Defuddle
Skill Warning ActiveExtract 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. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.
Extract clean, token-efficient markdown content from web pages to facilitate analysis or storage, avoiding unnecessary clutter and navigation elements.
Features
- Extracts clean markdown content from web pages.
- Removes clutter, ads, and navigation from fetched content.
- Reduces token usage for LLM processing.
- Supports saving output to a file.
- Extracts specific metadata like title, description, and domain.
Use Cases
- When needing to analyze the content of an article, blog post, or online documentation.
- When saving web content for later use and wanting to minimize token count.
- As an alternative to `WebFetch` for standard web pages that require content cleaning.
Non-Goals
- Processing URLs that already end in `.md` (use `WebFetch` directly).
- Replacing general-purpose web fetching for all URL types.
- Performing complex web interactions beyond simple page fetching and parsing.
Maintenance
- critical:Commit recencyThe last commit was over 12 months ago (2026-05-07), indicating the project is likely unmaintained and poses a risk due to potential dependency drift.
- warning:Dependency ManagementThe extension depends on the `defuddle` CLI tool (npm install), but there are no apparent measures for updating or merging dependencies, nor vulnerability checks mentioned.
Security
- warning:Transitive Supply-Chain GrenadesThe skill relies on an external npm package (`defuddle`) which is not version-pinned, creating a potential supply-chain risk if the package changes maliciously.
Trust
- warning:Issues AttentionThere are 20 issues opened in the last 90 days and only 3 closed, indicating slow maintainer responsiveness and a low closure rate.
Versioning
- warning:Release ManagementThere is no explicit versioning in the SKILL.md frontmatter or a changelog, and installation instructions reference the main branch, making it difficult to pin a specific version.
Execution
- warning:Pinned dependenciesThe skill depends on the `defuddle` npm package, but this dependency is not pinned, and no lockfile is present, increasing the risk of unexpected behavior from updates.
Installation
First, add the marketplace
/plugin marketplace add kepano/obsidian-skills/plugin install obsidian-skills@obsidian-skillsQuality Score
WarningSimilar Extensions
Agent Browser
100Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Trader Regime
100Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy
Setup
100Use first for install/update routing — sends setup, doctor, or MCP requests to the correct OMC setup flow
Project Session Manager
100Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
Mcp Setup
100Configure popular MCP servers for enhanced agent capabilities
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly