Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Fix: Added proper output formatting for error cases in Codex mode. Improved error handling when OPENAI_API_KEY is not set.
What This Skill Does
Routes search queries between Brave API and OpenAI Codex based on query complexity. Simple factual questions go to Brave (free, sub-2-second responses), while comparison, analysis, and multi-source questions route to OpenAI Codex. Mode selection is automatic but can be overridden with --mode flags.
Auto-routing between a free fast API and a paid reasoning model keeps costs proportional to query complexity without requiring manual tool selection.
When to use it
- Looking up quick facts without spending API credits
- Comparing two software frameworks with in-depth analysis
- Searching for recent academic papers on a research topic
- Running batch searches across mixed-complexity queries
- Pulling latest news with automatic backend selection
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: compare LangChain vs LlamaIndex in detail
- 1Analyze query for complexity keywords such as 'compare' and 'in detail'
- 2Score query above threshold (3+) using NLP keyword and length rules
- 3Route to OpenAI Codex (gpt-5-codex) for deep analysis
- 4Fetch multi-source synthesis via OpenAI Chat Completions API
- 5Return structured markdown comparison
Detailed multi-source comparison of LangChain and LlamaIndex covering architecture, use cases, and tradeoffs
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.