explain

Traces code from entry points through data flow to produce structured walkthroughs.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/Simon-YHKim/eject-button --skill explain-simon-yhkim
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: explain
Source: https://github.com/Simon-YHKim/eject-button/tree/main/.claude/skills/explain
Command: npx skills add https://github.com/Simon-YHKim/eject-button --skill explain-simon-yhkim

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Reading unfamiliar code is slow and error-prone when you don't know where to start. This Skill turns any function, module, or system into a structured explanation covering purpose, control flow, side effects, and invariants, so you understand what the code actually does and why. ## Core Features & Use Cases - Entry-point tracing: Identifies callers, dependencies, and related types using search tools to build a complete mental model before explaining. - Layered explanations: Delivers a high-level summary first, then the execution flow, then non-obvious details, with line-number citations like auth.py:42. - Depth matching: Adjusts explanation depth to the target, from a 5-line function to a whole system, and to the user's vocabulary and level. - Use Case: You inherit a Kotlin Android codebase and ask how the fake call overlay works. The Skill reads the service, its callers, and its dependencies, then walks you through the trigger-to-display flow with file references. ## Quick Start Ask the assistant to explain how a specific function, file, or module in your project works, for example by saying walk me through what this module does.

Frequently Asked Questions about explain

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

FAQPage Schema
How do I get an explanation of unfamiliar code?

Ask how a specific function, file, or module works, or request a walkthrough. The Skill reads the target code in full, finds its callers and dependencies with search tools, then explains purpose, flow, and side effects in layers.

How to understand a large module or system quickly?

Request a system-level walkthrough. The explanation starts with a one-sentence purpose, then covers components, data flow, entry points, and key files, citing line numbers so you can follow along in the source.

Does the explanation include callers and dependencies?

Yes. The workflow uses grep-style searches to find usages of the target and inspects what the target calls, including related types and interfaces, before building the explanation.

Can the explanation depth match my experience level?

Yes. Depth adjusts to both the target size and your level, starting high level and adding specifics only where behavior is non-obvious or you asked about it, using your own vocabulary.

What are the limitations of automated code explanation?

Explanations are grounded only in the code, comments, and history that can be read. When intent is unclear and no tests or comments exist, the Skill states the uncertainty rather than guessing.