Moark Web Search for Openclaw

A powerful web search integration for AI agents to retrieve real-time webpages, images, and video content via the Gitee AI API.

fchange
v1.0.0
Mar 24, 2026
0
759
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install moark-web-search

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install moark-web-search using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Moark Web Search?

Moark Web Search is a robust technical integration designed to provide AI agents with real-time access to the live web. By leveraging the Gitee AI API, this skill enables agents to look up current events, verify facts, and discover multimedia content across the internet. It is a vital component for developers building within the ecosystem of Openclaw Skills who require their agents to move beyond static training data.

The skill is built to be highly configurable, allowing for precise control over search depth, content freshness, and result types. Whether you are performing a deep dive into corporate ESG reports or seeking the latest industry news, Moark Web Search ensures your agent stays informed with accurate, up-to-date information directly from primary web sources.

Moark Web Search Use Cases

  • Performing real-time fact-checking and information lookup for user queries.
  • Discovering recent industry whitepapers, reports, or news articles using time-based filters.
  • Sourcing high-quality images and videos for multimedia-rich agent responses.
  • Automating competitive research and data gathering for specific niches.

How Moark Web Search Works

  1. The AI agent receives a natural language query or specific keyword from the user.
  2. The perform_web_search.py script is executed with tailored parameters such as query, freshness, and result count.
  3. The script communicates with the Gitee AI /web-search API using the provided Bearer token.
  4. The raw API response is processed to locate the SEARCH_RESULTS_JSON: identifier.
  5. The agent parses the JSON payload, prioritizing web page values to generate a concise, relevant summary for the user.

Moark Web Search Setup

To integrate this search capability into your workflow, first ensure you have the requests library installed via pip. You will also need a valid Gitee AI API key.

pip install requests

Set your API key as an environment variable to simplify execution:

export GITEEAI_API_KEY="your_api_key_here"

Run a test search using the bundled script:

python scripts/perform_web_search.py \
  --query "latest AI trends 2026" \
  --summary true \
  --freshness oneMonth \
  --count 5

Moark Web Search Data Schema & Taxonomy

The skill organizes its output through a structured JSON format to ensure machine-readability. The primary data points extracted include:

Field Description
webPages.value The primary list of webpage results containing snippets and URLs.
images Metadata for relevant image search results when requested.
videos Metadata for video content discovered via the query.
freshness Metadata indicating the time-range filter applied to the results.
summary Optional AI-generated summary of the search result content.

Moark Web Search Advanced Features

  • Flexible Freshness Filtering: Narrow results by oneDay, oneWeek, oneMonth, or oneYear for high-relevance discovery.
  • Multimedia Support: Explicitly toggle between webpage, image, or video search modes based on user intent.
  • Integrated Summarization: Built-in flags to return pre-summarized content, reducing the token overhead for the calling LLM.
  • Environment Variable Integration: Seamlessly hooks into Openclaw Skills architecture by automatically reading GITEEAI_API_KEY.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*