CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is defuddle in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A clean, well-structured, highly actionable single-purpose skill body: copy-paste commands, an output-format table, and an install precondition, all within a tight token budget. The only minor flaw is slight redundancy between the intro/When-to-use prose and the frontmatter description.

DimensionReasoningScore

Conciseness

The body is lean with executable commands and a compact table, but the intro line and 'When to Use' bullets restate the frontmatter description, adding minor redundancy that keeps it just short of a 5.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands covering the common cases — `defuddle parse <url> --md`, file output with `-o`, metadata extraction via `-p`, and an output-format table — matching the anchor for comprehensive executable guidance.

5 / 5

Workflow Clarity

This is a simple single-purpose skill (under 50 lines, one task) where the single action is unambiguous (`defuddle parse <url> --md`), and it even includes a precondition check ('If not installed: npm install -g defuddle'), meeting the simple-skill exception for a 5.

5 / 5

Progressive Disclosure

Under 50 lines with no bundle files and no need for external references, yet well-organized into clearly headed sections (When to Use, Usage, Output formats), satisfying the simple-skill exception for a 5.

5 / 5

Total

19

/

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 strong description that clearly states both capability and trigger conditions and distinguishes itself from the overlapping WebFetch tool. The only weakness is modest action breadth — it describes one extraction capability with a couple of attributes rather than several distinct actions.

DimensionReasoningScore

Specificity

Names the domain (web pages / markdown extraction) and two concrete actions ('Extract clean markdown content', 'removing clutter and navigation'), but these are variations of one core extraction capability rather than multiple distinct actions, so it is not comprehensive enough for a 4.

3 / 5

Completeness

Explicitly answers both what ('Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation') and when ('Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user terms — 'URL to read or analyze', 'online documentation', 'articles', 'blog posts', 'standard web page' — giving good keyword coverage, though it stops short of comprehensive synonyms/extensions needed for a 5.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (Defuddle-based clean markdown extraction) and explicitly differentiates from WebFetch, giving it distinct triggers with minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.