- Home
- Skills
- Workflow Automation
- Apikey Free Search
Works with the AI Agents you already use
Apikey Free Search
Free web search through DuckDuckGo with no API key: text, news, image and video results, instant answers, rate-limit-aware querying with retries, and a Bing fal
Free
Apikey Free Search
Example session with this skill installed
Search for the latest news on 'quantum computing advancements' in the us-en region and return the top 5 results as JSON.
- Read your context and instructions
- Compiled the apikey free search
[
{"title": "New Breakthrough in Superconducting Qubits", "url": "https://example.com/news/1", "source": "Tech Daily"},
{"title": "Quantum Error Correction Reaches Milestone", "url": "https://phys.org/news/2", "source": "Science Wire"}
]
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Integrating paid search APIs is overkill for casual tasks, side projects, or scripts that just need a few fresh links. Dealing with API keys, credits, and usage tiers adds unnecessary friction to simple automation workflows.
What it does
- Performs text, news, image, and video searches using DuckDuckGo without requiring an API key.
- Retrieves instant answers for factual queries to bypass full page parsing.
- Implements rate-limit discipline with exponential backoff and retries to maintain connection stability.
- Provides a Bing fallback mechanism that normalizes HTML scrapes into a consistent JSON format.
- Handles regional filtering for localized search results across major global locales.
Frameworks & tools
Python, ddgs library, BeautifulSoup/tolerant HTML parsers.
Why this beats prompting it yourself
Standard LLM prompts often fail to handle the structural nuances of search result objects or the timing required to avoid IP blocks. This skill provides a specific retry logic and a cross-engine fallback strategy that ensures your agent doesn't get stuck when one provider throttles requests.
Use cases
- Gathering recent news coverage or articles for automated newsletters.
- Sourcing image and video URLs for dynamic gallery generation.
- Fact-checking simple queries using instant answer endpoints.
- Scaffolding research tasks by deduplicating top results across multiple engines.
Known limitations
Not suitable for high-volume commercial scraping. Requires a 1-2 queries per second courtesy ceiling to avoid blocks. Result formats may change if providers update their HTML structure.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills to Reverse Engineer and Scrape Websites.
Best for low-volume usage under 2 queries per second. Free endpoints may break if provider HTML structures change. Not intended for high-availability commercial SLAs.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
5 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account
- Software
Python
Permissions
No special permissions declared or detected