Skip to content
Skills Library
Data & analytics · Conversion & formats

defuddle

/defuddle

Extract web pages and YouTube transcripts with Defuddle CLI. Use for articles, documentation, blog posts, and video transcript requests.

Author
kouko ↗
Licence
MIT
Last repository change
07.11.2026

Assessment and security

95/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content30 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 07.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Extract web pages and YouTube transcripts with Defuddle CLI. Use for articles, documentation, blog posts, and video transcript requests.

Original author description

Extract web pages and YouTube transcripts with Defuddle CLI. Use for articles, documentation, blog posts, and video transcript requests.

How it works

  1. Usage
  2. YouTube transcripts
Original SKILL.md headings · 43 lines, 225 words
SKILL.md preview
---
name: defuddle
description: |
  Extract web pages and YouTube transcripts with Defuddle CLI. Use for articles, documentation, blog posts, and video transcript requests.
---

# Defuddle

Use Defuddle CLI to extract readable content from web pages. Prefer it over WebFetch for standard web pages; for URLs ending in `.md`, use WebFetch directly.

Defuddle 0.19.0 or later is required. If the CLI is missing, report that it is required; install with `npm install -g defuddle`. Prefer the latest version for YouTube fixes; use `defuddle --version` to check the installed version.

## Usage

Use `--md` for markdown output (quote URLs in the shell):

```bash
defuddle parse '<url>' --md
```

Save to file:

```bash
defuddle parse '<url>' --md -o content.md
```

Extract a metadata property (`title`, `description`, or `domain`):

```bash
defuddle parse '<url>' -p title
```

Use `--frontmatter` for metadata and standard input with `defuddle parse - --md`.

## YouTube transcripts

Use Markdown for a video URL:

```bash
defuddle parse '<youtube-url>' --md
```

To request a preferred language, add `--lang ja`. This is a preference, not a guarantee or a translation request. Verify that the output contains a transcript, check its actual language from the text, and report missing captions, a different language, or command failure. If the language cannot be determined, report it as unknown; video descriptions are not transcripts.

For structured output, use `--json`: `variables.transcript` holds the transcript when available. The top-level `language` may come from page metadata and is only a clue.

Without `--md` or `--json`, output is HTML.
Files in this package (2)
  • LICENSE 1 KB
  • SKILL.md 2 KB

Versions

RepositoryScoreLicence
This page · kouko/monkey-skills95MIT
FrancoStino/opencode-skills-collection100MIT
tonydzi/second-brain-starter-kit100MIT
pantheon-org/tekhne100MIT
galyarderlabs/galyarder-framework100MIT
galyarderlabs/galyarder-framework100MIT
LiHongwei-cn/lihongwei-cn100MIT
yeaight7/agent-powerups100Apache-2.0
pinkpixel-dev/skills-collection-1100Apache-2.0

Database snapshot: 13.11.2026 · package version f9a1097e1652 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100baoyu-url-to-markdown
    Fetch any URL and convert to markdown using Chrome CDP. Saves the rendered HTML snapshot alongside the markdown, uses an upgraded Defuddle pipeline with better web-component handling and YouTube transcript extraction, and automatically falls back to the pre-Defuddle…
  • 100web-read
    Extract clean, readable markdown from a web page with the Defuddle CLI — strips nav, ads, and boilerplate to cut tokens versus WebFetch. Use when given a URL to read or analyze (docs, articles, blogs, changelogs, RFCs). Do NOT use for .md or JSON/API URLs — use WebFetch directly.
  • 100baoyu-url-to-markdown
    Fetch any URL and convert to markdown using Chrome CDP. Saves the rendered HTML snapshot alongside the markdown, uses an upgraded Defuddle pipeline with better web-component handling and YouTube transcript extraction, and automatically falls back to the pre-Defuddle…
  • 100youtube-content
    Fetch YouTube video transcripts and transform them into structured content (chapters, summaries, threads, blog posts). Use when the user shares a YouTube URL or video link, asks to summarize a video, requests a transcript, or wants to extract and reformat content from any YouTube video.
  • 100yt-transcript
    Fetch transcripts from YouTube videos. Use when user asks to get, download, extract, or retrieve YouTube video transcripts, captions, or subtitles. Also activates for video content analysis, summarizing YouTube videos, or processing video content.
  • 100web-to-markdown
    Convert a web URL into cleaned Markdown with deterministic routing. Use when Codex needs to read article-like content from links and should apply source-aware fetch strategies: default to r.jina.ai for general pages (including X/Twitter), use defuddle.md for YouTube links, and…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.