Skills Guide

Clean web content extraction

VerifiedCaution

Use Defuddle CLI to extract clean markdown content from web pages, removing clutter and saving tokens.

Download and use
Sby Skills Guide Bot
ContentBeginner
7/24/2026
Claude CodeCursorWindsurfCodex
#web-extraction#markdown#token-efficiency#cli#readability

Recommended for

Claude CodeCursorWindsurfCodexUI/UX designerSEO & content

Automated summary

Uses the Defuddle CLI to pull the readable content out of a web page as clean markdown, stripping navigation, ads and clutter.

Strengths

  • Markdown output via `--md` that is directly usable and far cheaper in tokens than raw HTML
  • Removes navigation and boilerplate from standard web pages
  • Targeted metadata extraction (`-p title`, `-p description`, `-p domain`)
  • Can write results to a file with `-o content.md` for later reuse

Limitations

  • Requires a prior global install via `npm install -g defuddle`
  • No guidance for login-protected, paywalled, or heavily JavaScript-rendered pages
  • No documented way to process several URLs in one command
When to use it

Use it whenever a user supplies a standard web page URL to read, summarize, or analyze, such as an article, docs page, or blog post.

When not to use it

Avoid it for pages behind a login, pages that depend on complex JavaScript rendering, or non-HTML resources like PDFs and JSON APIs.

Security analysis

Caution
Quality score80/100

This is a straightforward wrapper around a real, known CLI (defuddle by kepano) for extracting readable markdown from web pages. There is nothing destructive or exfiltrating: no secrets are read or sent anywhere, no encoded payloads, no forced remote install scripts. The risk profile is 'caution' rather than 'safe' because it requires unattended shell execution and a global npm install of an unpinned package, and it performs outbound fetches of arbitrary URLs — all legitimate but powerful.

Findings
  • •Instructs a global install via `npm install -g defuddle`, which mutates the host environment and requires trusting an unpinned third-party npm package (supply-chain risk, no version pin or integrity check).
  • •Skill body depends on shell/bash execution to run the `defuddle` CLI, yet the frontmatter declares no allowed-tools — the declared capability surface does not match what the instructions actually require.
  • •Fetches arbitrary user-supplied URLs over the network with no allowlist or scheme validation, so it could be pointed at internal/metadata/localhost endpoints (SSRF-style) if a user pastes such a URL.
  • •`-o content.md` writes output to the current working directory with no path restriction, so output location is not constrained.
  • •No obfuscation, no `curl | sh`, no credential/token handling, and no attempts to disable safety controls — the described actions are all transparent and consistent with the stated purpose.
How this analysis is made

Examples

Summarize an article
Read https://example.com/blog/why-markdown-matters and summarize the key arguments in five bullets.
Save docs to a file
Extract the page at https://docs.example.com/getting-started as markdown and save it to content.md so we can work through it.
Grab page metadata
Get the title, description and domain for https://example.com/landing-page.

name: defuddle description: Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. risk: unknown source: "https://github.com/kepano/obsidian-skills" date_added: "2026-03-21"

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.

When to Use

  • Use when the user provides a normal webpage URL to read, summarize, or analyze.
  • Prefer it over noisy page-fetch approaches when token efficiency matters.
  • Use for docs, articles, blog posts, and similar public web content.

If not installed: npm install -g defuddle

Usage

Always use --md for markdown output:

defuddle parse <url> --md

Save to file:

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

Extract specific metadata:

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 |

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/clean-web-content-extraction-mryiqilv' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/clean-web-content-extraction-mryiqilv/download' --output '.skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md.part' && mv '.skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md.part' '.skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md' && test -s '.skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/defuddle' && cp -R '.skill-downloads/clean-web-content-extraction-mryiqilv' '.claude/skills/defuddle'

Cursor
test -f '.skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md' && test -s '.skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/defuddle' && cp -R '.skill-downloads/clean-web-content-extraction-mryiqilv' '.cursor/skills/defuddle'

Codex
test -f '.skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md' && test -s '.skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/defuddle' && cp -R '.skill-downloads/clean-web-content-extraction-mryiqilv' '.agents/skills/defuddle'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/clean-web-content-extraction-mryiqilv'

openskills read 'clean-web-content-extraction-mryiqilv'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/clean-web-content-extraction-mryiqilv/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Writing Fragments

Content

Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.

Claude CodebeginnerSafe 240,316
Skills Guide Bot

UI Copywriting & Auditing

Content

Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.

Claude CodeCursorbeginnerSafe 108,623
Skills Guide Bot

Music MIDI Extraction

Content

Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.

Claude CodebeginnerSafe 69,866
Skills Guide Bot