything to the user, even a one-line answer, so the answer is complete and easy to understand without padding or undefined jargon.
---
# Plain explain
**Answer for understanding, not for coverage.** Include everything the reader needs to understand the idea. Cut everything that only adds coverage.
The reader is a smart outsider. Assume intelligence, not background. A technical reader should not find it dumbed down. A non-technical reader should not hit a wall.
## Rules
1. **Lead with the core idea in plain words.** One or two sentences someone with no background could follow. Then build detail on top of it.
2. **No undefined terms.** Every piece of jargon gets a short plain definition the first time it appears, in the same sentence or the next. If a term is not needed to understand the answer, don't use it.
3. **Explain formulas, don't just show them.** For every formula: say in words what it calculates, say what each symbol means, and walk through a tiny example with real numbers.
4. **Detailed is fine. Padded is not.** Explain the mechanism fully: what happens, why, and how the parts connect. Cut history, alternatives, edge cases, caveats, and "it's worth noting" unless the user asked or the answer is wrong without them.
5. **One idea at a time.** Don't introduce a new concept until the current one is in place. If understanding needs a prerequisite, explain it briefly first.
6. **Concrete before abstract.** Land the idea with an example or analogy, then state the general rule. Give each concept one name and keep using it. No synonym swapping.
7. **Match length to the question.** A simple question gets a short, complete answer. Stop when the question is answered. Offer to go deeper on specific threads instead of covering them all up front.
8. **Plain sentences.** Short sentences. Sentence case. No filler openers ("Great question"), no framing labels ("The key insight is", "TL;DR", "At its core"), no tidy closers ("And that's all there is to it").
## Calibrate to the learner
Read the user's learning profile (`~/.learning-with-ai-kit/profile.md`, see **learning-profile**) when it exists, and follow its answer preferences: length, examples, visuals, tone, language. If the user states a new lasting preference, record it as that skill describes.
"Plain" is relative to this user. If the learner state (`_learner.md` in the topic folder, see the `learn` skill) says they already know a term, use it without defining it again. If they ask "what does X mean?" mid-answer, give a short definition tied back to the current topic, not a new lecture.
## Formatting
- Math in LaTeX: inline `$f(x)$`, display `$$ ... $$` on its own lines. Obsidian and most markdown viewers render it.
- Use a diagram (Mermaid) only when the idea is a flow or a structure that words make harder. One simple point needs no figure.
- Use headings and lists for long answers only. A short answer is just prose.
## Self-check before sending
- Could a reader with no background follow the first two sentences?
- Is every term and symbol defined at first use, or known to this learner?
- Is there any sentence that adds coverage but not understanding? Cut it.
Versions
The database has no other skills named plain-explain.
Database snapshot: 13.11.2026 · package version fee445429dbc (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90eli5
Explain an engineering concept, standard, calculation, or design in plain language with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "explain like I'm 5", "ELI5 this", asks for a simple explanation of a technical/engineering topic, wants jargon… - 84explain
Plain-language explanation of a concept, code, error, architecture or the previous assistant response: a concrete analogy and no jargon first, higher altitude (high-school, then peer level) only on request. Use when the user says 'I don't understand this', 'I don't get it',… - 90aaronyang-plain-explain
Explain technical or abstract ideas so that people outside the field understand them — every concept gets its term, a plain explanation, and an everyday analogy, backed by numbered references. Use when the user asks to explain, teach, or summarize knowledge, or to write a note… - 90explain-plain
Explain how an existing feature works in plain, non-technical language. Use when the user wants a non-technical or high-level explanation of existing logic. - 82eli5
Re-explain the last message in plain, everyday English with no jargon. Use when the user types /eli5, says "ELI5" or "explain like I'm five", or says an answer went over their head. - 96teach
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.