Fetch web content in multiple formats - HTML, JSON, plain text, Markdown, readable articles, and YouTube transcripts
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
#!/bin/bash
URL=$(jq -r '.tool_input.url // empty')
if [ -n "$URL" ]; then
jq -n --arg url "$URL" '{
"hookSpecificOutput": {
"hookEventName": "PostToolUseFailure",
"additionalContext": ("WebFetch failed. Retry using the fetch MCP tools instead. Use mcp__fetch__fetch_markdown for general web pages, mcp__fetch__fetch_json for APIs, or mcp__fetch__fetch_readable for article content. The URL was: <url>" + $url + "</url>")
}
}'
fi