Web Search
- 62 installs
- 186 repo stars
- Updated August 4, 2026
- aws-samples/sample-strands-agent-with-agentcore
Web Search is a Claude Code skill that gives an AI agent ddg_web_search and fetch_url_content tools to search the web and read page content for research.
About
This skill gives an AI agent two tools: a DuckDuckGo web search and a URL content fetcher that strips HTML boilerplate. A developer adds it to a Strands agent so the model can pull current information, news, and research from the web. It also defines a cite-tag format so the agent attributes factual claims to their sources.
- Adds ddg_web_search and fetch_url_content tools to an agent
- Searches DuckDuckGo and extracts clean text from any URL
- Includes a cite-tag citation format for factual claims
Web Search by the numbers
- 62 all-time installs (skills.sh)
- Ranked #6,256 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
web-search capabilities & compatibility
- Capabilities
- web search · web scraping
- Use cases
- web search · web scraping · research
What web-search says it does
Search the web and fetch content from URLs for current information, news, and research topics.
fetch_url_content automatically strips navigation, scripts, and boilerplate HTML
npx skills add https://github.com/aws-samples/sample-strands-agent-with-agentcore --skill web-searchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 62 |
|---|---|
| repo stars | ★ 186 |
| Last updated | August 4, 2026 |
| Repository | aws-samples/sample-strands-agent-with-agentcore ↗ |
What it does
Let an agent search DuckDuckGo and fetch clean page text for current information and research.
Who is it for?
Agents that need current information, news, or research pulled from live web pages with source citations.
When should I use this skill?
The user needs current information, news, or research that requires searching the web or reading a URL.
By the numbers
- 2 tools (ddg_web_search, fetch_url_content)
- up to 10 results per search
- default 50000-character fetch length
Files
Web Search
Available Tools
- ddg_web_search(query, max_results=5): Search DuckDuckGo and return results with title, snippet, and link.
- fetch_url_content(url, include_html=False, max_length=50000): Fetch a URL and extract clean text content.
Parameters
ddg_web_search
| Parameter | Type | Default | Description |
|---|---|---|---|
query | str | (required) | Search query string |
max_results | int | 5 | Number of results (max 10) |
fetch_url_content
| 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
- Use specific, targeted search queries for best results
- Set max_results to 3-5 for focused searches, up to 10 for broad research
- Use fetch_url_content to read full page content from search result links
- Break complex research into multiple targeted queries rather than one broad query
- fetch_url_content automatically strips navigation, scripts, and boilerplate HTML
- Reduce max_length for quick summaries or when you only need the beginning of a page
Citation Format
When presenting information from search results or 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 search results.
- The
sourceattribute should contain the title or name of the source. - The
urlattribute should contain the source URL when available. - Do NOT cite your own reasoning or general knowledge.
- If search results don't contain relevant information, inform the user rather than guessing.
- Use the minimum number of citations necessary to support claims.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What search engine does this skill use?
It searches DuckDuckGo via ddg_web_search and returns title, snippet, and link for each result.
How does it read a full page?
fetch_url_content fetches a URL and extracts clean text, automatically stripping navigation, scripts, and boilerplate HTML.