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
Evaluation results
53%
53%Offline Documentation Cache
Known site selector patterns
curl pipeline used
0%
100%
html2markdown tool used
0%
100%
include-selector flag present
0%
100%
Anthropic selector correct
0%
0%
MDN selector correct
0%
0%
GitHub docs include selector
0%
0%
GitHub docs exclude selector
0%
100%
Absolute links via --domain
0%
100%
Without context: $0.2829 · 1m 20s · 20 turns · 24 in / 4,669 out tokens
With context: $1.0174 · 4m 20s · 47 turns · 52 in / 11,963 out tokens
100%
100%Universal Article Extractor
Generic content extraction
curl pipeline used
0%
100%
html2markdown tool used
0%
100%
Generic include selector
0%
100%
Exclude selector used
0%
100%
Nav/header/footer excluded
0%
100%
Absolute links via --domain
0%
100%
Without context: $0.4471 · 1m 34s · 27 turns · 31 in / 5,005 out tokens
With context: $0.5325 · 1m 54s · 31 turns · 65 in / 6,291 out tokens
69%
59%Content Extraction for an Unfamiliar Site
Selector discovery workflow
grep HTML inspection
0%
33%
Content container patterns
0%
76%
Selector output test
0%
65%
Line count check
46%
86%
Broader fallback selector
20%
100%
Final extraction command
0%
60%
Without context: $0.4920 · 3m 4s · 24 turns · 27 in / 9,069 out tokens
With context: $0.9016 · 5m 20s · 34 turns · 35 in / 15,707 out tokens
- Repository
- NeverSight/skills_feed
- Commit
5342bca
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
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.