Chanai Search Workflow for Openclaw

A sophisticated dual-route search engine for AI agents that intelligently navigates Chinese and international web landscapes.

cfyuanyi
v1.0.0
Mar 13, 2026
0
895
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install chanai-search-workflow

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 chanai-search-workflow 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 Chanai Search Workflow?

Chanai Search Workflow is a robust framework designed for Openclaw Skills to handle complex external information retrieval. It serves as a specialized alternative to local memory recall, focusing exclusively on public-web data including news, travel, e-commerce, and technical documentation. By classifying user intent and detecting dynamic real-time topics, the skill ensures that AI agents provide the most relevant and reliable information available.

The system distinguishes itself by using a tiered routing strategy. It identifies whether a query requires a domestic-first approach for Chinese-specific content or a global-first approach for technical or international research. This ensures high precision in results while maintaining a fallback mechanism to prevent dead ends during the search process.

Chanai Search Workflow Use Cases

  • Searching for real-time travel data like flights, hotel availability, and ticket pricing.
  • Researching technical documentation, GitHub repositories, and developer tutorials.
  • Monitoring Chinese consumer trends, local e-commerce prices, and community posts.
  • Gathering multi-perspective insights using the mixed global and domestic routing mode.
  • Verifying news and public-web information with reliability scoring.

How Chanai Search Workflow Works

  1. The workflow initiates via the run_search_workflow script to analyze the query intent and subtype.
  2. It assigns a search route based on the content: domestic-first, global-first, or mixed.
  3. The system generates starter URLs and prioritizes human-usable official sites over aggregators.
  4. If primary sources are blocked or yield weak results, it triggers a fallback strategy using alternative engines.
  5. Collected evidence is processed through a scoring script to determine data reliability.
  6. A final search report is generated using standardized templates to deliver a clear, structured response.

Chanai Search Workflow Setup

To integrate this skill into your Openclaw Skills environment, ensure you have the necessary Python environment configured. Use the following commands to get started:

# Navigate to the skill directory and run the entrypoint script
python3 scripts/run_search_workflow.py "your search query"

# For specific routing like Chinese flight information
python3 scripts/run_search_workflow.py "上海直飞赤峰航班价格"

Chanai Search Workflow Data Schema & Taxonomy

The skill utilizes a structured reference system to manage its logic and taxonomy:

Directory File Name Description
scripts/ query_router.py Handles initial intent and route classification.
references/ priorities.md Defines source hierarchy based on specific search scenarios.
references/ fallbacks.md Logic for switching search engines when primary routes fail.
references/ reliability-scoring.md Rubric for evaluating the quality of retrieved data.
references/ reporting-template.md Standardized formats for final information delivery.

Chanai Search Workflow Advanced Features

  • Dynamic Guard: Automatically detects high-volatility topics like inventory or stock prices to warn users of preliminary data.
  • Intelligent Routing: Swaps between domestic-first for local Chinese context and global-first for international research.
  • Automated Reliability Scoring: Built-in scripts to quantify the trustworthiness of web sources.
  • Multi-Source Synthesis: Merges findings from disparate domains (e.g., e-commerce and social community posts) into a unified report.
  • Direct-Site Entry: Uses templates to jump directly to official search interfaces, bypassing middle-man aggregators.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*