Agent skill

Defuddle

by kepano in kepano/obsidian-skills

Uses the Defuddle CLI to pull clean, readable Markdown, JSON or metadata from web pages, stripping navigation, ads and clutter to save tokens.

MITAuto-check passedKnowledge Management

Install Defuddle

skills CLI
$ npx skills add kepano/obsidian-skills --skill defuddle -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kepano/obsidian-skills defuddle --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kepano/obsidian-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/defuddle .claude/skills/defuddle && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
defuddle
GitHub stars
49k
Used in
11 other repos
Token cost
~208 tokens
SKILL.md length
70 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Uses the Defuddle CLI to pull clean, readable Markdown, JSON or metadata from web pages, stripping navigation, ads and clutter to save tokens.

  • Reading a standard web page without its navigation and ads
  • SKILL.md covers Usage and Output formats
  • Calls npm
  • Saving an article as clean Markdown in a local file

What it does

This skill tells the agent to use the Defuddle command-line tool instead of a generic fetch tool when it needs the readable content of a standard web page. The tool removes navigation, ads and other clutter, which cuts the number of tokens the agent has to read. If it is missing, it can be installed globally with npm.

The basic call is `defuddle parse` with a URL and the `--md` flag for Markdown, with `-o` to save the result to a file such as content.md. The `-p` flag pulls out a single metadata property, for example title, description or domain. Output can also be JSON holding both the HTML and the Markdown, or plain HTML when no format flag is given.

When your agent uses it

  • Reading a standard web page without its navigation and ads
  • Saving an article as clean Markdown in a local file
  • Pulling a page's title, description or domain
  • Cutting the token cost of fetching web content

Example prompts

  • “Fetch https://example.com/blog/launch as clean Markdown and save it to content.md.”
  • “Get the title and domain of https://example.com/docs/intro.”
  • “Read https://example.com/essay with defuddle instead of WebFetch to save tokens.”

Requirements

  • The Defuddle CLI, installed with npm install -g defuddle
  • Network access to fetch pages

What it can do on your machine

Read from SKILL.md and the folder at commit 3ccff53. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Defuddle loads about 208 tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 70 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~208

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from kepano/obsidian-skills at commit 3ccff53, republished under its MIT licence (© kepano). 70 words, ~208 tokens.

Download SKILL.mdSave it as .claude/skills/defuddle/SKILL.md (or your agent's skills folder).
name
defuddle
description
Extract clean Markdown from HTML pages with Defuddle CLI.

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
defuddle parse <url> --md

Save to file:

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

Extract specific metadata:

bash
defuddle parse <url> -p title
defuddle parse <url> -p description
defuddle parse <url> -p domain

Output formats

FlagFormat
--mdMarkdown (default choice)
--jsonJSON with both HTML and markdown
(none)HTML
-p <name>Specific metadata property

© kepano, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/defuddle of kepano/obsidian-skills.

Open the folder on GitHubat commit 3ccff53

Used in 11 other repositories

We found 24 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 11 other GitHub owners. This page covers the copy in kepano/obsidian-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Defuddle next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Defuddle compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Defuddle this skillkepano/obsidian-skills49k11 repos~208Automated safety check: PassMIT
URL to Markdown FetcherJimLiu/baoyu-skills26k1 repos~2.1kAutomated safety check: PassMIT
Baoyu URL To Markdownsdyckjq-lab/llm-wiki-skill2.5k2 repos~3.2kAutomated safety check: PassNone
X to Markdown ConverterJimLiu/baoyu-skills26k4 repos~1.8kAutomated safety check: WarnMIT
Web To Markdownrookie-ricardo/erduo-skills935—~894Automated safety check: PassMIT
Web Page ReaderHKUDS/Vibe-Trading35k—~627Automated safety check: PassMIT

Similar skills

  • URL to Markdown Fetcher

    JimLiu/baoyu-skills

    Fetches a web page, X post, YouTube transcript or Hacker News thread through a Chrome-driven CLI and saves it as clean markdown.

    26k GitHub starsUsed in 1 repo~2.1k tokens
    Knowledge ManagementAuto-check passed
  • Baoyu URL To Markdown

    sdyckjq-lab/llm-wiki-skill

    Fetch any URL and convert to markdown using Chrome CDP. An agent skill from sdyckjq-lab/llm-wiki-skill.

    2.5k GitHub starsUsed in 2 repos~3.2k tokens
    Knowledge ManagementAuto-check passed
  • X to Markdown Converter

    JimLiu/baoyu-skills

    Saves tweets, threads and X Articles as Markdown files with YAML front matter, using an unofficial API that asks for your consent first.

    26k GitHub starsUsed in 4 repos~1.8k tokens
    Knowledge ManagementAuto-check: warnings
  • Web To Markdown

    rookie-ricardo/erduo-skills

    Convert a web URL into cleaned Markdown with deterministic routing.

    935 GitHub stars~894 tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Web Page Reader

    HKUDS/Vibe-Trading

    Converts web pages, articles and documentation links into clean Markdown through the read_url tool, which sends the full URL to the third-party Jina Reader service.

    35k GitHub stars~627 tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Clean Content Fetch

    LeoYeAI/openclaw-master-skills

    获取干净、可读的网页正文内容,适合现代网页、博客、新闻、公告和微信公众号文章抓取;支持网页正文提取、内容清洗、去噪、Markdown 输出,适用于普通 fetch 效果不佳、页面噪音较多或动态渲染干扰的场景。Clean content fetch for modern web pages, article extraction, WeChat article capture, content…

    2.2k GitHub stars~574 tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed

More from kepano/obsidian-skills

  • Knap Markdown Templates

    kepano/obsidian-skills

    Renders Markdown notes from Knap templates and JSON data on the command line, including notes built from Defuddle web page output.

    49k GitHub starsUsed in 2 repos~986 tokens
    Auto-check passed

Works with

Questions about Defuddle

What does Defuddle do?

Uses the Defuddle CLI to pull clean, readable Markdown, JSON or metadata from web pages, stripping navigation, ads and clutter to save tokens. This skill tells the agent to use the Defuddle command-line tool instead of a generic fetch tool when it needs the readable content of a standard web page. The tool removes navigation, ads and other clutter, which cuts the number of tokens the agent has to read.

When should I use Defuddle?

Defuddle fits situations like: reading a standard web page without its navigation and ads; saving an article as clean Markdown in a local file; pulling a page's title, description or domain; cutting the token cost of fetching web content.

How do I install Defuddle in Claude Code?

Run `npx skills add kepano/obsidian-skills --skill defuddle -a claude-code`. Or copy the skill folder (skills/defuddle in kepano/obsidian-skills) into .claude/skills/defuddle in your project. Claude Code loads it when a task matches its description.

How do I install Defuddle in Codex?

Run `npx skills add kepano/obsidian-skills --skill defuddle -a codex`. Or copy the skill folder (skills/defuddle in kepano/obsidian-skills) into .agents/skills/defuddle in your project. Codex loads it when a task matches its description.

Can I use Defuddle in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kepano/obsidian-skills --skill defuddle -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/defuddle, .gemini/skills/defuddle, .github/skills/defuddle and .opencode/skills/defuddle in your project.

What does Defuddle need to run?

Going by SKILL.md and its folder, Defuddle needs the command-line tools its instructions call (npm). Our summary lists: The Defuddle CLI, installed with npm install -g defuddle; Network access to fetch pages.

Does Defuddle access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Defuddle safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Defuddle use?

Defuddle is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Defuddle use?

About 208 tokens (SKILL.md is roughly 832 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Defuddle?

Skills that share tags, products or a category with Defuddle: URL to Markdown Fetcher (JimLiu/baoyu-skills, 26k stars), Baoyu URL To Markdown (sdyckjq-lab/llm-wiki-skill, 2.5k stars), X to Markdown Converter (JimLiu/baoyu-skills, 26k stars) and Web To Markdown (rookie-ricardo/erduo-skills, 935 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Defuddle?

kepano (a GitHub user) maintains it in kepano/obsidian-skills, which has 49,220 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 15, 2026.

Source: kepano/obsidian-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.