Defuddle

Strips ads, nav bars, footers, and boilerplate from web pages before you ingest them into your wiki, leaving just the article body as clean markdown. Saves 40 to 60 percent on tokens for typical web articles. Wraps the defuddle-cli tool from kepano's repo and pipes output to `.raw/` for pickup by wiki-ingest. The ingest skill checks for it automatically when you pass a URL, so you don't always run it manually. Worth installing if you're pulling in a lot of web content. Some sites break the heuristics, but most articles clean up well. If it's not installed, ingest falls back to raw fetch.

skills.sh installs: 457
GitHub stars: 16.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add agricidaniel/claude-obsidian --skill defuddle --agent claude-code

Installs into .claude/skills of the current project.

Files

Defuddle

Treat Defuddle as an optional external extractor. This package supports inert URL plans and filesystem capture; it does not ship an enforcing network cleaner. Cleaning, raw capture, and wiki ingestion are separate operations.

Resolve the installed product root from this skill's own location, never from the selected vault or process working directory:

PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian
CORE="$PRODUCT_ROOT/scripts/claude-obsidian.py"
test -f "$CORE"

Every ../wiki/references/ link in this file resolves the same way, relative to this skill's own directory under $PRODUCT_ROOT, never relative to the selected vault's wiki/ directory. Upstream flags may be checked in a separately installed kepano/obsidian-skills reference, but do not override this package's privacy and transaction boundary.

Inert URL plan

Accept HTTPS URLs only. Reject credentials, fragments, controls, sensitive query parameters, and non-public hosts or IP addresses. Never interpolate a URL into a shell string. Use one argv element when constructing a plan:

SKILL.md on GitHub