Kimi Web Search for Openclaw

An AI-powered web search tool that enables agents to fetch real-time information and news via the Moonshot/Kimi API.

henryzhuhr
v1.0.9
Mar 18, 2026
0
1.1k
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install kimi-websearch

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 kimi-websearch 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 Kimi Web Search?

Kimi Web Search is a specialized tool designed for AI agents to bridge the gap between their training data and the live internet. By leveraging the Moonshot AI platform, this skill allows agents to perform deep web searches, retrieve the most recent news, and verify facts that are beyond their internal knowledge cutoff. As a vital part of the Openclaw Skills ecosystem, it ensures that your automated workflows are grounded in current, verifiable information.

The skill is particularly effective for scenarios where accuracy and source attribution are paramount. It doesn't just return raw data; it facilitates structured analysis and encourages agents to provide summarized conclusions backed by original source URLs.

Kimi Web Search Use Cases

  • Obtaining real-time news updates on specific topics like finance or technology.
  • Verifying facts or checking the status of recent events.
  • Researching technical documentation or API changes that occurred after the model's training date.
  • Providing categorized summaries of daily global or domestic news highlights.

How Kimi Web Search Works

  1. The agent analyzes the user's request and formulates a precise, single-sentence search query.
  2. The web search script is invoked using either Kimi or Moonshot API credentials.
  3. The tool crawls the web to gather relevant information based on the optimized query.
  4. Search results are processed, summarized, and categorized into relevant sections.
  5. The final output is presented to the user with mandatory source citations and direct links.

Kimi Web Search Setup

To integrate this into your Openclaw Skills environment, you must provide a Moonshot API key. You can obtain one from the Moonshot AI console.

# Set your environment variables
export MOONSHOT_API_KEY="your_api_key"

# Install dependencies
pip install "openai>=1.0.0"

# Execute a search
python3 scripts/web_search.py "your search query"

If your environment supports uv, you can run the script using uv run scripts/web_search.py.

Kimi Web Search Data Schema & Taxonomy

The skill produces structured outputs focused on clarity and citation. Data is organized as follows:

Component Requirement Description
Conclusion Required A summarized answer prioritized for the user.
Source URLs Required Direct links to the original web pages for verification.
News Categories Optional Labels such as Today's News, International, Finance, or Tech.
Validity Note Optional A warning if the search results appear incomplete or outdated.

Kimi Web Search Advanced Features

  • Smart query refinement to avoid ambiguous search results.
  • Automatic news categorization for broad queries like "today's news."
  • Support for the uv package manager for optimized script execution.
  • Seamless integration with other Openclaw Skills for multi-step research and analysis agents.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*