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.
80
100%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 an excellent skill description that clearly communicates what the skill does, when to use it, and critically, when NOT to use it. The explicit differentiation from WebFetch and the negative trigger for .md files make it exceptionally useful for skill selection in a multi-skill environment. The natural trigger terms cover a broad range of user phrasings.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: 'Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens.' This names the tool, the transformation (clean markdown extraction), and the benefit (saving tokens). | 3 / 3 |
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/analyze, for documentation, articles, blog posts). Also includes explicit 'do NOT use' guidance for .md URLs, which adds selection clarity. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'URL', 'web pages', 'online documentation', 'articles', 'blog posts', 'read or analyze'. Also includes negative triggers for .md files. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — explicitly differentiates itself from WebFetch, specifies its niche (web page content extraction via Defuddle), and includes a clear negative boundary (.md files). This makes it very unlikely to conflict with similar skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, lean skill that does exactly what it needs to. It provides concrete, executable commands without any unnecessary explanation, assumes Claude's competence, and is well-structured with a clear usage section and a helpful reference table. The skill description's guidance about when to use vs. not use this tool (e.g., skip for .md URLs) complements the body content well.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every token earns its place. No unnecessary explanations of what web scraping is or how CLI tools work. The one-liner install instruction and concise usage examples are exactly what Claude needs. | 3 / 3 |
Actionability | Provides fully executable, copy-paste ready commands for all common use cases. The flag reference table and specific metadata extraction examples give concrete guidance for every scenario. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose skill (run a CLI command to extract content). The single action is unambiguous, and the install prerequisite is clearly noted. No multi-step destructive operations require validation checkpoints. | 3 / 3 |
Progressive Disclosure | For a simple skill under 50 lines with no need for external references, the content is well-organized into logical sections (Usage, Output formats) with clear structure. No external files are needed. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- kepano/obsidian-skills
- Commit
ac93987
- Reviewed
Table of Contents
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.