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
Quality
83%
Does it follow best practices?
Impact
74%
24.66xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description adequately communicates the core functionality and includes explicit 'Use for' guidance, which is good. However, it could benefit from more specific action verbs and better coverage of natural trigger terms users would actually say when needing this skill. The description is functional but not optimally distinctive.
Suggestions
Add more natural trigger terms users would say, such as 'webpage', 'website', 'link', 'fetch URL', 'scrape', or 'read page content'
Expand specific capabilities beyond just 'content extraction' - mention handling of images, links, code blocks, or other specific content types if applicable
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (web content) and some actions ('fetches', 'converting HTML to clean markdown'), but lacks comprehensive specific actions like handling pagination, extracting metadata, or dealing with different content types. | 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 terms ('documentation', 'articles', 'http/https URLs') but misses common variations users might say like 'webpage', 'website', 'link', 'URL', 'scrape', or 'download page'. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to web fetching but could overlap with general web scraping skills or browser automation skills. The focus on 'clean markdown' conversion helps distinguish it, but 'web content' is still fairly broad. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that demonstrates best practices: concise executable examples, clear site-specific patterns in a scannable table, a logical progression from simple to complex use cases, and practical troubleshooting guidance. The content respects Claude's intelligence while providing the specific selectors and commands needed for immediate use.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing direct commands and tables without explaining what curl or HTML is. Every section serves a purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable bash commands that are copy-paste ready, with specific CSS selectors for known sites and clear fallback options. The comparison table and troubleshooting section add practical value. | 3 / 3 |
Workflow Clarity | Clear progression from quick usage (known sites) to universal fallback (unknown sites) to finding selectors manually. The troubleshooting section provides feedback loops for common failure modes. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from simple to complex. References the external Bun script appropriately without deep nesting. Tables provide scannable reference information. | 3 / 3 |
Total | 12 / 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
5342bca
- 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.