web-fetch
Fetches web content with intelligent content extraction, converting HTML to clean markdown. Use for documentation, articles, and reference pages http/https URLs.
83
83%
Does it follow best practices?
Impact
74%
24.66xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
75%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 is functional and covers both what the skill does and when to use it, with a reasonably distinct niche. However, it could benefit from more specific concrete actions and broader trigger term coverage to capture natural user language like 'scrape', 'read webpage', or 'browse a link'. There's also a minor grammatical issue ('reference pages http/https URLs' reads awkwardly).
Suggestions
Add more natural trigger terms users would say, such as 'scrape', 'read webpage', 'browse', 'website', 'open link', or 'fetch URL'.
List more specific concrete actions beyond fetching and converting, e.g., 'extracts article text, retrieves documentation pages, pulls content from URLs'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (web content fetching) and some actions (content extraction, converting HTML to markdown), but doesn't list multiple distinct concrete actions beyond fetch and convert. | 2 / 3 |
Completeness | Clearly answers both what ('Fetches web content with intelligent content extraction, converting HTML to clean markdown') and when ('Use for documentation, articles, and reference pages http/https URLs'), with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'web content', 'HTML', 'markdown', 'documentation', 'articles', 'http/https URLs', but misses common user terms like 'fetch URL', 'scrape', 'read webpage', 'browse', 'website', or 'link'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of web fetching, HTML-to-markdown conversion, and URL-based triggers creates a clear niche that is unlikely to conflict with other skills like general document processing or code generation. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-crafted skill that provides immediately actionable guidance for web content fetching. It efficiently covers common site patterns, a universal fallback, selector discovery, and troubleshooting without unnecessary explanation. The only weakness is minor redundancy between the quick usage examples and the site patterns table, and the lack of bundle files to support the referenced Bun script.
Suggestions
Consider removing the site patterns table since it duplicates the quick usage section, or consolidate them into a single representation to reduce redundancy.
Include the referenced fetch.ts script in the bundle so the universal fallback is fully self-contained and verifiable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what curl is, what markdown is, or how CSS selectors work—it assumes Claude's competence. Every section provides direct, usable information without padding. | 3 / 3 |
Actionability | Provides fully executable, copy-paste-ready bash commands for multiple site patterns, a universal fallback script, selector discovery commands, and a clear options reference. Nothing is left vague or abstract. | 3 / 3 |
Workflow Clarity | The workflow is clear: try known site patterns first, fall back to the Bun script for unknown sites, and use the selector discovery process when neither works. The troubleshooting section provides a feedback loop for common failure modes (wrong content, empty output, JS-rendered pages). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a logical progression from quick usage to fallback to troubleshooting. However, the bundle references a fetch.ts script at ~/.claude/skills/web-fetch/fetch.ts but no bundle files are provided, making it impossible to verify the reference. The content is also somewhat long and the site patterns table partially duplicates the quick usage section. | 2 / 3 |
Total | 11 / 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
- NeverSight/skills_feed
- Commit
aa009ea
- 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.