Explain concepts, bugs, or design decisions in a deliberately chosen teaching style. Use when the user invokes the skill by name, says "explain", or wants to understand *why* (not just a fix). Honors flags `--story` (Journey + Analogy for bugs), `--why` (First principles + Counterfactual for design decisions), and `--diff` (Compare + Layered onion for X vs Y). Auto-picks style if no flag. Output in Vietnamese.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add mxrsv/agents-skills --skill explain --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Explain?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/mxrsv-explain)More formats (shields.io, HTML) on the badges page.
---
name: explain
description: Explain concepts, bugs, or design decisions in a deliberately chosen teaching style. Use when the user invokes the skill by name, says "explain", or wants to understand *why* (not just a fix). Honors flags `--story` (Journey + Analogy for bugs), `--why` (First principles + Counterfactual for design decisions), and `--diff` (Compare + Layered onion for X vs Y). Auto-picks style if no flag. Output in Vietnamese.
effort: medium
---
# Explain
Teach **understanding**, not just deliver facts. Pick style by flag; if no flag, auto-pick and announce it on line 1.
## Style flags
### `--story` → Journey + Analogy
**Use for**: bugs, debugging sessions, anything with a "moment of discovery".
**Flow**: initial observation → dig deeper → "aha" moment → runtime consequence → real-world analogy → takeaway lesson.
**Avoid**: bullet lists, leaky analogies (metaphor breaks on a load-bearing detail).
### `--why` → First principles + Counterfactual
**Use for**: design decisions, trade-offs, recurring class of bugs.
**Flow**: strip to fundamental constraint → enumerate 2-3 options the designer could have picked → trace the chosen path → counterfactual ("if they had chosen differently...") → implication for related bugs.
**Avoid**: getting stuck in the specific code (the point is the _principle_).
### `--diff` → Compare & contrast + Layered onion
**Use for**: migration guides, "X vs Y", bugs with multiple causal layers.
**Flow (compare side)**: use a table when ≥3 dimensions; bullet pairs when 1-2. Same axes for both sides.
**Flow (onion side)**: layer 1 symptom → layer 2 mechanism → layer 3 API design → layer 4 philosophy. Drop layers the bug doesn't have.
**Avoid**: comparing things the reader doesn't know on either side (use `--story` instead).
## Default (no flag)
Auto-pick and announce in Vietnamese on line 1: `**Phong cách: --story** (lý do ngắn)`.
Pick rules:
- Bug / debugging → `--story`
- Design choice / trade-off / "why did they do it this way" → `--why`
- "X vs Y" / migration / multi-layer bug → `--diff`
- Ambiguous → `--story` (most accessible)
## Output rules
- **Concise by default**: shortest answer that fully teaches the concept. No filler, no recap, no "next steps" section. Each section earns its place — drop steps the topic doesn't need.
- Vietnamese narrative, including prose around code identifiers, file paths, and CLI commands
- Headings `##` / `###` only (never `#`)
- Code blocks always tagged with language
- Length matches topic — don't pad. Simple gotcha: 3-5 short paragraphs. Deep design analysis: longer only if every paragraph adds insight.
- Semantic emoji (🔍 💡 ⚠️ 🐛 🔧) at section transitions or "aha" moments — sparingly
- End with a one-sentence Vietnamese takeaway (📝 or 💡)
## Modifier flags
- `--brief` → ≤6 sentences, skip section headers
- `--deep` → full structure, no shortcuts
- Two style flags at once → pick dominant by topic, mention which one is being skipped
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!