Skill

defuddle

Extract readable web content, removing navigation/ads to save tokens.

npx claudepluginhub otaviof/gosmith --plugin gosmith

Tool Access

This skill uses the workspace's default tool permissions.

Preview

1. **Validate**: If URL ends in `.md`, use WebFetch directly and return content

SKILL.md

Similar Skills

finishing-a-development-branch

174.6k

Verifies tests pass on completed feature branch, presents options to merge locally, create GitHub PR, keep as-is or discard; executes choice and cleans up worktree.

superpowers

systematic-debugging

174.6k

Guides root cause investigation for bugs, test failures, unexpected behavior, performance issues, and build failures before proposing fixes.

10 files

superpowers

writing-plans

174.6k

Writes implementation plans from specs for multi-step tasks, mapping files and breaking into TDD bite-sized steps before coding.

1 file

superpowers

Stats

Stars2

Forks0

Last CommitApr 8, 2026

Actions

View Source View Plugin View on GitHub View README

Defuddle

Instructions

Validate: If URL ends in .md, use WebFetch directly and return content

Parse arguments:

--property <name> → Extract metadata (title, description, domain, author, date)
--json → Return full JSON output
(default) → Return markdown content

Execute: npx -y defuddle parse <URL> --md (or with flags as specified)

Report:

Default: Print markdown content to stdout
Property mode: Print metadata value
JSON mode: Print full JSON structure

Edge cases:

.md URL: Skip defuddle, use WebFetch
Network error: "Failed to fetch content from "
Parse failure: "Defuddle could not extract content"
Missing property: "Property '' not found"

Usage Examples

Goal

Command

Parse to stdout

npx -y defuddle parse <url> --md

Get Metadata

npx -y defuddle parse <url> -p <property>

JSON Output

npx -y defuddle parse <url> --json

Options

-p <name>: Metadata (title, description, domain, author, date)

-o <file>: Save output to local file

--json: Full JSON output

--md: Markdown output (default for this skill)

Defuddle

Instructions

Validate: If URL ends in .md, use WebFetch directly and return content
Parse arguments:
- --property <name> → Extract metadata (title, description, domain, author, date)
- --json → Return full JSON output
- (default) → Return markdown content
Execute: npx -y defuddle parse <URL> --md (or with flags as specified)
Report:
- Default: Print markdown content to stdout
- Property mode: Print metadata value
- JSON mode: Print full JSON structure
Edge cases:
- .md URL: Skip defuddle, use WebFetch
- Network error: "Failed to fetch content from "
- Parse failure: "Defuddle could not extract content"
- Missing property: "Property '' not found"

Usage Examples

Goal	Command
Parse to stdout	`npx -y defuddle parse <url> --md`
Get Metadata	`npx -y defuddle parse <url> -p <property>`
JSON Output	`npx -y defuddle parse <url> --json`

Options

-p <name>: Metadata (title, description, domain, author, date)
-o <file>: Save output to local file
--json: Full JSON output
--md: Markdown output (default for this skill)