defuddle

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.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is defuddle in kepano/obsidian-skills

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary short skill body: lean, fully executable, and well-organized with no padding and no missing references. It appropriately assumes Claude's competence while providing concrete commands for every common use case.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: a tight intro, a one-line install instruction, and compact executable blocks with no re-explanation of concepts Claude already knows; the only near-redundancy ('removes navigation, ads, and clutter, reducing token usage') is minor and earns its place.	5 / 5
Actionability	Fully executable, copy-paste-ready CLI commands covering the common cases (parse to markdown, save to file, extract specific metadata) plus a clear output-format table.	5 / 5
Workflow Clarity	Simple single-purpose read-only skill where the single action ('defuddle parse <url> --md') is unambiguous, with an install-if-needed conditional; the simple-skill exception applies and no destructive/batch validation cap is triggered.	5 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed, with well-organized sections (Usage, Output formats); per the simple-skills note this qualifies for 5 on structure alone.	5 / 5
	Total	20 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description that clearly states what the skill does, when to use it, and when not to, with explicit boundary guidance against WebFetch. Its only weakness is moderate action specificity, listing essentially one core action rather than several distinct capabilities.

Suggestions

Add one or two more concrete actions to broaden capability specificity (e.g., 'save extracted content to a file' or 'pull specific metadata like title, description, or domain'), which are demonstrated in the body but not surfaced in the description.

Include common user synonyms such as 'webpage', 'scrape a page', or 'extract text from a URL' to broaden natural trigger coverage beyond the current set.

Dimension	Reasoning	Score
Specificity	Names the domain (web pages) and one main concrete action ('Extract clean markdown content ... removing clutter and navigation') but does not list several distinct actions, matching the anchor for 1-2 concrete actions rather than the 'several specific actions' of a 4.	3 / 5
Completeness	Explicitly answers 'what' (extract clean markdown from web pages via Defuddle CLI) and 'when' with concrete trigger phrases ('Use instead of WebFetch when the user provides a URL ... for online documentation, articles, blog posts'), plus a negative boundary clause.	5 / 5
Trigger Term Quality	Includes natural user-facing terms ('URL to read or analyze', 'online documentation', 'articles', 'blog posts', 'standard web page') with good coverage, but misses a few synonyms (e.g., 'webpage', 'scrape', 'extract text') that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (web-page content extraction via Defuddle), distinct triggers, and explicit disambiguation from WebFetch including a .md exclusion ('Do NOT use for URLs ending in .md — use WebFetch directly'), minimizing conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: breferrari/obsidian-mind
Path: .claude/skills/defuddle/SKILL.md
Commit: b84464b

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.