defuddle

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

Quality

68%

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

82%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.

The body is exceptionally lean and contains one genuinely executable command, but it is thin on integration detail — the output destination and its relationship to the KB target directory are implied rather than stated. Structure is adequate for a skill this size.

Dimension	Reasoning	Score
Conciseness	The ~13-line body has zero padding and explains nothing Claude already knows; every line carries information (role, target directory, command), matching the 'lean and efficient' anchor.	5 / 5
Actionability	"defuddle parse <url> --md" is a real, executable command in copy-paste form, but only one templated invocation is given with no example or output options — minor gaps per the score-4 anchor.	4 / 5
Workflow Clarity	As a simple single-purpose skill the action is mostly unambiguous, but how the command's output lands in `Sources/Web/` is implicit rather than shown, so it fits 'clear sequence with minor gaps' rather than 5.	4 / 5
Progressive Disclosure	Under 50 lines with no bundle files, content is appropriately inline and navigable; structure is adequate but minimal (flat labels instead of sections), matching 'good structure, minor organization gaps'.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description states a clear, concrete capability but lacks explicit trigger guidance: no 'Use when...' clause and few natural keyword variations. It is distinct within its niche yet under-specified for reliable skill selection.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to save a webpage, URL, or article as Markdown" — this would raise completeness from the capped 3.

Include natural synonyms users would say ("webpage", "URL", "article", "clip a page") in the description to improve trigger term coverage.

Optionally mention an additional concrete capability (e.g. output format or site-specific extraction) to move specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	"Extract clean Markdown from web pages" names the domain and one concrete action, matching the '1-2 concrete actions, not comprehensive' anchor; it stays at 3 because no further actions or capabilities are listed.	3 / 5
Completeness	The 'what' is clear (extract clean Markdown from web pages), but the 'when' is only weakly implied by "In the KB workflow, use it as a utility under obsidian-source-ingestion" — there is no explicit 'Use when...' trigger clause, which caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like "Markdown", "web pages", and "obsidian-source-ingestion" are relevant, but natural user phrasings ("webpage", "URL", "clip/save a page", "article") are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Web-to-Markdown extraction is a distinct niche and scoping under obsidian-source-ingestion reduces overlap; only minor conflict risk with generic web-fetch skills keeps it below 5.	4 / 5
	Total	13 / 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: Galaxy-Dawn/claude-scholar
Path: skills/defuddle/SKILL.md
Commit: 9037873

Reviewed: 2 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.