quick-explainer

Generates a single concrete worked example explaining what a PR, design doc, or plan changes.

3|Updated Apr 14, 2026
One-click install
npx skills add https://github.com/nvie/skills --skill quick-explainer-nvie
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: quick-explainer
Source: https://github.com/nvie/skills/tree/main/skills/quick-explainer
Command: npx skills add https://github.com/nvie/skills --skill quick-explainer-nvie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long PRs, design docs, and plans are full of abstraction, background, and motivation sections that cost twenty minutes of focused reading. This Skill compresses any of them into a twenty-second explainer built from one concrete worked example: what goes wrong today, and what the same situation looks like after the change lands. ## Core Features & Use Cases - One concrete example, never a summary: Every output is a specific instance with real names, real values, and real numbers — no categories, no theory, no changelog bullets. - Multi-source input handling: Accepts GitHub PRs and issues (via gh), the current branch diff, design docs, Mikado graphs, screenshots, URLs, or pasted text, and treats the diff as the source of truth. - Grounded examples only: Examples come from real bug reports, repro steps, tests, or traced diffs — never invented scenarios — and the Skill says so explicitly when the source cannot support one. - Use Case: You are about to review a teammate's PR you have never seen. Run /quick-explainer <PR URL> and get a 20-line before/after scenario showing exactly what breaks today and what the fix changes. ## Quick Start Run /quick-explainer with a PR link, issue, file path, or nothing to explain the current branch in one concrete before-and-after example.

Frequently Asked Questions about quick-explainer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I quickly understand what a GitHub PR actually does?▼

Run /quick-explainer with the PR URL or number. It fetches the PR body and diff with gh, treats the diff as the source of truth, and returns a roughly 20-line before-and-after example showing the concrete problem and fix.

How to get a quick summary of a design doc without reading it all?▼

Point /quick-explainer at the doc's file path or URL. Instead of a summary, it extracts the problem statement and proposed change, then expresses them as one concrete scenario with a Today and After section.

Can I use quick-explainer on the current git branch?▼

Yes. Invoke it with no argument and it diffs the current branch against main using the merge base, reads the commit subjects, and builds the explainer from what the branch actually changes.

What inputs does quick-explainer accept besides pull requests?▼

It accepts GitHub issues, local file paths such as design docs or plans, Mikado graphs, images or screenshots, doc URLs, and pasted text. Each input type has a defined gathering method, and the output shape stays the same.

What happens when a document has no concrete failure to explain?▼

The Skill never invents a scenario. If the source argues from principle without a real failure, it outputs a one-line statement saying the example cannot be grounded and suggests asking the author what actually broke.

When should I use quick-explainer instead of a code review?▼

Use it before doing the work, to prime your understanding of what a change is about. It is explicitly not a review — findings, concerns, and nits belong in a separate review pass, and the explainer stops after one example.