Tooluck logoTooluck
SKILL.md

defuddle

Agent skill fromkepano/obsidian-skills

Extract clean Markdown from HTML pages with Defuddle CLI.

How to install defuddle

install defuddle
# install the obsidian-skills pack with the skills CLI
npx skills add kepano/obsidian-skills

# or add only this skill to Claude Code: copy the folder

skills/defuddle/

# into

~/.claude/skills/defuddle/ (all projects)

.claude/skills/defuddle/ (one project)

skills/defuddle/SKILL.md

MITFull file
1# Defuddle
2
3Use 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.
4
5If not installed: `npm install -g defuddle`
6
7## Usage
8
9Always use `--md` for markdown output:
10
11```bash
12defuddle parse <url> --md
13```
14
15Save to file:
16
17```bash
18defuddle parse <url> --md -o content.md
19```
20
21Extract specific metadata:
22
23```bash
24defuddle parse <url> -p title
25defuddle parse <url> -p description
26defuddle parse <url> -p domain
27```
28
29## Output formats
30
31| Flag | Format |
32|------|--------|
33| `--md` | Markdown (default choice) |
34| `--json` | JSON with both HTML and markdown |
35| (none) | HTML |
36| `-p <name>` | Specific metadata property |

Excerpt shown under the repository's MIT license.

More skills in obsidian-skills

Keep exploring

Similar skill repositories

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates