web-fetch

Fetches web content with intelligent content extraction, converting HTML to clean markdown. Use for documentation, articles, and reference pages http/https URLs.

24.66x

Quality

—

Does it follow best practices?

Impact

74%

24.66x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

The body is highly actionable with executable commands and a clear fallback workflow, but it carries some redundant selector duplication and depends on a referenced Bun script that is not shipped in the bundle.

Suggestions

Remove the redundant 'Site Patterns' table or the overlapping selector examples in 'Quick Usage' so selector information lives in one place.

Bundle the referenced 'fetch.ts' script under scripts/ (and adjust the path) so the universal-fallback path works without an external install, or replace the missing-script dependency with self-contained instructions.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with terse commands and tables, but the 'Site Patterns' table largely duplicates the selectors already shown in the 'Quick Usage' code block — content that could be tightened to remove redundancy.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands — 'curl -s "<url>" \| html2markdown --include-selector ...' and the Bun fallback — plus concrete diagnostic grep commands, matching the executable-and-specific anchor.	3 / 3
Workflow Clarity	The flow is unambiguous for a simple skill: site-specific selectors first, then the universal Bun fallback, then a 'Finding the Right Selector' diagnostic sequence, with a troubleshooting section. No destructive/batch operations require validation checkpoints.	3 / 3
Progressive Disclosure	Sections are well organized, but the universal-fallback path depends on a Bun script referenced at '~/.claude/skills/web-fetch/fetch.ts' that is not present in the bundle (no references/, scripts/, or assets/ directories exist) — a signaled reference to a missing file.	2 / 3
	Total	10 / 12 Passed

Description

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.

A strong, concise description that states concrete capabilities and provides explicit 'Use for' trigger guidance covering natural user terms. It is clearly distinct from generic skills and answers both what and when.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Fetches web content', 'intelligent content extraction', 'converting HTML to clean markdown' — matching the multi-action anchor. The word 'intelligent' is mildly buzzword-ish but does not reduce the action list below comprehensive.	3 / 3
Completeness	Answers both what ('Fetches web content... converting HTML to clean markdown') and when via the explicit 'Use for documentation, articles, and reference pages' clause, matching the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Includes natural trigger phrasings a user would actually say — 'documentation', 'articles', 'reference pages' — giving good coverage of common terms.	3 / 3
Distinctiveness Conflict Risk	The HTML-to-markdown conversion niche is distinct and unlikely to trigger for unrelated skills; the 'Use for' triggers are specific to web content fetching.	3 / 3
	Total	12 / 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: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 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.