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.

Quality

93%

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

Quality

Content

92%Scale 1-5

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

This is a well-crafted, concise skill that provides clear, actionable CLI commands for a single-purpose tool. It efficiently communicates when to use Defuddle, how to use it, and what output options are available. The only minor weakness is slight redundancy between the intro and the 'When to Use' section.

Dimension	Reasoning	Score
Conciseness	Mostly efficient. The 'When to Use' section has minor redundancy with the intro paragraph (both mention preferring over WebFetch, token efficiency). The rest is lean and assumes Claude's competence.	4 / 5
Actionability	Fully executable, copy-paste ready commands covering the common cases: basic usage, saving to file, extracting metadata. The install command is also provided. All commands are concrete and specific.	5 / 5
Workflow Clarity	This is a simple, single-purpose skill (run a CLI command to extract content). The single action is unambiguous, and the various usage patterns are clearly presented. No destructive or batch operations require validation steps.	5 / 5
Progressive Disclosure	For a simple skill under 50 lines with no need for external references, the content is well-organized with clear sections (When to Use, Usage, Output formats). The output format table is a nice concise reference. No external files are needed.	5 / 5
	Total	19 / 20 Passed

Description

95%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.

This is a strong skill description that clearly communicates what the skill does (extract markdown from web pages), when to use it (when a user provides a URL for reading/analyzing), and how it differs from alternatives (use instead of WebFetch). The inclusion of multiple natural trigger terms and explicit routing guidance makes it highly effective for skill selection.

Dimension	Reasoning	Score
Specificity	Describes concrete actions: 'Extract clean markdown content from web pages', 'removing clutter and navigation to save tokens'. Names the tool (Defuddle CLI) and the output format (markdown). Could list more specific capabilities but covers the core well.	4 / 5
Completeness	Clearly answers both 'what' (extract clean markdown from web pages using Defuddle CLI, removing clutter) and 'when' (when user provides a URL to read or analyze, for documentation, articles, blog posts, or standard web pages). The 'Use instead of WebFetch' clause adds explicit routing guidance.	5 / 5
Trigger Term Quality	Excellent coverage of natural trigger terms: 'URL', 'web pages', 'online documentation', 'articles', 'blog posts', 'read', 'analyze'. Also includes the differentiator 'Use instead of WebFetch' which helps with routing. These are terms users would naturally use.	5 / 5
Distinctiveness Conflict Risk	Highly distinctive by explicitly differentiating from WebFetch, specifying the tool (Defuddle CLI), and narrowing to URL-based web page content extraction. The 'Use instead of WebFetch' clause directly addresses potential conflict with a similar skill.	5 / 5
	Total	19 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/defuddle/SKILL.md
Commit: 8a63c75

Reviewed: ~6 hours 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.