· 1 observation
Technical updates · 1
Package or technical metadata updated
View technical comparison →RONALD FERRARI SOARES v0.19.4
Clean article extraction
Developer declarations; not independently tested. Listing last checked Nov 4, 2026. Package observed Nov 3, 2026.
Not specified in the available declarations: limitations, pricing & account requirements.
Extract the readable content from this page
From the marketplace listing
Guides extraction of readable article content from noisy pages and documents. Actual fetching or page access depends on tools available in the host environment.
Language: English · Automatically detected from descriptions.
Exact text from the indicated source. A mention alone does not establish support for your task.
Article extraction guidance HTML-to-Markdown workflows
web extraction markdown html metadata cli
· 1 observation
Package or technical metadata updated
View technical comparison →· 2 observations
Package or technical metadata updated
View technical comparison →· 2 observations
Package or technical metadata updated
View technical comparison →Find competitors to follow as you develop your plugin.
Read clean, source-grounded text from public articles and YouTube videos. Use smry to summarize key points, compare sources, answer quest...
Shared terms: article, clean, source
Create SEO, AEO, and GEO articles with research-based FAQs, internal-link plans, metadata, schema suggestions, and image plans.
Shared terms: article, metadata, content
Inspect supported hidden information in ordinary Word and PDF documents and create a separately verified cleaned copy. Hosted processing ...
Shared terms: clean, metadata, document, content
Create and optimize web content for GEO, AI visibility, citations, and brand mentions.
Shared terms: article, guide, content, page
Search and read public, source-linked Swedish relocation guides from SwedishExpat.
Shared terms: guide, primary, document, source
--- name: defuddle-web-content description: Use when the user asks to extract the main readable article or page content from a public web page while removing navigation, ads, and other clutter. license: MIT compatibility: Requires a local Node.js/npm environment to execute Defuddle. The bundled source is reference material and does not install the runtime automatically. --- # Defuddle Web Content ## Host capability adaptation 1. **Native host capability:** when ChatGPT/Codex exposes a native tool or connected source that satisfies this task, use it. 2. **Original external runtime:** when the upstream runtime named by this skill is actually available, use it as documented below. 3. **Instruction-only fallback:** when neither is available, perform only the reasoning/instruction portion that remains valid, state the limitation, and never fabricate tool output, successful execution, or persisted state. Use an equivalent native host capability when available; otherwise perform only the instruction-based portion and clearly disclose the unavailable runtime. Use Defuddle when a local terminal/runtime is available and the task calls for removing navigation, ads, sidebars, comments, and other page clutter while preserving the main content and metadata. ## Preferred CLI flow Use `npx defuddle` so a global installation is not required: ```bash npx defuddle parse <source> --markdown ``` `<source>` may be a URL or local HTML file. HTML may also be piped on stdin. Common output modes: ```bash npx defuddle parse page.html --markdown npx defuddle parse page.html --json npx defuddle parse page.html --frontmatter npx defuddle parse page.html --property title ``` For exact CLI options and Node/browser API usage, read `references/source/README.md`. ## Runtime rule Do not claim Defuddle extracted a page unless the command or library actually ran successfully. If the environment cannot execute Node/npm or cannot access the requested URL, explain that limitation and use another available reading method only if the user permits it. ## Source reference The bundled `references/source/src/` directory contains the original 0.19.4 TypeScript source for implementation/reference purposes. It is not an installed npm dependency.
Referenced files: 69 — file references are metadata, not package contents.
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Package observed Nov 3, 2026.
plugins_6ab01bcd65ac819188faeba97d476fcb
Download plugin data (JSON)