# Explain

> 当用户看不懂代码、想理解某段逻辑、需要解释某个文件或函数时使用 — 用大白话解释代码逻辑

- **Type:** Skill
- **Install:** `agentstack add skill-lightpointventures-claude-code-starter-explain`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [lightpointventures](https://agentstack.voostack.com/s/lightpointventures)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [lightpointventures](https://github.com/lightpointventures)
- **Source:** https://github.com/lightpointventures/claude-code-starter/tree/main/skills/explain
- **Website:** https://github.com/lighthouse-strategy/claude-code-starter

## Install

```sh
agentstack add skill-lightpointventures-claude-code-starter-explain
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 代码解释

用最简单的语言解释代码，让用户真正理解它在做什么。

## 步骤

### 1. 确定要解释的代码

如果用户指定了文件或函数，直接读取对应代码。

如果用户没有指定，问：
> 你想让我解释哪段代码？可以告诉我文件名、函数名，或者直接贴代码。

### 2. 阅读并理解代码

读取完整的代码上下文，包括：
- 这段代码所在的文件
- 它被谁调用、它调用了谁
- 相关的类型定义或数据结构

### 3. 分层解释

用中文输出解释，按以下结构：

**一句话总结**
> 这段代码的作用是：xxx

**逐步拆解**
用编号列表，按执行顺序解释每个关键步骤。每一步用一句大白话说清楚在做什么。

- 不要逐行翻译代码，而是解释逻辑意图
- 用类比帮助理解（比如"就像一个过滤器，只留下符合条件的数据"）
- 遇到专业术语，先用大白话解释，再括号标注术语

**关键细节**
如果有容易忽略的重要细节（边界处理、错误处理、性能考虑），单独指出。

### 4. 回答追问

解释完后，告诉用户：
> 有哪里不清楚的吗？可以继续问。

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [lightpointventures](https://github.com/lightpointventures)
- **Source:** [lightpointventures/claude-code-starter](https://github.com/lightpointventures/claude-code-starter)
- **License:** MIT
- **Homepage:** https://github.com/lighthouse-strategy/claude-code-starter

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-lightpointventures-claude-code-starter-explain
- Seller: https://agentstack.voostack.com/s/lightpointventures
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.