> ## Documentation Index
> Fetch the complete documentation index at: https://docs.newenergycoder.club/llms.txt
> Use this file to discover all available pages before exploring further.

# defuddle

> Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the us…

| 项目 | 内容                                                                                                                                                                                                                                                              |
| -- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 来源 | [skills/defuddle/SKILL.md](https://github.com/new-energy-coder-club/new_energy_coder_club/blob/Skill/skills/defuddle/SKILL.md)                                                                                                                                  |
| 分类 | 开发工程 & 工作流                                                                                                                                                                                                                                                      |
| 安装 | 克隆 [Skill 分支](https://github.com/new-energy-coder-club/new_energy_coder_club/tree/Skill) 后，将 `skills/defuddle/` 目录复制到 `~/.claude/skills/`（Claude Code）、`~/.trae/skills/`（Trae IDE）或 `~/.qclaw/skills/`（QClaw/OpenClaw），详见 [Skill 安装方式](/community/skill-branch) |

# Defuddle

Use Defuddle CLI to extract clean readable content from web pages. Prefer over WebFetch for standard web pages — it removes navigation, ads, and clutter, reducing token usage.

If not installed: `npm install -g defuddle`

## Usage

Always use `--md` for markdown output:

```bash theme={null}
defuddle parse <url> --md
```

Save to file:

```bash theme={null}
defuddle parse <url> --md -o content.md
```

Extract specific metadata:

```bash theme={null}
defuddle parse <url> -p title
defuddle parse <url> -p description
defuddle parse <url> -p domain
```

## Output formats

| Flag        | Format                           |
| ----------- | -------------------------------- |
| `--md`      | Markdown (default choice)        |
| `--json`    | JSON with both HTML and markdown |
| (none)      | HTML                             |
| `-p <name>` | Specific metadata property       |