explain
/explain
Explain a technical idea, or rewrite a confusing explanation, so the reader understands it on the first read without losing accuracy. Use when the user asks how something works, says an explanation is confusing or full of jargon, or asks to make technical text clearer.
- Author
- dpkingii ↗
- Repository
- dpk-skills ↗
- Licence
- MIT
- Last repository change
- 11.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 11.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Explain a technical idea, or rewrite a confusing explanation, so the reader understands it on the first read without losing accuracy. Use when the user asks how something works, says an explanation is confusing or full of jargon, or asks to make technical text clearer.
Original author description
Explain a technical idea, or rewrite a confusing explanation, so the reader understands it on the first read without losing accuracy. Use when the user asks how something works, says an explanation is confusing or full of jargon, or asks to make technical text clearer.
How it works
- 1. Pick the reader
- 2. Get the facts right
- 3. Structure it
- 4. Write the sentences
- 5. Rewriting the user's text
- 6. Check before finishing
SKILL.md preview
--- name: explain description: Explain a technical idea, or rewrite a confusing explanation, so the reader understands it on the first read without losing accuracy. Use when the user asks how something works, says an explanation is confusing or full of jargon, or asks to make technical text clearer. --- # Clear explanations ## 1. Pick the reader Use the audience the user names. Otherwise infer it from context (a recruiter, a classmate, a senior engineer, the user) and say in one line who you wrote for. If the right answer depends heavily on the audience and you can't tell who it is, ask. ## 2. Get the facts right If the subject is code in the current project, read the code before explaining it. Separate what you confirmed from what you inferred. When something is uncertain, say what is unknown and how to check it. ## 3. Structure it 1. Start with what the thing is and what problem it solves, in one or two sentences. 2. Explain how it works, with the steps in the order they happen. Name the component that does each step. 3. Give one concrete example with real values, from the codebase when possible. 4. Mention limits or gotchas only if they matter to this reader. Match the length to the question. A short question gets a short answer. ## 4. Write the sentences - One idea per sentence. - Use common, concrete words. Keep a technical term when it is the correct one, and define it the first time. - Expand each acronym the first time it appears. - Use active voice and name who or what acts. - State cause and effect directly. - Use lists for steps or parallel items, and prose when the ideas depend on each other. - Cut filler, vague intensifiers and decorative jargon. - No em dashes or semicolons. Don't end with a summary that repeats what you just said. Don't give up accuracy to make it shorter. ## 5. Rewriting the user's text When the user hands you their own explanation, keep their wording and structure wherever they already work. Fix only what is unclear or wrong. After the rewrite, list the changes that matter in a few short lines. ## 6. Check before finishing - Every pronoun has a clear referent. - Every term is defined or already familiar to this reader. - Each step says what changes and why. - In a rewrite, no fact from the original was lost.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · dpkingii/dpk-skills | 100 | MIT |
| crbnos/carbon | 100 | AGPL-3.0 |
| PerilloAI/flowtrace-plugin | 100 | Apache-2.0 |
| mickeyyaya/evolve-loop | 100 | Apache-2.0 |
| zenobi-us/dotfiles | 100 | MIT |
| imgly/agent-skills | 100 | MIT |
| marcel-bich/marcel-bich-claude-marketplace | 100 | MIT |
| nicodiansk/draw-it-out | 100 | MIT |
| ramboz/jig | 100 | MIT |
Database snapshot: 13.11.2026 · package version 90eede3a9ad6 (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
- 100plain-writing
Writes and rewrites prose, summaries, and lists so a reader without context understands them in one pass. Use for /plain-writing or deslopify. - 92say-it-plain
Explains any topic so the reader understands it on the first read, with the answer first and short, plain sentences. Use when the user asks for a clear, simple, or to-the-point explanation of anything, or says they did not understand something. - 81language_humanizer
Review, rewrite, or write a document so its intended reader understands it on the first read: coherent from beginning to end, plain in its wording, and carrying every load-bearing element of the input (conditions, requirement strength, numbers, actors, causal joints) through… - 100unbury
Rewrite AI-generated or AI-influenced technical writing so a competent engineer builds the correct mental model as fast as possible, without losing technical accuracy. Use when the user asks to de-slop, humanize, tighten, or clarify a PR description, code review comment, design… - 100ste
Explain technical ideas in clear, precise language. Use when an explanation is confusing, jargon-heavy, vague, or hard to follow, or when the user asks for Standard Technical English. - 100textbook-style-explanation
Explain a theory, hypothesis, method, concept, or principle in clear textbook-style prose, or rewrite technical material for understanding. Use when the user asks to explain, teach, or understand how an idea works, with or without a research project.