defuddle

Extract clean Markdown from web pages. In the KB workflow, use it as a utility under obsidian-source-ingestion.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/defuddle/SKILL.md

Quality

Content

100%

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

The content body is exemplary for a simple utility skill: concise, actionable, and well-organized with an executable command and clear target. It adds only what Claude would not already infer about the KB workflow integration.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding or explanation of concepts Claude already knows; every token earns its place.	3 / 3
Actionability	It provides a concrete, copy-paste-ready command (`defuddle parse <url> --md`) plus a specific target directory, fully executable without ambiguity.	3 / 3
Workflow Clarity	This is a simple single-task skill where the action is unambiguous; per the scoring notes, workflow clarity can score 3 in that case, and no destructive or batch operations require validation checkpoints.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no need for external references, and its sections are well-organized, satisfying the simple-skill exemption for full progressive disclosure.	3 / 3
	Total	12 / 12 Passed

Description

57%

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

The description clearly states what the skill does and situates it within a specific KB workflow, but it lacks an explicit trigger clause and broader natural keyword coverage. It is distinctive but not maximally actionable for discovery.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants clean Markdown from a web page or article.'

Broaden trigger terms with natural phrasings like 'scrape', 'article', or 'clean HTML'.

List additional concrete actions if the tool supports them (e.g. extract main content, strip boilerplate) to reach full specificity.

Dimension	Reasoning	Score
Specificity	Names a single concrete action ("Extract clean Markdown from web pages") but does not list multiple specific actions, so it falls short of the score-3 anchor.	2 / 3
Completeness	The "what" is explicit (extract clean Markdown from web pages) but "when" is only implied via the KB-workflow note; there is no explicit "Use when..." clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Relevant keywords like "web pages", "Markdown", and "KB workflow" appear, but common natural variations a user might say (e.g. "scrape", "article", "clean HTML") are missing.	2 / 3
Distinctiveness Conflict Risk	The niche is clearly scoped to web-to-Markdown extraction under obsidian-source-ingestion, making it unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 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: Galaxy-Dawn/claude-scholar
Path: skills/defuddle/SKILL.md
Commit: 2f7766f

Reviewed: about 14 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.