url-fetcher
0
总安装量
1
周安装量
安装命令
npx skills add https://github.com/aws-samples/sample-strands-agent-with-agentcore --skill url-fetcher
Agent 安装分布
amp
1
cline
1
opencode
1
cursor
1
continue
1
kimi-cli
1
Skill 文档
URL Fetcher
Available Tool
- fetch_url_content(url, include_html=False, max_length=50000): Fetch a URL and extract clean text content.
Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
url |
str | (required) | URL to fetch (must start with http:// or https://) |
include_html |
bool | False | Include raw HTML in response |
max_length |
int | 50000 | Maximum character length of extracted text |
Usage Guidelines
- Useful for reading articles, documentation, job postings, and other web content
- Automatically strips navigation, scripts, and boilerplate HTML
- Extracts page title and clean text content
- Use include_html=True only when you need to analyze the page structure
- Reduce max_length for quick summaries or when you only need the beginning of a page
Error Handling
- Returns error JSON if the URL is unreachable, times out (30s), or returns non-200 status
- Always check the
successfield in the response before using the content
Citation Format
When presenting information from fetched pages, wrap every specific claim in <cite> tags:
<cite source="SOURCE_TITLE" url="URL">claim text</cite>
Rules:
- Cite factual claims, statistics, quotes, and specific information from fetched content.
- The
sourceattribute should contain the page title or site name. - The
urlattribute should contain the fetched URL. - Do NOT cite your own reasoning or general knowledge.
- Use the minimum number of citations necessary to support claims.