{
  "schema": "https://ai-atoms.com/schemas/skill-v1.json",
  "type": "skill",
  "id": "skill/defuddle",
  "version": "1.0.0",
  "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. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.",
  "system_prompt_fragment": "# Defuddle\n\nUse 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.\n\nIf not installed: `npm install -g defuddle`\n\n## Usage\n\nAlways use `--md` for markdown output:\n\n```bash\ndefuddle parse <url> --md\n```\n\nSave to file:\n\n```bash\ndefuddle parse <url> --md -o content.md\n```\n\nExtract specific metadata:\n\n```bash\ndefuddle parse <url> -p title\ndefuddle parse <url> -p description\ndefuddle parse <url> -p domain\n```\n\n## Output formats\n\n| Flag | Format |\n|------|--------|\n| `--md` | Markdown (default choice) |\n| `--json` | JSON with both HTML and markdown |\n| (none) | HTML |\n| `-p <name>` | Specific metadata property |",
  "applicable_domains": [
    "knowledge",
    "productivity",
    "notes"
  ],
  "invocation": [
    "/defuddle"
  ],
  "tags": [
    "obsidian",
    "markdown",
    "kepano",
    "knowledge-management"
  ],
  "authored_by": "kepano",
  "source_url": "https://github.com/kepano/obsidian-skills/blob/main/skills/defuddle/SKILL.md",
  "lifecycle": "stable",
  "category": "knowledge",
  "provenance": {
    "source": "kepano/obsidian-skills",
    "source_url": "https://github.com/kepano/obsidian-skills/blob/main/skills/defuddle/SKILL.md",
    "author": "Steph Ango (kepano)",
    "license": "MIT",
    "notes": "Imported by scripts/import-anthropic-skills.py."
  }
}